free-zone

Zustand state management for React. Covers stores, actions, and persistence. Use for simple global state management. USE WHEN: user mentions "zustand", "global state", "store", asks about "simple state management", "lightweight state", "create store", "persist state", "middleware", "devtools integration" DO NOT USE FOR: server data - use `tanstack-query` or `swr` instead; Vue apps - use `pinia`; complex async workflows - use `redux-toolkit`

Zod TypeScript schema validation library for runtime type checking. USE WHEN: user mentions "Zod", "schema validation", "form validation", "API validation", "type-safe validation", asks about "runtime validation", "React Hook Form validation" DO NOT USE FOR: Yup projects (use yup skill), class-validator/NestJS DTOs (use class-validator skill), PropTypes, compile-time only validation

Zero-downtime deployment strategies and automation: blue-green, rolling, and canary deployments with Nginx upstream switching, symlink-based atomic deploys, rsync deploy scripts, GitHub Actions SSH deploy workflows, health check polling, and rollback runbooks. USE WHEN: - Implementing blue-green deployment with Nginx upstream swapping - Writing a production deploy script with symlink-based atomic release management - Configuring canary traffic splitting with Nginx split_clients - Setting up a GitHub Actions workflow that deploys via SSH with health check polling - Writing or testing a rollback runbook - Planning database migration strategy alongside zero-downtime deploys DO NOT USE FOR: - Kubernetes rolling updates and canary with Argo Rollouts (use the kubernetes skill) - Container image building and registry management (use the docker skill) - Cloud-specific deployment (AWS CodeDeploy, GCP Cloud Deploy — use the cloud skill) - Frontend-only CDN cache invalidation strategies

Yup schema validation library. Popular with Formik for form validation. Use when building forms with React/Formik or needing schema-based validation. USE WHEN: user mentions "Yup", "Formik validation", asks about "yup schema", "Formik setup", "form validation library" DO NOT USE FOR: Zod projects (use zod skill), NestJS/class-validator (use class-validator skill), new projects (prefer Zod)

xUnit.net testing framework with Fact, Theory, fixtures, DI, and mocking with Moq and NSubstitute. Covers .NET testing best practices. USE WHEN: user mentions "xUnit", ".NET testing", "Fact", "Theory", "InlineData", "Moq", "NSubstitute", "C# unit test" DO NOT USE FOR: NUnit - use `nunit`, Vitest - use `vitest`, Jest - use `jest`, Playwright - use `playwright`

WireGuard VPN setup on Linux. Covers server config, client config, key management, NAT/IP forwarding, peer management, split tunnel, full tunnel, and site-to-site. USE WHEN: user mentions "wireguard", "wg0", "wg-quick", "wireguard vpn", "wireguard server setup", "wireguard peer", "wireguard keys", "wireguard client", "wireguard nat", "wireguard iptables", "wireguard split tunnel", "wireguard qr code", "wg genkey", "wireguard site-to-site", "wireguard keepalive" DO NOT USE FOR: OpenVPN setups - different tool and protocol, IPsec / IKEv2 VPNs, Tailscale or Netbird (they use WireGuard underneath but have their own CLIs), Cloud VPN gateways (AWS VPN, GCP Cloud VPN)

Winston - versatile logging library for Node.js with multiple transports, custom formatting, and log rotation. Supports structured logging, custom levels, and enterprise integration. USE WHEN: user mentions "winston", "node.js logging", "multiple transports", "log rotation", asks about "how to log to multiple destinations", "rotate log files in Node.js", "custom log formats" DO NOT USE FOR: Pino logging - use `pino` instead, Python logging - use `python-logging` instead, Java logging - use `slf4j` or `logback` instead

WebRTC peer-to-peer communication. Signaling, ICE/STUN/TURN, media streams, data channels, screen sharing, and SFU integration (mediasoup, LiveKit). USE WHEN: user mentions "WebRTC", "video call", "peer-to-peer", "P2P", "screen sharing", "data channel", "STUN", "TURN", "mediasoup", "LiveKit" DO NOT USE FOR: server-to-client streaming - use `sse`; chat messaging - use `socket-io`

Webpack module bundler. Covers configuration, loaders, plugins, optimization. Use when working with Webpack-based projects or migrating from Webpack. USE WHEN: user mentions "Webpack", "webpack.config", "webpack loaders", "webpack plugins", asks about "Webpack configuration", "bundle optimization" DO NOT USE FOR: Vite projects (use vite skill), esbuild (use esbuild skill), new projects (prefer Vite), Parcel

Webhook patterns for sending and receiving. Signature verification, retry logic, idempotency, payload design, and webhook infrastructure. Covers Stripe, GitHub, Slack webhook consumption and custom webhook dispatch. USE WHEN: user mentions "webhook", "webhook endpoint", "webhook signature", "event callback", "HTTP callback", "webhook retry", "webhook dispatch" DO NOT USE FOR: WebSocket real-time - use `socket-io` or `sse`; message queues - use messaging skills

WebAuthn/FIDO2 passwordless authentication. Passkeys, registration and authentication ceremonies, SimpleWebAuthn library, resident credentials, and platform/cross-platform authenticators. USE WHEN: user mentions "WebAuthn", "FIDO2", "passkey", "passwordless", "biometric login", "security key", "fingerprint login", "SimpleWebAuthn" DO NOT USE FOR: password-based auth - use `jwt` or `oauth2`; magic links - different flow; OAuth social login - use `oauth2`

Web scraping for RAG ingestion. Covers Firecrawl API, Crawl4AI (open source), trafilatura (main-content extraction), BeautifulSoup + readability-lxml, Scrapy for large crawls, Playwright for JS-rendered pages, sitemap.xml discovery, robots.txt, polite crawling, anti-bot, and deduplication. USE WHEN: user mentions "web scraping", "crawl website", "Firecrawl", "Crawl4AI", "trafilatura", "readability", "BeautifulSoup", "Scrapy", "Playwright scrape", "sitemap", "robots.txt", "crawl for RAG", "extract article" DO NOT USE FOR: parsing already-downloaded HTML files for layout - use `unstructured-io`; PDF downloads from the web - use `pdf-extraction`; office docs behind login - use `office-docs`; structured markdown vaults - use `markdown-structured`

Advanced Weaviate 1.27+ features. Native hybrid (BM25+vector) search, modules (reranker, generative), multi-tenancy, replication, compression (PQ / BQ / SQ), async indexing, sharding, and Weaviate Cloud vs self-hosted tradeoffs. USE WHEN: user mentions "Weaviate", "hybrid BM25", "weaviate multi-tenant", "weaviate reranker", "weaviate generative", "weaviate compression", "PQ BQ SQ weaviate" DO NOT USE FOR: basic vector DB usage - use `ai-integration/vector-databases`; other stores - use other `vector-stores/*`

User-Mode Driver Framework v2 (UMDF). User-mode driver model that uses the same WDF object model as KMDF but runs in a host process (WUDFHost.exe) protected by the reflector. Required for some categories (Indirect Display Drivers, many sensor and camera drivers) and recommended for any driver that doesn't strictly need kernel mode. USE WHEN: user mentions "UMDF", "WUDFHost", "user-mode driver", "reflector", "IDD", "ISensor", "WDFHOST", "UMDF v2", "FX2" DO NOT USE FOR: KMDF (use `wdf-kmdf`), classic UMDF v1 (deprecated, COM-based)

Kernel-Mode Driver Framework (KMDF), the Microsoft-recommended way to write Windows kernel-mode drivers. Covers DriverEntry, EvtDeviceAdd, IRPs and IOCTLs, I/O queues, PnP and Power state machines, IRQL discipline, memory pools, WPP tracing, SAL annotations, and Driver Verifier. USE WHEN: user mentions "KMDF", "WDF kernel", "Windows kernel driver", "DriverEntry", "WdfDriverCreate", "EvtDeviceAdd", "IRP", "IOCTL", "DISPATCH_LEVEL", "PASSIVE_LEVEL", "NTSTATUS", "PoolTag", "WdfRequestComplete" DO NOT USE FOR: UMDF v2 (use `wdf-umdf`), classic WDM-only drivers, file-system filters (FltMgr is a separate framework)

WCAG 2.2 Web Content Accessibility Guidelines. Covers conformance levels A/AA/AAA, success criteria, testing with axe-core, and common accessibility patterns. USE WHEN: user mentions "accessibility", "a11y", "WCAG", "screen reader", "ARIA", asks about "color contrast", "keyboard navigation", "accessible forms", "compliance", "ADA", "Section 508" DO NOT USE FOR: automated testing implementation - use `axe-core` instead

Warp Rust web framework using filters. Covers routing, filters, rejection, WebSocket, and TLS. Use for composable, type-safe Rust APIs. USE WHEN: user mentions "warp", "rust filters", "composable rust api", asks about "warp filters", "warp rejection", "filter composition rust", "rust hyper warp", "warp websocket" DO NOT USE FOR: Axum projects - use `axum` instead, Actix-web projects - use `actix-web` instead, Rocket projects - use `rocket` instead, non-Rust backends

Web Application Firewall configuration. Covers ModSecurity v3 with Nginx and Cloudflare WAF: managed rulesets, custom rules, rate limiting, and tuning. USE WHEN: user mentions "waf", "web application firewall", "modsecurity", "owasp crs", "core rule set", "cloudflare waf", "cloudflare firewall rules", "cloudflare rate limiting", "cloudflare custom rules", "modsecurity nginx", "secruleengine", "false positive waf", "waf exclusion", "waf bypass", "cloudflare bot fight mode", "cloudflare managed ruleset", "waf tuning" DO NOT USE FOR: Network-layer firewalls (iptables, nftables, ufw) — those are not WAF, DDoS volumetric protection at ISP level, API authentication / authorization — use `authentication` skill, Input validation in application code — use application-level validation

Vue 3 with Composition API. Covers reactivity, composables, lifecycle hooks, and component patterns. USE WHEN: user mentions "Vue", "Composition API", "composables", "ref", "reactive", "v-model", "v-if", "v-for", asks about "Vue 3 patterns", "reactive state in Vue" DO NOT USE FOR: Vue 2 Options API - use legacy Vue documentation instead, React - use `frontend-react`, Angular - use `angular`, Svelte - use `svelte`

Vitest testing framework. Covers unit tests, mocking, and coverage. Use for testing Vite-based and Node.js projects. USE WHEN: user mentions "vitest", "vite test", "unit test", asks about "vi.fn", "vi.mock", "test coverage", "mock functions", "test vite project" DO NOT USE FOR: E2E tests - use `playwright` instead; React component testing - combine with `testing-library`; Jest projects - use `jest` instead

Vite frontend build tool and dev server. Fast HMR and optimized builds. USE WHEN: user mentions "Vite", "vite config", "vite.config", asks about "Vite setup", "Vite dev server", "Vite build", "fast HMR" DO NOT USE FOR: Webpack projects (use webpack skill), Next.js (uses its own bundler), Create React App (uses Webpack), library builds with Rollup only

UX visual hierarchy principles. Covers fluid typography scales, spatial layout, color contrast, cognitive load reduction, and user scanning patterns. USE WHEN: user mentions "visual hierarchy", "typography", "type scale", "color system", "cognitive load", "whitespace", "layout", "information architecture", "visual weight", "readability", "scanning pattern", "F-pattern", "progressive disclosure" DO NOT USE FOR: WCAG compliance auditing (use accessibility/wcag), Tailwind-specific utility classes (use styling/tailwindcss), component library APIs (use styling/shadcn-ui or styling/radix-ui)

Virtualization and isolation architecture: hypervisors (type-1/type-2), container internals (namespaces, cgroups), microVMs, and the isolation-vs-overhead spectrum. Architect-level choice of isolation boundary. USE WHEN: choosing an isolation/virtualization boundary, "hypervisor", "KVM", "type-1/type-2", "container", "namespaces", "cgroups", "microVM", "Firecracker", "gVisor", "Kata", multi-tenant isolation, sandboxing untrusted workloads. DO NOT USE FOR: Kubernetes/Docker operational config (use infrastructure skills); OS internals (use `os-kernel-architecture`).

Video ingestion for multimodal RAG. Covers keyframe extraction (ffmpeg, PySceneDetect), audio-track transcription via Whisper, visual embeddings per keyframe (CLIP, SigLIP, VoyageAI multimodal), multi-modal retrieval combining visual + transcript hits, timestamp-anchored citations, and YouTube transcript ingestion. USE WHEN: user mentions "video RAG", "video transcription", "keyframe extraction", "PySceneDetect", "ffmpeg scenes", "CLIP embeddings", "SigLIP", "VoyageAI multimodal", "YouTube transcript", "multimodal retrieval", "video chunking" DO NOT USE FOR: audio-only content (podcasts, meetings) - use `audio-transcription`; screen recordings that are effectively slide decks - use `office-docs` on the source PPTX; static images - use `ocr` or pure vision embeddings

Vespa hybrid retrieval and ranking. BM25 + ANN + ColBERT late interaction in one query, ranking phases (match-phase, first-phase, second-phase, global-phase), tensor expressions, cloud vs self-hosted, schema definition (.sd files), embedding in-cluster, scale to billions. USE WHEN: user mentions "Vespa", "Vespa schema", "Vespa ranking", "vespa.ai", "tensor ranking", "Vespa hybrid", "Vespa cloud" DO NOT USE FOR: other vector stores - use `vector-stores/*` siblings; ColBERT without Vespa - use `retrieval/colbert-retrieval`; classical reranking - use `rag/reranking`

Vector compression techniques: scalar quantization (int8, int4), binary quantization (bit vectors + Hamming), product quantization (PQ), optimized PQ, residual quantization. Covers rescoring workflow, storage math, accuracy tradeoffs, and Faiss/Qdrant/pgvector implementations. USE WHEN: user mentions "quantization", "int8 embeddings", "binary embeddings", "product quantization", "PQ", "OPQ", "residual quantization", "Hamming distance", "compress embeddings", "rescoring" DO NOT USE FOR: Matryoshka dimension truncation - use `matryoshka-embeddings`; ANN algorithm choice - use `ann-algorithms`

Vector database integration for embeddings and similarity search. Pinecone, Weaviate, Qdrant, ChromaDB, pgvector. Index management, metadata filtering, hybrid search, and production optimization. USE WHEN: user mentions "vector database", "embeddings", "similarity search", "Pinecone", "Weaviate", "Qdrant", "ChromaDB", "pgvector", "HNSW", "ANN" DO NOT USE FOR: LangChain integration - use `langchain`; RAG architecture - use `rag-patterns`; traditional databases - use database skills

Unstructured.io library for partitioning documents by filetype (PDF, DOCX, HTML, EPUB, PPT, email). Covers partition strategies (fast, hi_res, ocr_only, auto), chunking by title, metadata extraction, and serverless API usage. USE WHEN: user mentions "unstructured.io", "unstructured library", "partition documents", "multi-format ingestion", "DOCX to chunks", "HTML to RAG", "EPUB parser", "PPT extraction" DO NOT USE FOR: PDF-specific layout - use `pdf-extraction`; pure OCR work - use `ocr`; table-specific extraction - use `table-extraction`

Unity XR — XR Interaction Toolkit 3.x (Interactor/Interactable/Manipulation), AR Foundation (planes, anchors, image tracking, body tracking), OpenXR, hand tracking on Quest/Vision OS. USE WHEN: VR/AR/MR projects, integrating XR controllers, AR plane detection, XR locomotion, hand tracking, eye tracking, OpenXR features. DO NOT USE FOR: regular 3D gameplay (use `unity-physics-anim`); rendering pipeline (use `unity-rendering` — XR has URP-specific considerations).

Unity Test Framework — EditMode + PlayMode tests, [UnityTest] coroutines, Test Runner, mocking patterns, Unity.PerformanceTesting package. USE WHEN: writing/debugging tests, setting up CI test runs, performance regression tests, asserting scene state, mocking time/input. DO NOT USE FOR: runtime in-game telemetry (use `unity-performance` for profiling); end-to-end automation (use editor tooling + custom harness).

Unity rendering pipelines (Built-in / URP / HDRP), Shader Graph, Renderer Features, Volume framework, post-processing, materials, lighting, and GPU Resident Drawer. USE WHEN: choosing or migrating rendering pipeline, writing/editing shaders (Shader Graph, HLSL, ShaderLab), tuning lighting, debugging draw calls, configuring Volume profiles, custom render passes. DO NOT USE FOR: 2D Renderer specifics (use `unity-2d-lighting`); UI Toolkit rendering (use `unity-input-ui`); profiling-only questions (use `unity-performance`).

Unity 3D physics (Rigidbody, Collider, Joints) and animation (Animator state machines, parameters, layers, Animation Rigging, Humanoid retargeting, blend trees). USE WHEN: tuning rigidbody movement, designing Animator state machines, blending animations, layer collision matrix, joints/constraints, motion warping, IK setups. DO NOT USE FOR: 2D physics or 2D animation (use `unity-2d-physics` / `unity-2d-animation`); ECS physics (use `unity-dots`).

Unity performance — Profiler, Frame Debugger, Memory Profiler, GC allocation hunting, object pooling, IL2CPP build settings, Burst, batching, LOD, GPU Resident Drawer. USE WHEN: frame drops, GC spikes, long load times, memory growth, draw-call storms, mobile thermal/battery issues, profiling captures. DO NOT USE FOR: gameplay logic refactoring (use `unity-core`); pipeline selection (use `unity-rendering`).

Unity Netcode for GameObjects (NGO) — NetworkBehaviour, NetworkVariable, RPCs (Server/Client/Owner), client-side prediction, lag compensation, Multiplay/Relay/Lobby integration. USE WHEN: building multiplayer (co-op, competitive, MMO-lite), network authority decisions, anti-cheat, matchmaking + relay. DO NOT USE FOR: P2P state-sync without NGO (Mirror, Photon — out of scope); ECS-native networking (NetCode for Entities — adjacent stack).

Unity new Input System and UI — InputAction, InputActionAsset, PlayerInput, rebinding, multi-device, plus UI Toolkit (UXML/USS, runtime + editor) and uGUI Canvas optimization. USE WHEN: wiring input bindings, supporting gamepads/keyboard/touch, building menus/HUD with UI Toolkit or uGUI, optimizing Canvas batches, runtime rebinding, on-screen control overlays. DO NOT USE FOR: legacy `Input.GetKey` API (deprecated — migrate to new Input System); 3D world-space UI specifics (use `unity-rendering`).

Unity Editor scripting — custom Inspectors, PropertyDrawers, EditorWindow, MenuItems, asset post-processors, Editor Coroutines, automated builds via `-batchmode -executeMethod`. USE WHEN: building tools for designers, custom Inspector UI, gizmos, scene validators, asset import hooks, editor menu commands, headless CI builds. DO NOT USE FOR: runtime UI (use `unity-input-ui`); test runner (use `unity-testing`).

Unity DOTS — Entities 1.x, Burst-compiled jobs, IJobChunk / IJobEntity, NativeArray / NativeList, SystemBase vs ISystem, baking GameObject to entity, hybrid components. USE WHEN: massive entity counts (RTS, swarms, particles-as-entities), data-oriented refactor of hot simulations, deterministic netcode targets, Burst-friendly math. DO NOT USE FOR: regular GameObject gameplay (use `unity-core`); rendering (DOTS uses Entities Graphics — link from `unity-rendering`); networking with NGO (use `unity-netcode`).

Unity core scripting fundamentals — MonoBehaviour lifecycle, GameObject / Component model, ScriptableObjects, prefabs, serialization, coroutines, events, and execution order. USE WHEN: writing or refactoring core Unity scripts, designing data flow, setting up ScriptableObjects, dealing with serialization issues, choosing between Update / FixedUpdate / LateUpdate, coroutine vs async patterns. DO NOT USE FOR: rendering / shaders (use `unity-rendering`); 2D-specific topics (use `unity-2d-*`); networking (use `unity-netcode`); ECS/DOTS (use `unity-dots`).

Unity builds — IL2CPP vs Mono, build profiles, addressables-aware builds, Android (Gradle, AAB, Play Asset Delivery), iOS (Xcode post-processing, capabilities), WebGL, console NDA paths (high-level only). USE WHEN: configuring build settings, fixing platform-specific issues, signing, store submission, build size optimization, multi-platform CI. DO NOT USE FOR: editor-side build code (use `unity-editor-tooling`); runtime perf (use `unity-performance`).

Unity project conventions — folder layout, asmdef structure, naming, source control (.gitignore + LFS + force text serialization), prefab variants, ScriptableObject-based architecture. USE WHEN: starting a new Unity project, refactoring an unhealthy one, setting up source control, organising assets, deciding on naming. DO NOT USE FOR: specific systems (use feature-specific skills).

Unity Addressables — AssetReference, async loading, labels, groups, build profiles, remote content, Cloud Content Delivery integration, content catalogs and updates. USE WHEN: replacing `Resources.Load`, async asset loading, scene streaming, remote content, DLC delivery, runtime asset hot-swap, splitting builds for size. DO NOT USE FOR: editor-time asset queries (use AssetDatabase); legacy Asset Bundles workflows (Addressables wraps them).

Unity 2D Tilemap — Grid + Tilemap, Rule Tiles, Animated Tiles, Tile Palette, Hexagonal/Isometric grids, Composite Collider 2D + Tilemap Collider 2D, procedural tilemap generation. USE WHEN: building level geometry from tiles, painting auto-tiling terrain, isometric/hex maps, optimising tilemap colliders, runtime tilemap generation. DO NOT USE FOR: free-form sprites (use `unity-2d-core`); platforming movement (use `unity-2d-gameplay`); 2D physics general topics (use `unity-2d-physics`).

Unity 2D physics — Rigidbody2D body types, Collider2D shapes, joints, effectors, layer collision matrix, contact filters, IEEE physics gotchas in 2D, raycast/overlap APIs. USE WHEN: tuning Rigidbody2D movement, joint setups (hinge/spring/distance/ slider), one-way platforms, conveyor belts, area effects, layered collisions, raycast queries. DO NOT USE FOR: 3D physics (use `unity-physics-anim`); platformer character movement (use `unity-2d-gameplay`); tilemap collision (use `unity-2d-tilemap`).

Unity 2D lighting — URP 2D Renderer, Light 2D types (Point/Freeform/Sprite/ Parametric/Global), Shadow Casters 2D, Sprite Mask, Renderer2DData, normal mapped sprites, blend styles. USE WHEN: setting up the URP 2D Renderer, lighting a 2D scene, adding 2D shadows, using Sprite Mask for stencil-like effects, normal-mapped sprites. DO NOT USE FOR: 3D lighting (use `unity-rendering`); UI lighting concepts (UI doesn't normally use Light 2D); 2D animation (use `unity-2d-animation`).

Unity 2D gameplay patterns — character controllers (kinematic vs dynamic), coyote time, jump buffer, variable jump height, ledge grab, dash, wall slide, hitstop, juice patterns, top-down 8-way movement. USE WHEN: implementing platformer / metroidvania / top-down character controllers, "feel" tuning, ability layers (dash/double jump/wall slide). DO NOT USE FOR: 2D physics fundamentals (use `unity-2d-physics`); animations (use `unity-2d-animation`); cameras (use `unity-2d-cameras`).

Unity 2D fundamentals — Sprite Renderer, Sprite Atlas v2 (master/variants), 9-slice rendering, Sorting Layers vs Order in Layer vs Sorting Group, sprite import settings, Pixels Per Unit (PPU), Pixel Perfect Camera, point filtering. USE WHEN: importing sprites, packing atlases, controlling draw order in 2D, setting up pixel-art rendering, configuring 9-slice UI/decorations. DO NOT USE FOR: Tilemap (use `unity-2d-tilemap`); 2D physics (use `unity-2d-physics`); animation (use `unity-2d-animation`); 2D Lights (use `unity-2d-lighting`).

Unity 2D cameras — Cinemachine 2D (CinemachineCamera, Confiner 2D, Framing Transposer, Group Composer), Pixel Perfect Camera, parallax via cameras vs sprites, screen shake, target groups, virtual camera priorities. USE WHEN: setting up smooth 2D camera follow, framing rules, level-bound confiners, dynamic groups (multiple players), screen shake, pixel-perfect rendering of camera motion. DO NOT USE FOR: 3D Cinemachine (covered separately under unity-rendering / unity-physics-anim); UI cameras (use `unity-input-ui`).

Unity 2D Animation — sprite sheet frame-by-frame, skeletal 2D animation (bones + skinning + IK), PSD Importer, Aseprite Importer, Sprite Library / Resolver for character variants. USE WHEN: animating characters/enemies, swapping outfits, IK for arms/legs, importing layered art (PSB/PSD/Aseprite), 2D rigging. DO NOT USE FOR: tilemap animation (use `unity-2d-tilemap` Animated Tile); 3D character animation (use `unity-physics-anim`); UI animations (use `unity-input-ui`).

UniFFI by Mozilla — generates idiomatic Kotlin, Swift, Python, and Ruby bindings from a Rust crate. Covers UDL definition, proc-macro mode, async support, callback interfaces, error handling, custom types, and the Kotlin Multiplatform fork (uniffi-kotlin-multiplatform-bindings) used by BDK, Breez SDK, CDK, LWK. USE WHEN: user mentions "UniFFI", "Rust to Kotlin", "Rust to Swift", "FFI bindings", "uniffi-rs", "UDL file", "uniffi-bindgen", "BDK bindings", "Breez SDK bindings", "kotlin-multiplatform-bindings", "Mozilla UniFFI" DO NOT USE FOR: Raw C FFI - use `languages/swift` interop quick-ref + Rust core DO NOT USE FOR: WebAssembly bindings - use wasm-bindgen DO NOT USE FOR: Flutter/Rust bridge - use `flutter_rust_bridge` skill if exists DO NOT USE FOR: React Native - use `uniffi-bindgen-react-native` (out of scope here)

TypeScript and JavaScript application security across frontend and backend code. USE WHEN: securing TypeScript/JavaScript applications, reviewing frontend/backend code for vulnerabilities DO NOT USE FOR: code quality issues (use `typescript-quality`), general TypeScript patterns, styling

Reviewing TypeScript code - what to flag, and what the compiler and linter already flag for you USE WHEN: you are reviewing, critiquing or auditing existing TypeScript or TSX code - a "code review", a "review" of a .ts/.tsx file, a diff, a PR or a pull request; deciding what to comment on in TypeScript; avoiding false positives on typed JavaScript DO NOT USE FOR: writing, explaining or learning TypeScript - use `languages/typescript`; anything `tsc` under `strict` or a default typescript-eslint run already reports (this skill lists those so you can stay silent about them); React-specific review - pair with the React skills; lint rule configuration - use `quality/typescript-eslint`

TypeScript/JavaScript code quality with ESLint, Biome, and strict TypeScript. Covers linting, formatting, type safety, and best practices. USE WHEN: user works with "TypeScript", "JavaScript", "ESLint", "Biome", asks about "TS strict mode", "type safety", "linting rules", "code formatting" DO NOT USE FOR: SonarQube - use `sonarqube` skill, testing - use Vitest/Jest skills, security - use security skills

typescript-eslint - ESLint plugin for TypeScript USE WHEN: user mentions "typescript-eslint", "TypeScript linting", "type-aware rules", asks about "no-floating-promises", "TypeScript ESLint config", "@typescript-eslint rules" DO NOT USE FOR: ESLint 9 full setup - use `eslint-biome` skill, Biome - use `eslint-biome`, general quality - use `quality-common`

TypeScript language. Covers types, generics, and advanced patterns. Use when writing type-safe JavaScript code. USE WHEN: user mentions "typescript", "types", "generics", asks about "type safety", "type errors", "tsconfig", "utility types", "type guards", "branded types" DO NOT USE FOR: reviewing existing TypeScript code - use `review/typescript`, which covers the defects `tsc` and typescript-eslint do not report DO NOT USE FOR: Plain JavaScript without types - use `javascript` skill instead DO NOT USE FOR: Node.js runtime - use `nodejs` skill instead DO NOT USE FOR: Framework-specific typing - use framework skills (React, Vue, etc.)

TypeORM for TypeScript/JavaScript. Covers entities, repositories, and relations. Use with SQL databases. USE WHEN: user mentions "typeorm", "@Entity", "Repository", "DataSource", "QueryBuilder", "typeorm migration", asks about "decorators for database", "active record pattern", "entity relationships", "typeorm relations" DO NOT USE FOR: Prisma projects - use `prisma` skill; Drizzle - use `drizzle` skill; SQLAlchemy (Python) - use `sqlalchemy` skill; raw SQL - use `database-query` MCP; NoSQL - use `mongodb` skill; Sequelize - not supported

End-to-end type safety patterns for API development. Covers Zod-to-OpenAPI, ts-rest, Zodios, and contract testing. Use for ensuring type consistency between backend and frontend. USE WHEN: user mentions "type-safe API", "end-to-end types", "Zod to OpenAPI", "ts-rest", "Zodios", "contract testing", asks about "share types between frontend and backend", "type safety across API", "API contract", "Pact testing" DO NOT USE FOR: tRPC (use `trpc` instead); GraphQL (use `graphql` instead); Simple OpenAPI generation (use `openapi-codegen` instead); Non-TypeScript projects

Automatic type generation from OpenAPI and GraphQL schemas. Covers openapi-typescript, graphql-codegen, and contract sync. USE WHEN: user asks about "openapi-typescript", "graphql-codegen", "generate types from API", "type generation", "API types", "schema to TypeScript" DO NOT USE FOR: manual type definitions - use TypeScript skills, contract validation - use `openapi-contract` skill

txtai — lightweight, SQLite-backed embeddings + semantic search + pipeline framework. Covers Embeddings index, pipelines (summarization, translation, QA), workflows, graph support, agents, and edge/on-device deployment with small models. USE WHEN: user mentions "txtai", "SQLite embeddings", "lightweight RAG", "on-device RAG", "edge RAG", "txtai pipeline", "txtai workflow" DO NOT USE FOR: heavy Pinecone stacks - use `canopy`; full KG/agent platforms - use `r2r`; large LangChain/LlamaIndex apps - use `langgraph-rag`/`llamaindex`

Turborepo high-performance monorepo build system. Intelligent caching and task orchestration. Use when managing monorepos with complex build dependencies. USE WHEN: user mentions "Turborepo", "turbo.json", "turbo build", asks about "monorepo caching", "Turbo configuration", "remote cache" DO NOT USE FOR: Nx monorepos (use nx skill), single-package projects, Lerna (deprecated), Rush

Turbine — small Kotlin testing library for kotlinx.coroutines Flows. Provides ergonomic API to test Flow emissions deterministically: awaitItem, expectMostRecentItem, awaitComplete, awaitError. Works with StateFlow, SharedFlow, Channel-backed flows, combine/map/debounce. KMP-friendly. USE WHEN: user mentions "Turbine", "app.cash.turbine", ".test {}", "awaitItem", "Flow testing", "StateFlow test", "SharedFlow test", "expectMostRecentItem", "cancelAndIgnoreRemainingEvents" DO NOT USE FOR: Mobile E2E - use `testing/maestro` DO NOT USE FOR: Compose snapshot - use `testing/compose-snapshot` DO NOT USE FOR: Generic Kotlin testing - use `testing/kotest` DO NOT USE FOR: Suspend function (non-Flow) testing - use `kotlinx-coroutines-test` directly

Microsoft SQL Server T-SQL procedural language. Covers stored procedures, functions, triggers, error handling, and SQL Server-specific features. Use for SQL Server database server-side programming. USE WHEN: user mentions "tsql", "T-SQL", "SQL Server procedures", "SQL Server functions", "TRY...CATCH", "THROW", "sp_executesql", "SSMS" DO NOT USE FOR: basic SQL Server SQL - use `sqlserver` instead, PostgreSQL - use `plpgsql` instead, Oracle - use `plsql` instead

tRPC for type-safe APIs. Covers routers, procedures, and React Query integration. Use for end-to-end type-safe APIs. USE WHEN: user mentions "tRPC", "type-safe API", "end-to-end types", "procedures", "tRPC router", "tRPC React Query", asks about "how to build type-safe API", "tRPC with Next.js", "tRPC middleware", "tRPC context" DO NOT USE FOR: REST APIs - use `rest-api` instead; GraphQL - use `graphql` instead; OpenAPI specs - use `openapi` instead; Non-TypeScript projects

Traefik v3 cloud-native reverse proxy. Covers providers, entrypoints, routers, middlewares, services, Docker labels, TLS/ACME, dashboard, and metrics. USE WHEN: user mentions "traefik", "traefik v3", "traefik docker", "traefik labels", "traefik middleware", "traefik dashboard", "traefik tls", "traefik acme", "traefik router", "traefik entrypoint", "traefik reverse proxy", "traefik cloudflare", "traefik let's encrypt", "traefik rate limit" DO NOT USE FOR: Caddy-based setups - use `caddy` skill, Nginx load balancing - use `load-balancer` skill, Kubernetes ingress with nginx-ingress - use `kubernetes` skill, Application-level TLS inside app code

Token optimization best practices for MCP server and tool interactions. Minimizes token consumption while maintaining effectiveness. USE WHEN: user mentions "token usage", "optimize tokens", "reduce API calls", "MCP efficiency", asks about "how to use less tokens", "MCP best practices", "limit output size", "efficient queries" DO NOT USE FOR: Code optimization - use `performance` instead, Text compression - this is about API usage patterns, Cost optimization (infrastructure) - use cloud/DevOps skills

Temporal awareness in RAG. Recency bias weighting, exponential decay scoring, time-range filtering, LLM-based date extraction ("last quarter", "yesterday"), temporal knowledge graphs, freshness vs authority tradeoff, event-based retrieval, timestamp metadata, differential reindexing of old vs fresh docs. USE WHEN: user mentions "time-aware RAG", "recency bias", "temporal retrieval", "freshness", "date filter", "temporal knowledge graph", "exponential decay" DO NOT USE FOR: static metadata filters generally - use `self-querying-retriever`; CDC for ingestion - use `cdc-streaming-ingestion`; evaluation of time-sensitive answers - use `rag-evaluation`

Thymeleaf template engine for Java/Spring. Covers HTML templates, expressions, fragments, i18n, and email templates. USE WHEN: user mentions "thymeleaf", "spring template", "HTML template Spring", "email template Java", "th:text", "th:each", "th:if", "fragments", "layout" DO NOT USE FOR: REST API JSON - use `spring-rest` skill, SPA frontend - use React/Vue/Angular skills, PDF generation - use JasperReports or iText

3D graphics in the browser with Three.js and React Three Fiber (R3F). Covers the R3F Canvas, core concepts, the useFrame loop, geometries, materials, lights and the @react-three/drei helpers. USE WHEN: user mentions "Three.js", "React Three Fiber", "R3F", "drei", "useFrame", "mesh", "3D scene", asks about rendering or animating 3D in a web page DO NOT USE FOR: 2D canvas drawing (use `canvas-webgl`), SVG (use `svg-animation`), DOM animation (use `framer-motion`)

Testing Library for UI testing. Covers queries, user events, and async utilities. Use for React/Vue component testing. USE WHEN: user mentions "testing library", "react testing", "component test", asks about "screen.getByRole", "userEvent", "render", "fireEvent", "waitFor", "accessibility testing" DO NOT USE FOR: E2E tests - use `playwright` or `cypress`; Unit tests - use `vitest` or `jest`; API testing - use framework HTTP clients; Non-UI logic - use unit testing

testcontainers-python specialist. Covers all container modules (PostgreSQL, MySQL, MongoDB, Redis, Kafka, RabbitMQ, MinIO, Elasticsearch, LocalStack), GenericContainer, wait strategies, Docker Compose, networks, pytest fixtures, and CI/CD integration. USE WHEN: user mentions "testcontainers", "docker in tests", "real database in tests", "test with real postgres/redis/kafka", asks about container fixtures or Docker-based testing. DO NOT USE FOR: Spring Boot testcontainers (Java) - use `spring-boot-integration`; Mocking HTTP - use `fastapi-testing`; Pure pytest patterns - use `pytest`

Testcontainers for Docker-based integration testing in Java. Covers database containers, messaging systems, and Spring Boot @ServiceConnection. USE WHEN: user mentions "testcontainers", "docker test", "integration test", asks about "@ServiceConnection", "PostgreSQLContainer", "MongoDBContainer", "test database", "docker compose test" DO NOT USE FOR: Unit tests - use `junit`; REST API tests - use `rest-assured`; Tests without Docker - use H2 or embedded databases; Non-Java projects - check language-specific tools

Terraform infrastructure as code. HCL syntax, providers (AWS, Azure, GCP), modules, state management, workspaces, and production patterns. USE WHEN: user mentions "Terraform", "HCL", "infrastructure as code", "IaC", "terraform plan", "terraform apply", "tfstate", "OpenTofu" DO NOT USE FOR: Kubernetes manifests - use `kubernetes`; Docker - use `docker`; Pulumi - different IaC tool

High-performance serving of embedding and reranker models in production. Covers HuggingFace Text Embeddings Inference (TEI) on GPU, Docker deployment, ONNX/FP16 quantization, dynamic batching, NVIDIA Triton for co-serving embedding + reranker + LLM, and NVIDIA NIM as a managed alternative. Benchmarks and configs. USE WHEN: user mentions "TEI", "Text Embeddings Inference", "Triton", "Triton Inference Server", "NIM", "NVIDIA NIM", "embedding server", "reranker server", "ONNX embedding", "serve BGE", "serve E5" DO NOT USE FOR: vector DB serving - use `rag-architecture`; LLM serving in general - use provider-specific docs; cost tracking - use `cost-allocation`

Tauri framework for building cross-platform desktop applications with Rust backend and web frontend. Covers architecture, IPC commands, plugins, bundling, code signing, and security best practices. USE WHEN: user mentions "Tauri", "Rust desktop app", asks about "Tauri commands", "Tauri plugins", "Tauri IPC", "Rust + Svelte/React", "lightweight desktop app", "Tauri bundling", "Tauri security" DO NOT USE FOR: Electron applications - use `electron` skill instead

TanStack Router for React with file-based routing. Covers route definitions, layouts, authentication guards, loaders, and type-safe navigation. USE WHEN: user mentions "TanStack Router", "file-based routing", "type-safe routing", "route loaders", "beforeLoad", asks about "TanStack Router patterns", "typed navigation" DO NOT USE FOR: React Router v6 - use React Router docs, Next.js App Router - use `react-server-components`, Vue Router, Angular Router

TanStack Query for data fetching. Covers queries, mutations, and caching. Use for server state management in React. USE WHEN: user mentions "tanstack query", "react query", "data fetching", "API calls", asks about "cache management", "mutations", "infinite scroll", "optimistic updates", "prefetching", "server state", "useQuery", "useMutation" DO NOT USE FOR: client state - use `zustand` or `redux-toolkit`; Vue apps - use `pinia` with composables; static data - use React context

Tailwind CSS utility framework. Covers utility classes, responsive design, and customization. Use for styling web applications. USE WHEN: user mentions "Tailwind", "utility CSS", "Tailwind classes", asks about "responsive design", "Tailwind config", "utility-first CSS" DO NOT USE FOR: CSS-in-JS (styled-components, emotion), CSS Modules only projects, traditional CSS/SCSS workflows, component libraries like Material-UI

Structured data + RAG. NL2SQL hybrid patterns (text-to-SQL then execute vs embed rows), table embedding strategies (row-level, schema-level, hybrid), semantic layer integration (Cube, dbt metrics), LangChain SQLDatabaseChain, LlamaIndex PandasQueryEngine, safe SQL execution (read-only, sandboxed), schema-aware retrieval. Full PostgreSQL + pgvector hybrid code. USE WHEN: user mentions "tabular RAG", "NL2SQL", "text to SQL", "RAG on tables", "database RAG", "SQL RAG", "semantic layer", "structured data RAG" DO NOT USE FOR: unstructured doc RAG - use `rag-architecture`; metadata filtering only - use `self-querying-retriever`; KG retrieval - use `graph-rag`

Table extraction from PDFs and images for RAG. Covers Camelot, Tabula, pdfplumber, TableTransformer (DETR), Amazon Textract Tables, Azure Document Intelligence. Conversion to markdown/CSV/JSON, merged-cell handling. USE WHEN: user mentions "table extraction", "PDF tables", "Camelot", "Tabula", "TableTransformer", "Textract tables", "Azure form recognizer tables", "markdown table for LLM" DO NOT USE FOR: general PDF text - use `pdf-extraction`; full OCR pipelines - use `ocr`

Systems-level networking architecture: kernel-bypass (DPDK, io_uring, eBPF/XDP), zero-copy, the network stack data path, NIC offloads, congestion control, and high-connection-count (C10M) server design. Architect-level, not app HTTP. USE WHEN: designing high-throughput/low-latency networking, packet processing, "kernel bypass", "DPDK", "io_uring", "eBPF", "XDP", "zero-copy", "C10M", "line rate", NIC offload, congestion control, software data plane. DO NOT USE FOR: REST/GraphQL API design (use api-design skills); app websockets (use real-time skills); cloud LB config (use infrastructure skills).

systemd unit file authoring and system management skill: service units, timer units, socket activation, drop-in overrides, journalctl, and security hardening options. USE WHEN: - Writing or modifying systemd service unit files for Node.js, Python, Go, or other apps - Setting up automatic restarts, dependency ordering, and environment variable loading - Creating timer units as a cron replacement for periodic tasks - Hardening a service with PrivateTmp, NoNewPrivileges, ProtectSystem=strict, etc. - Using drop-in overrides to modify upstream package-provided unit files - Debugging service startup failures, missing env vars, or timer misfires - Managing logs with journalctl (filtering, following, exporting) DO NOT USE FOR: - Docker container orchestration (use docker or kubernetes skill) - Application-level scheduling (job queues, cron-based business logic — use job-queues skill) - Full init system replacement on non-systemd distros (Alpine uses OpenRC) - Windows Task Scheduler or macOS launchd equivalents

SWR - React hooks for data fetching with caching. Lightweight alternative to TanStack Query for simple data fetching needs. USE WHEN: user mentions "swr", "stale-while-revalidate", "useSWR", asks about "simple data fetching", "real-time data", "automatic revalidation", "lightweight caching", "vercel data fetching" DO NOT USE FOR: Vue apps - use `pinia` or composables; complex cache management - use `tanstack-query`; client state - use `zustand`

Reviewing Swift code - what to flag, and what the compiler and SwiftLint already flag for you USE WHEN: you are reviewing, critiquing or auditing existing Swift code - a "code review", a "review" of a .swift file, a diff, a PR or a pull request; deciding what to comment on in Swift; avoiding false positives on Swift code DO NOT USE FOR: writing, explaining or learning Swift - use `languages/swift`; anything the compiler or a configured SwiftLint already reports (this skill lists those so you can stay silent about them); SwiftUI layout - use the SwiftUI material; Kotlin Multiplatform bridging - use `languages/uniffi`

Swift language fundamentals (5.10+ / 6.x). Covers optionals, value vs reference semantics, protocols & generics, Swift Concurrency (async/await, actors, Sendable, structured tasks), Result Builders, and Apple platform interop. USE WHEN: user mentions "Swift", "SwiftUI", "async/await Swift", "actor", "Sendable", "Codable", "Combine", "Result Builder", "Apple Keychain", "Secure Enclave", "iOS native" DO NOT USE FOR: reviewing existing Swift code - use `review/swift`, which covers retain cycles and the concurrency checking that is a per-target setting DO NOT USE FOR: SwiftUI screen layouts in depth - use SwiftUI-specific skill if exists DO NOT USE FOR: Compose iOS via Skia - use `frontend-frameworks/compose-multiplatform` DO NOT USE FOR: Kotlin/Native ↔ Swift bridging - use `languages/uniffi`

Swashbuckle and NSwag for ASP.NET Core API documentation. Covers XML comments, operation filters, and OpenAPI customization. USE WHEN: user mentions "Swagger", "Swashbuckle", "NSwag", ".NET OpenAPI", "API documentation", "Swagger UI", ".NET API docs" DO NOT USE FOR: Springdoc OpenAPI - use `springdoc-openapi`, generic OpenAPI spec - use `openapi`

Animating SVG with CSS, Framer Motion, GSAP and native SVG attributes. Covers SVG fundamentals, path `d` syntax, filters, generative SVG in React and animated gradients. USE WHEN: user mentions "SVG animation", "path morphing", "stroke-dasharray", "SVG filter", "animated icon", asks about animating an inline SVG or drawing a path on scroll DO NOT USE FOR: raster or pixel graphics (use `canvas-webgl`), 3D (use `three-js`), general component animation (use `framer-motion`)

SvelteKit full-stack Svelte framework. Covers routing, load functions, form actions, and server-side rendering. Use when building SvelteKit applications. USE WHEN: user mentions "SvelteKit", "Svelte Kit", asks about "+page.svelte", "load functions", "form actions in SvelteKit", "SvelteKit routing", "use:enhance", "hooks.server.ts", "SvelteKit adapters" DO NOT USE FOR: Svelte without SvelteKit - use `frontend-svelte` instead; Next.js - use `nextjs-app-router` instead; Nuxt - use `nuxt3` instead; Remix - use `remix` instead

Svelte 5 with runes reactivity system. Covers components, state management, and reactive declarations. USE WHEN: user mentions "Svelte", "runes", "$state", "$derived", "$effect", "SvelteKit", asks about "Svelte 5 patterns", "reactive runes" DO NOT USE FOR: Svelte 4 and earlier - use Svelte 4 documentation, React - use `frontend-react`, Vue - use `vue-composition`, Angular - use `angular`

Software supply chain security. Covers dependency management, SBOM generation, package integrity verification, and CI/CD security. OWASP A03:2025. USE WHEN: user mentions "supply chain", "dependencies", "npm audit", "SBOM", "vulnerable packages", asks about "dependency scanning", "lockfiles", "Dependabot", "typosquatting", "CI/CD security" DO NOT USE FOR: license compliance - use `license-compliance`, secrets - use `secrets-management`, general OWASP - use `owasp-top-10`

structlog - structured logging library for Python with native JSON support, context binding, and processor pipeline. Integrates with FastAPI, Django, and standard logging module. USE WHEN: user mentions "structlog", "python structured logging", "context binding", asks about "JSON logging python", "fastapi logging", "django structured logging" DO NOT USE FOR: Standard Python logging - use `python-logging` instead, Node.js logging - use `pino` or `winston`, Java logging - use `slf4j` or `logback` instead

Stripe payment processing. Covers Checkout Sessions, Payment Intents, Subscriptions, Webhooks, idempotency, and Stripe.js frontend integration. USE WHEN: user mentions "stripe", "payment", "checkout", "subscription billing", "payment intent", "payment gateway", "credit card", "invoice", "Stripe.js" DO NOT USE FOR: PayPal-only integration; cryptocurrency payments; accounting software

Streamlit Python web application framework. Covers session state, caching, layouts, widgets, multipage apps, and deployment. Use when building interactive Python data apps or dashboards. USE WHEN: user mentions "streamlit", "st.session_state", "st.cache_data", "streamlit app", "python dashboard", "python web app", "streamlit deploy", "streamlit form", "streamlit component" DO NOT USE FOR: FastAPI/Flask REST APIs, Django web apps, Jupyter notebooks

Streaming LLM responses with inline citations. Token-level source attribution, SSE vs WebSocket, TTFT optimization, progressive disclosure (retrieval status then tokens), Python async generators, Vercel AI SDK streaming with sources, LangChain streaming callbacks, client-side citation rendering. USE WHEN: user mentions "streaming RAG", "streaming citations", "SSE RAG", "TTFT", "progressive disclosure", "AI SDK streaming", "token streaming", "inline citations" DO NOT USE FOR: generic RAG pipelines - use `rag-architecture`; citation correctness evaluation - use `rag-evaluation`; conversational memory - use `conversational-rag`

Storage-engine and database-internals architecture: B-tree vs LSM-tree, write- ahead logging, buffer/page cache, MVCC and concurrency control, durability/fsync, and compaction. Architect-level engine selection and data-path design. USE WHEN: designing or choosing a storage engine, "B-tree vs LSM", "WAL", "buffer pool", "MVCC", "compaction", "write amplification", "fsync/durability", embedded KV store, database internals, read/write-optimized store choice. DO NOT USE FOR: SQL query writing/ORM (use database/orm skills); data pipelines (use `data-intensive`); vector indexes (use vector-stores skills).

SSL/TLS certificate management skill: Let's Encrypt, Certbot, certificate types, TLS version/cipher configuration, HSTS, OCSP stapling, renewal automation, and local development certificates. USE WHEN: - Obtaining and renewing Let's Encrypt certificates (standalone, webroot, DNS challenge) - Configuring TLS on Nginx or Apache (protocols, cipher suites, session parameters) - Setting up HSTS with preload, OCSP stapling, or DHParam generation - Automating certificate renewal via systemd timer and deploy hooks - Managing multi-domain (SAN) or wildcard certificates - Debugging TLS handshake failures, mixed content, or ACME challenge errors - Setting up mkcert for trusted local HTTPS development DO NOT USE FOR: - mTLS / client certificate authentication (use service-mesh or api-gateway skill) - Application-level JWT or session token management - SSH key management - Internal CA for Kubernetes clusters (use cert-manager)

Server-Sent Events for real-time server-to-client streaming. Express, Fastify, FastAPI, Spring WebFlux SSE implementations. Event streams, reconnection, and EventSource API. USE WHEN: user mentions "SSE", "Server-Sent Events", "EventSource", "event stream", "text/event-stream", "live feed", "streaming updates" DO NOT USE FOR: bidirectional communication - use `socket-io`; WebRTC - use `webrtc`; LLM streaming - use AI SDK skills

Amazon SQS managed message queue service. Covers standard and FIFO queues, dead-letter queues, and integration patterns. Use for AWS-native serverless and microservices architectures. USE WHEN: user mentions "sqs", "aws queues", "fifo queue", "lambda trigger", "sns to sqs", asks about "aws messaging", "serverless queues", "standard queue", "visibility timeout" DO NOT USE FOR: event streaming - use `kafka` or AWS Kinesis; Azure-native - use `azure-service-bus`; GCP-native - use `google-pubsub`; on-premise - use `rabbitmq` or `activemq`; complex routing - use `rabbitmq`

Microsoft SQL Server specific features. Covers data types, indexes, partitioning, and SQL Server-specific syntax. Use for SQL Server database work. USE WHEN: user mentions "sql server", "mssql", "IDENTITY", "GETDATE()", "temporal tables", "columnstore", "SQL Server specifics", "Azure SQL" DO NOT USE FOR: T-SQL programming - use `tsql` instead, PostgreSQL - use `postgresql` instead, Oracle - use `oracle` instead

SQLCipher — transparent AES-256 encryption for SQLite databases. Drop-in SQLite replacement used by mobile wallets, password managers, and offline-first apps storing sensitive data. Covers key derivation (PBKDF2), key rotation, performance tuning, integration in Rust (rusqlite + bundled-sqlcipher feature), Android (sqlcipher-android), iOS (SQLCipher.framework or Swift package), KMP (SQLDelight + SQLCipher driver), license model (community BSD-3 vs commercial). USE WHEN: user mentions "SQLCipher", "encrypted SQLite", "PRAGMA key", "PRAGMA rekey", "sqlite-cipher", "rusqlite bundled-sqlcipher", "encrypted database for mobile wallet", "SQLDelight encryption" DO NOT USE FOR: Plain SQLite without encryption - use `databases/sqlite` (or relevant skill) DO NOT USE FOR: Server-side encrypted DB (use TDE) - use `databases/postgresql` etc. DO NOT USE FOR: Encryption primitives outside SQLite - use `security/libsodium`

SQLAlchemy Python ORM. Covers models, sessions, and queries. Use for Python database applications. USE WHEN: user mentions "sqlalchemy", "declarative_base", "DeclarativeBase", "Session", "Query", "relationship()", "alembic", asks about "python orm", "sqlalchemy models", "sqlalchemy async", "sqlalchemy relationships", "python database" DO NOT USE FOR: Node.js/TypeScript ORMs - use `prisma`, `drizzle`, or `typeorm` skills; Django ORM - use Django-specific resources; raw SQL - use `database-query` MCP; NoSQL - use `mongodb` skill; other Python ORMs (Peewee, Pony) - not supported

SQL Server and Azure SQL Database with T-SQL, indexes, stored procedures, and performance optimization patterns. USE WHEN: user mentions "SQL Server", "T-SQL", "MSSQL", "Azure SQL", "SQL Server indexes", "stored procedures", "SQL Server performance" DO NOT USE FOR: PostgreSQL - use `postgresql`, MySQL - use `mysql`, MongoDB - use `mongodb`

Reviewing SQL - what to flag, and what the database and linters actually check for you USE WHEN: you are reviewing, critiquing or auditing existing SQL - a "code review" of a query, a migration, a stored procedure, a view, or ORM-generated SQL in a diff or a PR; deciding what to comment on in SQL; judging whether a query is correct under concurrency and at scale DO NOT USE FOR: writing or learning SQL - use `databases/sql-fundamentals` or `databases/sql-advanced`; vendor-specific tuning - use the PostgreSQL, MySQL, Oracle or SQL Server skills; schema migration mechanics - use `databases/migrations` and `databases/flyway`

Core SQL knowledge based on ANSI SQL standard. Covers DML (SELECT, INSERT, UPDATE, DELETE), DDL (CREATE, ALTER, DROP), joins, transactions, and fundamental database concepts. Foundation for all SQL database work. USE WHEN: user mentions "SQL basics", "SELECT", "JOIN", "INSERT", "UPDATE", "DELETE", "DDL", "DML", "transactions", "foreign keys", "indexes", asks about basic SQL queries DO NOT USE FOR: reviewing existing SQL - use `review/sql`, which covers the NULL, concurrency and plan defects nothing in the pipeline checks DO NOT USE FOR: advanced queries (CTEs, window functions) - use `sql-advanced` instead, PostgreSQL specifics - use `postgresql` instead, NoSQL - use `mongodb` or `redis` instead

Advanced SQL patterns including CTEs, window functions, recursive queries, query optimization, and EXPLAIN analysis. Use for complex query writing and performance tuning. USE WHEN: user mentions "CTE", "window functions", "recursive queries", "EXPLAIN", "query optimization", "ROW_NUMBER", "RANK", "PARTITION BY", "running totals" DO NOT USE FOR: basic SQL - use `sql-fundamentals` instead, database-specific features - use `postgresql`, `mysql`, or `sqlserver` instead

Springdoc OpenAPI for API documentation in Spring Boot. Covers Swagger UI configuration, annotations, schema customization, and security documentation. Based on production patterns from castellino and gestionale-presenze projects. USE WHEN: user mentions "Springdoc", "Spring Boot OpenAPI", "Swagger in Spring", "@Operation", "@Schema", "Swagger UI Spring", asks about "Spring Boot API documentation", "Spring REST documentation", "OpenAPI in Java" DO NOT USE FOR: General OpenAPI specs - use `openapi` instead; GraphQL - use `graphql` instead; Non-Spring Boot projects; Frontend OpenAPI generation - use `openapi-codegen` instead

Spring WebSocket for real-time communication in Spring Boot 3.x. Covers STOMP over WebSocket, SockJS fallback, message brokers (simple and RabbitMQ/Redis), security, session handling, and testing. Use for chat, live notifications, and real-time updates. USE WHEN: user mentions "spring websocket", "STOMP", "SockJS", "real-time Spring", "@MessageMapping", "@SendTo", "WebSocket security", "message broker Spring", "chat application Spring", "live notifications" DO NOT USE FOR: REST APIs - use `spring-rest` skill, server-sent events only - use simpler SSE endpoints, NestJS WebSocket - use `nestjs-websocket` skill

Spring WebFlux for reactive programming in Spring Boot 3.x. Covers Mono/Flux, reactive operators, WebClient, functional endpoints, R2DBC integration, reactive error handling, and testing. Use for non-blocking high-concurrency apps. USE WHEN: user mentions "spring webflux", "reactive Spring", "Mono", "Flux", "WebClient reactive", "functional endpoints", "R2DBC", "non-blocking", "StepVerifier", "reactive streams" DO NOT USE FOR: traditional blocking MVC - use `spring-web` skill, simple REST APIs - use `spring-rest` skill, batch processing - use `spring-batch` skill

Spring Web MVC advanced for Spring Boot 3.x. Covers RestClient (Spring 6.1+), WebClient, ResponseEntity patterns, interceptors, content negotiation, file upload/download, streaming responses, and custom argument resolvers. USE WHEN: user mentions "spring web", "RestClient", "WebClient", "ResponseEntity", "HTTP client Spring", "file upload", "file download", "streaming response", "HandlerInterceptor", "content negotiation", "argument resolver" DO NOT USE FOR: reactive web stack - use `spring-webflux` skill, REST controller basics - use `spring-rest` skill, WebSocket - use `spring-websocket` skill

Bean Validation (JSR-380) with Spring Boot. Covers request validation, custom validators, validation groups, and error handling. USE WHEN: user mentions "spring validation", "@Valid", "@NotNull", "@NotBlank", "bean validation", "request validation", "custom validator", "validation groups", "ConstraintValidator", "@Pattern" DO NOT USE FOR: business rule validation - use service layer, security validation - use `spring-security` skill

Spring Statemachine for building finite state machine applications. Covers states, transitions, guards, actions, persistence, and hierarchical states. USE WHEN: user mentions "spring statemachine", "state machine Spring", "workflow Spring", "finite state machine", "order state", "document lifecycle", "guards actions transitions" DO NOT USE FOR: simple status flags - use enum fields, complex workflow orchestration - use `spring-integration` or Camunda, business rules engine - use Drools

Spring Shell for building interactive CLI applications. Covers @ShellComponent, @ShellMethod, input validation, tables, and command groups. USE WHEN: user mentions "spring shell", "@ShellComponent", "@ShellMethod", "CLI application Spring", "interactive shell", "command line tool Spring" DO NOT USE FOR: simple scripts - use regular main method, batch processing - use `spring-batch` skill, web endpoints - use `spring-rest` skill

Spring Session for distributed session management with Redis, JDBC, or Hazelcast. Covers session configuration, security integration, and session events. USE WHEN: user mentions "spring session", "distributed session", "session Redis", "session JDBC", "session cluster", "session management", "@SessionScope" DO NOT USE FOR: stateless JWT auth - use `jwt` skill, OAuth2 tokens - use `oauth2` skill

Spring Security JWT authentication for Spring Boot 3. Covers SecurityFilterChain, JWT filter, authentication, authorization, CORS, rate limiting, and security headers. USE WHEN: user mentions "security", "JWT", "authentication", "authorization", asks about "login", "token", "CORS", "roles", "permissions", "@PreAuthorize" DO NOT USE FOR: Spring Boot basics (use `spring-boot`), OAuth2 details (use OAuth2 skill if available), general encryption (use security-expert)

Spring Scheduling and Async for Spring Boot 3.x. Covers @Scheduled, @Async, cron expressions, ThreadPoolTaskExecutor, task monitoring, distributed scheduling with ShedLock, and error handling. USE WHEN: user mentions "@Scheduled", "@Async", "cron expression Spring", "background jobs Spring", "async Spring Boot", "ThreadPoolTaskExecutor", "ShedLock" DO NOT USE FOR: complex batch jobs - use `spring-batch` skill, workflow orchestration - consider Temporal or Camunda, message-driven - use messaging skills

Spring Retry for transparent retry support in Spring applications. Covers @Retryable, @Recover, RetryTemplate, backoff policies, and circuit breakers. USE WHEN: user mentions "spring retry", "@Retryable", "@Recover", "RetryTemplate", "backoff policy", "retry transient failure", "automatic retry" DO NOT USE FOR: circuit breaker patterns - use `spring-cloud-circuitbreaker` skill, message retry - use `spring-kafka` or messaging skill retry topics

Spring REST Controller patterns. Covers ResponseEntity, exception handling, validation, HATEOAS, content negotiation, and async controllers. USE WHEN: user mentions "spring rest", "@RestController", "ResponseEntity", "REST API Spring", "exception handling Spring", "@ControllerAdvice" DO NOT USE FOR: GraphQL - use `spring-graphql` skill, WebFlux reactive - use `spring-webflux` skill, HATEOAS deep dive - use `spring-hateoas` skill

Spring Data R2DBC for reactive database access in Spring Boot 3.x. Covers R2dbcRepository, DatabaseClient, reactive transactions, and WebFlux integration. USE WHEN: user mentions "r2dbc", "reactive database", "R2dbcRepository", "DatabaseClient", "reactive SQL", "WebFlux database", "non-blocking database" DO NOT USE FOR: blocking JDBC - use `spring-data-jdbc` or `spring-data-jpa` instead, MongoDB reactive - use `spring-data-mongodb` with reactive repository

Configuration and profiles management in Spring Boot 3.x. Covers @Profile, @ConfigurationProperties, property sources, YAML/properties, external configuration, secrets management, and environment-specific beans. USE WHEN: user mentions "spring profiles", "@Profile", "@ConfigurationProperties", "environment configuration", "property sources", "profile groups", "conditional beans" DO NOT USE FOR: feature flags at runtime - consider feature flag libraries, Spring Cloud Config - use `spring-cloud-config` skill

Spring Modulith for modular architecture in Spring Boot 3.x. Covers module structure, API vs internal packages, inter-module events, module testing, documentation generation, and observability. USE WHEN: user mentions "spring modulith", "modular monolith", "@ApplicationModule", "module boundaries", "inter-module events", "@ApplicationModuleTest", "modular architecture" DO NOT USE FOR: simple applications - unnecessary complexity, microservices - use proper service boundaries, existing tightly coupled monoliths - requires significant refactoring

Spring Mail for sending emails in Spring Boot 3.x. Covers JavaMailSender, SimpleMailMessage, MimeMessage, HTML emails, attachments, templates (Thymeleaf/FreeMarker), async sending, and testing. USE WHEN: user mentions "spring mail", "JavaMailSender", "email Spring Boot", "send email", "MimeMessage", "email templates", "SMTP Spring" DO NOT USE FOR: transactional email services (SendGrid, SES) - use their SDKs, SMS/push notifications - use appropriate services

Spring LDAP for LDAP/Active Directory integration and authentication. Covers LdapTemplate, @Entry mapping, LdapRepository, and Spring Security integration. USE WHEN: user mentions "LDAP", "Active Directory", "AD authentication", "LdapTemplate", "@Entry", "directory services", "enterprise authentication" DO NOT USE FOR: OAuth2/OIDC - use `spring-security` or `oauth2` skill, simple auth - use Spring Security with database

Spring for Apache Kafka integration with KafkaTemplate and @KafkaListener. Covers producers, consumers, retry topics, DLT, and transactions. USE WHEN: user mentions "spring kafka", "KafkaTemplate", "@KafkaListener", "kafka producer Spring", "kafka consumer Spring", "retry topic" DO NOT USE FOR: raw Kafka - use `kafka` skill, RabbitMQ - use `spring-amqp` instead

Spring Integration for Enterprise Integration Patterns (EIP) in Spring Boot 3.x. Covers Message Channels, Gateways, Transformers, Routers, Filters, Splitters, Aggregators, Adapters (File, JMS, Kafka, HTTP), and DSL. USE WHEN: user mentions "spring integration", "EIP", "enterprise integration patterns", "IntegrationFlow", "message channel", "gateway", "@MessagingGateway" DO NOT USE FOR: simple REST APIs - use Spring MVC, Kafka only - use `spring-kafka` skill, simple messaging - consider Spring Events

Spring HATEOAS for building hypermedia-driven RESTful APIs. Covers EntityModel, CollectionModel, RepresentationModelAssembler, HAL, and affordances. USE WHEN: user mentions "HATEOAS", "hypermedia", "HAL", "EntityModel", "CollectionModel", "RepresentationModelAssembler", "Richardson Maturity Level 3" DO NOT USE FOR: simple REST APIs without hypermedia - use plain Spring MVC, GraphQL - use `spring-graphql` skill

Spring for GraphQL - building GraphQL APIs with Spring Boot. Covers queries, mutations, subscriptions, @BatchMapping, DataLoader, and security. USE WHEN: user mentions "spring graphql", "@QueryMapping", "@MutationMapping", "@SubscriptionMapping", "@BatchMapping", "GraphQL Spring Boot", "N+1 GraphQL" DO NOT USE FOR: REST APIs - use standard Spring MVC, standalone GraphQL - use `graphql-java` skill

Spring Application Events for Spring Boot 3.x. Covers ApplicationEventPublisher, @EventListener, @TransactionalEventListener, custom events, async events, and event-driven architecture patterns. USE WHEN: user mentions "spring events", "ApplicationEventPublisher", "@EventListener", "@TransactionalEventListener", "event-driven Spring", "domain events" DO NOT USE FOR: external messaging - use `spring-amqp` or `spring-kafka`, distributed events - use messaging systems

Spring Data Redis for caching, session storage, and data persistence. Covers RedisTemplate, @Cacheable, repositories, pub/sub, and distributed locks. USE WHEN: user mentions "spring data redis", "RedisTemplate", "@Cacheable", "Spring Boot caching", "@RedisHash", "spring session redis", "distributed lock Spring" DO NOT USE FOR: raw Redis commands - use `redis` instead, non-Spring Redis clients - use `redis` instead

Spring Data Neo4j for graph database operations. Covers node/relationship entities, Cypher queries, and Neo4jTemplate. USE WHEN: user mentions "spring data neo4j", "Neo4jRepository", "@Node", "@Relationship", "Cypher Spring", "graph database Spring Boot" DO NOT USE FOR: raw Cypher queries - consult Neo4j documentation, relational databases - use `spring-data-jpa` instead

Spring Data MongoDB for Java/Spring Boot applications. Covers repositories, MongoTemplate, aggregations, and document mapping. USE WHEN: user mentions "spring data mongodb", "MongoTemplate", "MongoRepository", "@Document", "Spring Boot MongoDB", "aggregation pipeline Java" DO NOT USE FOR: raw MongoDB driver - use `mongodb` instead, relational databases - use `spring-data-jpa` or `spring-data-jdbc` instead

Spring Data JPA for database access in Spring Boot applications. Covers repositories, entities, relationships, queries, pagination, and auditing. Based on production patterns from castellino and gestionale-presenze projects. USE WHEN: user mentions "JPA", "repository", "entity", "database queries", asks about "pagination", "Criteria API", "Specifications", "@Query", "relationships" DO NOT USE FOR: Spring Boot basics (use `spring-boot`), Spring Security (use `spring-security`), MongoDB (use `mongodb-expert`), SQL-only tasks (use `sql-expert`)

Spring Data JDBC for simple, lightweight database access without JPA complexity. Covers aggregates, repositories, custom queries, and DDD patterns. USE WHEN: user mentions "spring data jdbc", "simple database access", "no JPA", "aggregate roots", "DDD with JDBC", "lightweight ORM", "@MappedCollection" DO NOT USE FOR: JPA/Hibernate features - use `spring-data-jpa` instead, reactive database - use `spring-r2dbc` instead, NoSQL - use respective skills

Spring Data Elasticsearch for full-text search and analytics. Covers ElasticsearchOperations, repositories, aggregations, and index management. USE WHEN: user mentions "spring data elasticsearch", "ElasticsearchRepository", "ElasticsearchOperations", "@Document elasticsearch", "Spring Boot Elasticsearch" DO NOT USE FOR: raw Elasticsearch queries - use `elasticsearch` instead, ELK stack setup - use `elasticsearch` instead

Declarative HTTP client for microservices communication with Spring Cloud OpenFeign. Covers @FeignClient, error handling, interceptors, and circuit breaker integration. USE WHEN: user mentions "feign", "openfeign", "@FeignClient", "declarative HTTP client", "service-to-service communication", "microservices client" DO NOT USE FOR: external APIs - consider WebClient or RestClient, simple HTTP calls - use RestClient

Spring Cloud Gateway for API routing, filtering, and load balancing. Covers route predicates, filters, rate limiting, and circuit breaker integration. USE WHEN: user mentions "spring cloud gateway", "API gateway", "route predicates", "gateway filters", "rate limiting gateway", "load balancing gateway" DO NOT USE FOR: simple reverse proxy - use nginx, Zuul (deprecated) - use Spring Cloud Gateway instead

Spring Cloud Function for serverless and FaaS deployments. Covers function beans, AWS Lambda, Azure Functions, and GCP adapters. USE WHEN: user mentions "spring cloud function", "serverless Spring", "AWS Lambda Spring", "Azure Functions Spring", "FaaS", "function composition" DO NOT USE FOR: simple REST APIs - use standard controllers, complex workflows - consider Step Functions or similar

Netflix Eureka for service discovery in Spring Cloud microservices. Covers Eureka Server, Eureka Client, registration, and health checks. USE WHEN: user mentions "eureka", "service discovery", "service registry", "@EnableEurekaServer", "@EnableDiscoveryClient", "eureka dashboard" DO NOT USE FOR: Kubernetes service discovery - use native K8s, Consul - use Consul-specific patterns

Spring Cloud Config for centralized configuration management in microservices. Covers Config Server, Config Client, Git backend, and dynamic refresh. USE WHEN: user mentions "spring cloud config", "config server", "centralized configuration", "@RefreshScope", "externalized config" DO NOT USE FOR: simple properties files - use standard Spring Boot, secrets management - combine with Vault

Resilience patterns with Spring Cloud Circuit Breaker and Resilience4j. Covers circuit breaker, retry, rate limiter, bulkhead, and fallback patterns. USE WHEN: user mentions "circuit breaker", "resilience4j", "fallback", "retry pattern", "rate limiter", "bulkhead", "fault tolerance Spring" DO NOT USE FOR: basic HTTP errors - handle in code, Hystrix (deprecated) - use Resilience4j instead

Spring Cloud patterns for microservices in Spring Boot 3.x. Covers Service Discovery, Config Server, API Gateway, Circuit Breaker, Load Balancing, and Distributed Tracing. USE WHEN: user mentions "spring cloud", "microservices architecture", "service discovery", "config server", "cloud native Spring" DO NOT USE FOR: specific components - use dedicated skills like `spring-cloud-gateway`, `spring-cloud-eureka`, `spring-cloud-config`

Spring Cache abstraction for Spring Boot 3.x. Covers @Cacheable, @CacheEvict, @CachePut, cache managers (Caffeine, Redis, EhCache), TTL configuration, cache keys, conditional caching, and cache synchronization. USE WHEN: user mentions "spring cache", "@Cacheable", "@CacheEvict", "cache manager", "Caffeine cache", "@EnableCaching", "cache abstraction" DO NOT USE FOR: Redis operations - use `spring-data-redis` instead, distributed caching architecture - combine with `redis` skill

Spring Boot testing fundamentals including @SpringBootTest, slice tests, MockMvc, mocking with @MockBean, test configuration, and testing utilities. For integration tests with Testcontainers, see spring-boot-integration. USE WHEN: user mentions "spring boot test", "mockmvc", "@WebMvcTest", "@DataJpaTest", asks about "@SpringBootTest", "@MockBean", "spring test", "controller test", "repository test" DO NOT USE FOR: Unit tests - use `junit` with Mockito; Integration tests with real DB - use `spring-boot-integration`; REST API clients - use `rest-assured`; E2E tests - use Selenium

Spring Boot integration testing with Testcontainers, sliced tests, and full context. Covers real database testing, API integration, and end-to-end flows. USE WHEN: user mentions "spring integration test", "testcontainers spring", "full context test", asks about "@SpringBootTest webEnvironment", "integration test database", "API integration test" DO NOT USE FOR: Unit tests - use `junit`; Slice tests only - use `spring-boot-test`; REST client testing - use `rest-assured`; E2E browser tests - use Selenium

Spring Boot 3 Java framework with enterprise patterns. Covers REST controllers, services, repositories, JPA entities, MapStruct mappers, Lombok, JWT security, Flyway migrations, and global exception handling. USE WHEN: user mentions "Spring Boot", "REST API", "enterprise Java", asks about "controller patterns", "service layer", "repository", "DTO mapping", "JWT auth", "Flyway", "MapStruct" DO NOT USE FOR: Spring Data JPA (use `spring-data-jpa`), Spring Security (use `spring-security`), Spring WebFlux (use `spring-webflux`), Spring WebSocket (use `spring-websocket`)

Spring Batch for batch processing in Spring Boot 3.x. Covers Job, Step, ItemReader/Processor/Writer, chunk processing, job parameters, restart, skip/retry, partitioning, and monitoring. USE WHEN: user mentions "spring batch", "batch job", "ETL Spring", "ItemReader", "ItemWriter", "chunk processing", "job scheduling Spring" DO NOT USE FOR: real-time processing - use streaming, simple scheduled tasks - use `spring-scheduling` instead

Spring Authorization Server for building OAuth 2.1 and OpenID Connect providers. USE WHEN: user mentions "OAuth2 server", "authorization server", "OIDC provider", "token endpoint", asks about "how to implement OAuth2", "create authorization server", "issue JWT tokens", "custom OAuth provider" DO NOT USE FOR: OAuth2 client configuration - use `spring-security` instead, resource server JWT validation - use `spring-security` instead

Spring AOP (Aspect-Oriented Programming) per Spring Boot 3.x. Copre @Aspect, pointcut expressions, @Around/@Before/@After advice, custom annotations, logging, security, caching, e transaction patterns. Usa per cross-cutting concerns. USE WHEN: user mentions "aspect", "AOP", "cross-cutting", "logging aspect", "pointcut", asks about "how to intercept methods", "apply logic to multiple methods", "@Around advice" DO NOT USE FOR: security configuration - use `spring-security` instead, transaction management - use `spring-data-jpa` instead

Spring AMQP for RabbitMQ integration with RabbitTemplate and @RabbitListener. Covers exchanges, queues, bindings, DLQ, and message conversion. USE WHEN: user mentions "spring amqp", "RabbitTemplate", "@RabbitListener", "RabbitMQ Spring", "AMQP", "message queue Spring Boot" DO NOT USE FOR: raw RabbitMQ - use `rabbitmq` skill, Kafka - use `spring-kafka` skill, generic messaging patterns - use `messaging-expert`

Spring AI for integrating AI/ML models (OpenAI, Azure, Ollama, etc.) into Spring applications. Covers ChatClient, embeddings, RAG, vector stores, and function calling. USE WHEN: user mentions "spring ai", "ChatClient", "LLM integration Spring", "RAG Spring", "embeddings Java", "vector store Spring", "OpenAI Spring Boot" DO NOT USE FOR: raw OpenAI/Anthropic API - use respective SDKs, ML model training - use Python frameworks

Spring Boot Actuator for monitoring and management. Covers health indicators, metrics with Micrometer, Prometheus integration, custom endpoints, Kubernetes probes, and endpoint security. USE WHEN: user mentions "actuator", "health endpoint", "metrics", "prometheus", "micrometer", "kubernetes probes", "liveness", "readiness", "/health", "/metrics" DO NOT USE FOR: application profiling - use `spring-profiles` instead, distributed tracing - use `micrometer-tracing` instead

SPLADE / SPLADE++ learned sparse retrieval in depth. How SPLADE differs from BM25 (learned term expansion), FLOPS regularization, indexing in Qdrant sparse vectors and Elasticsearch, hybrid with dense, efficiency tradeoffs, and when SPLADE beats BM25. USE WHEN: user mentions "SPLADE", "SPLADE++", "learned sparse", "neural sparse", "FLOPS regularization", "sparse vector retrieval", "naver/splade" DO NOT USE FOR: classical BM25 tuning - use `retrieval/bm25-tuning`; dense retrieval - use `vector-stores/*`; hybrid fusion math - use `rag/hybrid-search`

SonarQube/SonarCloud integration for continuous code quality. Setup, configuration, quality gates, and CI/CD integration. USE WHEN: user mentions "SonarQube", "SonarCloud", "quality gates", asks about "code coverage", "technical debt", "code smells", "sonar-project.properties", "SonarScanner" DO NOT USE FOR: ESLint/Biome - use linting skills, OWASP security - use security skills, testing tools - use Vitest/Playwright skills

SOLID design principles. Covers SRP, OCP, LSP, ISP, DIP. Use when designing classes and modules. USE WHEN: user mentions "SOLID", "single responsibility", "open closed", "Liskov", "interface segregation", "dependency inversion", "dependency injection", asks about "class design", "OOP principles", "extensibility", "abstraction", "how to design classes" DO NOT USE FOR: General code quality - use `clean-code` instead, Specific patterns - use design patterns skills, Language-specific OOP - use framework-specific skills

SolidJS reactive UI library. Covers signals, effects, and fine-grained reactivity. USE WHEN: user mentions "SolidJS", "Solid", "createSignal", "createEffect", "createMemo", "fine-grained reactivity", asks about "Solid patterns", "reactive primitives" DO NOT USE FOR: React - use `frontend-react` (different API despite similar JSX), Vue - use `vue-composition`, Svelte - use `svelte`, Angular - use `angular`

Socket.IO real-time bidirectional communication. Rooms, namespaces, acknowledgments, middleware, scaling with Redis adapter, and TypeScript types. USE WHEN: user mentions "Socket.IO", "socket.io", "real-time chat", "live updates", "bidirectional WebSocket", "rooms", "namespaces" DO NOT USE FOR: SSE (server-sent events) - use `sse`; WebRTC - use `webrtc`; raw WebSocket without Socket.IO - use framework WS skills

Smoke testing patterns for verifying backend implementations end-to-end. Covers build verification, service health checks, authentication flows, test data setup, and HTTP endpoint validation. USE WHEN: user mentions "smoke test", "verify implementation", "test endpoints", "check if it works", "end-to-end verification", "does it actually run" DO NOT USE FOR: Unit test writing - use `vitest` or `junit`; E2E browser tests - use `playwright`; Load testing - use `performance-expert`; Static API validation - use `integration-validator-expert`

SLF4J - Simple Logging Facade for Java. Standard logging API that abstracts underlying implementation (Logback, Log4j2). Provides parameterized logging and MDC support. USE WHEN: user mentions "slf4j", "java logging api", "parameterized logging", asks about "how to log in Java", "logger facade", "MDC in java", "logging best practices java" DO NOT USE FOR: Logback configuration - use `logback` instead, Log4j2 configuration - use Log4j2 skill, Node.js logging - use `winston` or `pino` instead, Python logging - use `python-logging` instead

Creates and improves Claude Code Skills (SKILL.md files). Covers frontmatter, descriptions, progressive disclosure, bundled resources, and content guidelines. Follows official Anthropic best practices. USE WHEN: user mentions "create skill", "write skill", "SKILL.md", "skill file", "slash command", "custom command", "extend Claude", "skill description", "skill not triggering", "skill authoring" DO NOT USE FOR: creating agents/subagents - use `agent-authoring`; creating hooks - use `hook-authoring`; creating MCP servers - use `mcp-authoring`; creating plugins - use `plugin-authoring`

Skeleton UI component library for Svelte applications. Built on Tailwind CSS with comprehensive theming, design tokens, and accessible components. Expert patterns for layouts, forms, data display, and navigation. USE WHEN: user mentions "Skeleton UI", "Skeleton Svelte", asks about "Svelte component library", "Tailwind + Svelte", "Skeleton components", "Svelte design system", "Skeleton theming" DO NOT USE FOR: Other UI libraries - use respective skills (Shadcn, DaisyUI, etc.)

Sigstore — keyless signing for software artifacts using OIDC identities and short-lived certificates from Fulcio CA, with Rekor transparency log. Cosign is the CLI for signing/verifying containers, OCI artifacts, blobs, and attestations (SBOMs, provenance). Covers GitHub Actions OIDC integration, policy enforcement (cosign-policy-controller, Kyverno), Notary v2 vs Cosign, and supply-chain attestation patterns (SLSA). USE WHEN: user mentions "Sigstore", "Cosign", "Fulcio", "Rekor", "keyless signing", "OIDC signing", "cosign sign", "cosign verify", "SLSA provenance", "OCI artifact signing", "attestation cosign" DO NOT USE FOR: GPG-style signing - use GPG-specific docs DO NOT USE FOR: Code signing certificates (Apple Developer ID, Authenticode) - platform-specific DO NOT USE FOR: Reproducible builds spec - use `infrastructure/reproducible-builds`

Shadow and canary deployment of RAG pipeline changes: dual-execute new + old, offline LLM-judge comparison, gradual traffic ramp, auto-rollback guardrails, multi-armed bandits, per-component feature flags (retriever, reranker, generator). USE WHEN: user mentions "shadow mode", "canary deployment", "dual execute", "shadow traffic RAG", "feature flags RAG", "multi-armed bandit", "auto rollback", "LaunchDarkly RAG", "Unleash RAG" DO NOT USE FOR: CI pre-merge eval - use `continuous-evaluation`; offline eval only - use `rag-evaluation`; drift detection - use `drift-detection`

shadcn/ui component library with Radix primitives and Tailwind CSS. Covers component installation, customization, theming, and common patterns. USE WHEN: user mentions "shadcn", "shadcn/ui", asks about "shadcn components", "installing shadcn", "shadcn setup", "copy-paste components" DO NOT USE FOR: Radix UI only (use radix-ui skill), Tailwind only (use tailwindcss skill), Material-UI, Chakra UI, Ant Design

Service mesh patterns and implementations. Istio, Linkerd, traffic management, mutual TLS, observability, circuit breaking, and canary routing at the infrastructure level. USE WHEN: user mentions "service mesh", "Istio", "Linkerd", "sidecar proxy", "mutual TLS", "mTLS", "traffic splitting", "Envoy", "mesh" DO NOT USE FOR: API gateway patterns - use `api-gateway`; in-app resilience - use `resilience-patterns`; Kubernetes basics - use `kubernetes`

Serverless computing patterns. AWS Lambda, Azure Functions, GCP Cloud Functions. Deployment frameworks: Serverless Framework, AWS SAM, SST. Cold starts, event sources, and production optimization. USE WHEN: user mentions "serverless", "Lambda", "cloud function", "Azure Functions", "SAM", "SST", "Serverless Framework", "cold start", "FaaS" DO NOT USE FOR: container orchestration - use `kubernetes` or `docker`; always-on servers - use backend framework skills

Linux server and application-layer performance tuning for production workloads, covering kernel networking parameters, file descriptor limits, Nginx worker config, database connection pooling (PgBouncer), I/O scheduler tuning, and profiling tools. USE WHEN: - Tuning kernel sysctl parameters for high-concurrency web servers - Increasing file descriptor limits for Nginx, Node.js, or Postgres - Configuring Nginx worker settings for optimal throughput - Setting up PgBouncer as a Postgres connection pool - Diagnosing high TIME_WAIT, OOM kills, or disk I/O bottlenecks - Tuning vm.swappiness, dirty ratios, and I/O schedulers for SSD servers - Profiling with perf, strace, or flamegraphs DO NOT USE FOR: - Application-level code profiling (use language-specific profiling tools) - Kubernetes resource requests/limits (use the kubernetes skill) - Network interface bonding or VLAN configuration - Windows Server performance tuning

Production server monitoring stack covering Prometheus, Node Exporter, Grafana, Alertmanager, Loki, and Promtail on bare-metal or VM Linux hosts. USE WHEN: - Setting up monitoring for a new production server or VPS - Configuring Prometheus scrape targets for application or system metrics - Creating Grafana dashboards and datasource provisioning - Writing Alertmanager routing rules with email/Slack notifications - Implementing the PLG stack (Promtail + Loki + Grafana) for log aggregation - Performing live system diagnostics with htop, iotop, nethogs, ss, vmstat, iostat - Setting up uptime monitoring with UptimeRobot or healthchecks.io DO NOT USE FOR: - Kubernetes-native observability (use the kubernetes skill instead) - Application-level APM (distributed tracing with Jaeger/Tempo — use observability skill) - Cloud-managed monitoring (CloudWatch, GCP Monitoring, Azure Monitor) - Windows Server monitoring

Linux server security hardening covering CIS Benchmark areas: automatic security updates, AppArmor/SELinux MAC, auditd, intrusion detection, login security (PAM), network hardening sysctl, filesystem security, and service minimization. USE WHEN: - Hardening a new Ubuntu/Debian or RHEL/CentOS server before production use - Configuring automatic security updates with unattended-upgrades - Setting up auditd to track privilege escalation and file modifications - Enabling AppArmor enforcement or writing custom profiles - Running rkhunter or Wazuh for intrusion detection - Locking down PAM login policies (account lockout, password quality) - Auditing SUID/SGID binaries and open ports DO NOT USE FOR: - Application-layer WAF rules (use the waf skill instead) - Network firewall and UFW/iptables rules (use the firewall skill instead) - SSL/TLS certificate management (use the ssl-tls skill instead) - Container security (seccomp profiles, AppArmor with Docker — use the docker skill)

Sentry self-hosted — error tracking, performance monitoring, and crash reporting, hosted on your own infrastructure (no third-party data sharing). Critical for privacy-respecting apps (wallets, healthcare, finance) where exfil to SaaS is unacceptable. Covers Docker Compose self-host install, SDKs (Rust, Kotlin/Android, Swift/iOS, JS), event sampling + scrubbing for PII redaction, source maps, release health, alert rules. Privacy patterns: opt-in only, route via Tor, scrub addresses/balances. USE WHEN: user mentions "Sentry", "Sentry self-hosted", "sentry-rust", "sentry-android", "sentry-cocoa", "Sentry Relay", "release health", "sentry beforeSend", "self-hosted error tracking", "GlitchTip" (lightweight Sentry alternative) DO NOT USE FOR: Logging - use `observability/rust-tracing` or platform loggers DO NOT USE FOR: Metrics (Prometheus) - use Prometheus skill DO NOT USE FOR: APM tracing only - use `observability/rust-tracing` (OTel) DO NOT USE FOR: Cloud Sentry SaaS - this skill focuses on self-hosted privacy

Near-duplicate and semantic-duplicate detection in corpora before indexing. MinHash / LSH, SimHash, embedding-cosine clustering (DBSCAN), FAISS-based scalable dedup, threshold selection, paraphrase handling. USE WHEN: user mentions "deduplication", "near-duplicates", "MinHash", "SimHash", "LSH", "semantic dedup", "corpus cleaning", "FAISS dedup", "paraphrase detection" DO NOT USE FOR: exact-hash dedup at ingest (use SHA256); chunking decisions - use `chunking-strategies`; drift detection - use `drift-detection`

LangChain SelfQueryRetriever pattern. LLM infers structured metadata filters from natural language ("books by Asimov after 2000" -> filter author=Asimov AND year>2000). Metadata schema declaration, comparators and operators, LlamaIndex AutoRetriever equivalent, combining with hybrid search, evaluation of filter correctness. USE WHEN: user mentions "self-querying retriever", "SelfQueryRetriever", "auto retriever", "metadata filter from query", "NL to filter", "AutoRetriever" DO NOT USE FOR: text-to-SQL on tables - use `tabular-rag`; plain query rewriting - use `query-transformations`; hybrid search - use `hybrid-search`

System-level security architecture: threat modeling, secure-by-design, defense-in-depth, zero-trust, trust boundaries, TEE/confidential computing, and secure boot / chain of trust. Architect-level — designing the security of a system, not app-level OWASP bug fixing. USE WHEN: designing a system's security architecture, "threat model", "zero-trust", "defense in depth", "trust boundary", "TEE", "enclave", "confidential computing", "secure boot", "attack surface", security design review. DO NOT USE FOR: fixing app vulnerabilities / OWASP code issues (use the security agent/skills); auth library wiring (use authentication skills).

Secrets and credentials management. Covers environment variables, secret stores, rotation policies, and detection of leaked secrets. USE WHEN: user mentions "secrets", "credentials", "API keys", "environment variables", ".env", asks about "secret leaks", "vault", "secret rotation", "gitleaks", "secret detection" DO NOT USE FOR: OWASP vulnerabilities - use `owasp-top-10`, supply chain - use `supply-chain`, general security - use `owasp`

rustls — modern, safe TLS implementation in pure Rust. Drop-in replacement for OpenSSL/native-tls in Rust apps. No C dependencies — perfect for mobile cross- compile and embedded targets. Covers ClientConfig + ServerConfig, certificate verification with webpki-roots, mTLS, custom verifier (cert pinning), ALPN negotiation (HTTP/2, HTTP/3), session resumption, integration with hyper + reqwest + tokio. USE WHEN: user mentions "rustls", "ClientConfig", "ServerConfig", "webpki-roots", "rustls-pemfile", "rustls cert pinning", "rustls mTLS", "rustls Tokio", "rustls hyper" DO NOT USE FOR: OpenSSL specifics - use OpenSSL skill (or platform TLS) DO NOT USE FOR: Apple/Windows native TLS - use platform-specific skills DO NOT USE FOR: Tor anonymous transport - use `network/arti` DO NOT USE FOR: TLS protocol theory - use OWASP / RFC docs

Rust `tracing` crate — structured, async-aware diagnostics. Spans, events, fields, instrument macro, subscribers (fmt, JSON, OpenTelemetry, Tokio Console), filtering (env-filter, RUST_LOG), targets, contextual fields with span data, integration with `tracing-subscriber` layers, OpenTelemetry export, and patterns for embedded/mobile (FFI to Android Logcat / iOS os.Logger), wallet apps with privacy-respecting log redaction. USE WHEN: user mentions "tracing", "tracing-subscriber", "instrument", "Span", "info!/error!/debug!", "tracing-opentelemetry", "tokio-console", "env-filter", "RUST_LOG", "JSON logs Rust", "structured logging Rust" DO NOT USE FOR: Mobile-specific log integration only - use `mobile/android-native` or `mobile/ios-native` DO NOT USE FOR: Java/Kotlin logging (slf4j) - use Java/Kotlin specific DO NOT USE FOR: Generic Rust language - use `languages/rust`

Rust testing with cargo test, tokio-test, and mockall. Covers unit tests, integration tests, async testing, mocking, and benchmarks. USE WHEN: user mentions "rust test", "cargo test", "mockall", asks about "#[test]", "#[tokio::test]", "proptest", "criterion", "async rust testing" DO NOT USE FOR: JavaScript/TypeScript - use `vitest` or `jest`; Java - use `junit`; Python - use `pytest`; Go - use `go-testing`; E2E browser tests - use Playwright

Rust supply-chain & quality toolchain — cargo-deny (license + advisory + bans), cargo-audit (RustSec advisory DB), cargo-nextest (faster test runner with retry/parallel), cargo-tarpaulin / llvm-cov (code coverage), cargo-machete (unused deps), cargo-outdated (version gap detection), cargo-vet (third-party audit attestations). CI integration patterns and policies for production Rust apps. USE WHEN: user mentions "cargo-deny", "cargo-audit", "RustSec", "cargo-nextest", "cargo-tarpaulin", "llvm-cov rust", "cargo-machete", "cargo-outdated", "cargo-vet", "deny.toml", "rust supply chain" DO NOT USE FOR: Cross-compile mechanics - use `build-tools/rust-cross-compile` DO NOT USE FOR: Pure Rust language - use `languages/rust` DO NOT USE FOR: Kotlin/JS supply chain - use `quality/osv-scanner` (covers all)

Rust security patterns for web applications. Covers memory safety guarantees, dependency auditing, secure coding practices, and OWASP for Rust ecosystem. USE WHEN: user works with "Rust", "Actix", "Axum", "Rocket", "Warp", asks about "Rust vulnerabilities", "cargo audit", "Rust injection", "Rust authentication" DO NOT USE FOR: general OWASP concepts - use `owasp` or `owasp-top-10` instead, other language security - use language-specific skills

Reviewing Rust code - what to flag, and what rustc and clippy already flag for you USE WHEN: you are reviewing, critiquing or auditing existing Rust code - a "code review", a "review" of a .rs file, a diff, a PR or a pull request; deciding what to comment on in Rust; avoiding false positives on Rust code DO NOT USE FOR: writing, explaining or learning Rust - use `languages/rust`; anything rustc or a default clippy run already reports (this skill lists those so you can stay silent about them); async runtime specifics - use the tokio material; FFI binding generation - use `languages/uniffi`

Rust code quality with Clippy, rustfmt, and cargo tools. Covers linting, formatting, and idiomatic Rust patterns. USE WHEN: user works with "Rust", "Cargo", "Actix", "Axum", asks about "Clippy", "rustfmt", "Rust linting", "Rust best practices", "idiomatic Rust" DO NOT USE FOR: SonarQube - use `sonarqube` skill, security - use `rust-security` skill

rust_decimal — fixed-point decimal arithmetic for Rust. 128-bit signed decimal, exact (no float rounding errors), suitable for finance, currency, Bitcoin sat ↔ fiat conversions, accounting. Up to 28 significant digits, arithmetic preserves precision. Includes RoundingStrategy for explicit truncation/rounding control. Integrates with serde, sqlx, postgres. USE WHEN: user mentions "rust_decimal", "Decimal", "dec!", "RoundingStrategy", "no float", "exact arithmetic", "fixed-point Rust", "currency math Rust", "sat to fiat conversion" DO NOT USE FOR: Crypto primitives - use `security/libsodium` or `bitcoin/cryptography/*` DO NOT USE FOR: BigInteger / arbitrary-precision math - use `num-bigint` DO NOT USE FOR: Time/duration math - use `chrono` or `time` crate

Cross-compiling Rust crates for mobile (Android, iOS) and other non-host targets. Covers rustup target management, cargo-ndk for Android (NDK toolchain), iOS targets (aarch64-apple-ios, aarch64-apple-ios-sim, x86_64-apple-ios), `cross` for general cross-compile via Docker, lipo for iOS universal binaries, XCFramework packaging, sysroot configuration, dependency cross-compile gotchas (openssl, ring, C deps), and CI matrix patterns. USE WHEN: user mentions "cross-compile rust", "cargo-ndk", "rustup target add", "aarch64-apple-ios", "lipo", "cargo cross", "rust for android", "rust for ios", "Rust XCFramework", "static library mobile" DO NOT USE FOR: Gradle KMP build - use `build-tools/gradle-kmp` DO NOT USE FOR: Pure Rust language - use `languages/rust` DO NOT USE FOR: UniFFI specifics - use `languages/uniffi`

Rust systems programming language. Covers ownership, borrowing, lifetimes, async/await, error handling, and Cargo. Use for high-performance backend systems. USE WHEN: user mentions "rust", "ownership", "borrowing", "lifetimes", asks about "borrow checker", "cargo", "traits", "Result type", "async rust", "tokio" DO NOT USE FOR: reviewing existing Rust code - use `review/rust`, which covers the few defects rustc and clippy structurally cannot reach DO NOT USE FOR: Actix/Axum/Rocket frameworks - use framework-specific skills DO NOT USE FOR: WASM - use WebAssembly-specific skill DO NOT USE FOR: Tauri - use `tauri` skill instead

rusqlite — ergonomic Rust SQLite client with bundled SQLite (no system dep), prepared statements, parameter binding, transactions, custom types via traits, blob I/O, FTS5 full-text search, JSON1 extension, R-Tree spatial indexes, connection pooling (r2d2_sqlite or deadpool-sqlite), and SQLCipher integration via `bundled-sqlcipher` feature. Async wrapper via `tokio-rusqlite` or `sqlx`. USE WHEN: user mentions "rusqlite", "rust sqlite", "Connection::open", "params!", "rusqlite ToSql", "rusqlite FromSql", "bundled-sqlite", "tokio-rusqlite", "rusqlite migration" DO NOT USE FOR: SQLCipher specifics - use `databases/sqlcipher` DO NOT USE FOR: SQL language - use `databases/sql-fundamentals` DO NOT USE FOR: Server PostgreSQL/MySQL - use respective skills DO NOT USE FOR: ORM patterns (Diesel, SeaORM) - use ORM-specific skills

Ruff Python linter and formatter. Covers configuration in pyproject.toml, rule selection, auto-fix, and integration with editors and CI. Use when configuring or troubleshooting Python code quality tooling. USE WHEN: user mentions "ruff", "ruff check", "ruff format", "python linting", "pyproject.toml linting", "isort alternative", "black alternative", "flake8 replacement", "python formatter" DO NOT USE FOR: ESLint/Prettier (JavaScript), mypy type checking

Rocket Rust web framework. Covers routing, fairings, guards, state, and testing. Use for type-safe, boilerplate-free Rust APIs. USE WHEN: user mentions "rocket", "rust type-safe api", "rocket guards", asks about "rocket fairings", "rocket state", "compile-time route checking", "rust web macros", "rocket testing" DO NOT USE FOR: Axum projects - use `axum` instead, Actix-web projects - use `actix-web` instead, Warp projects - use `warp` instead, non-Rust backends

REST Assured Java library for testing REST APIs. Covers HTTP requests, JSON/XML validation, and Spring Boot integration. USE WHEN: user mentions "rest assured", "api test java", "rest api test", asks about "given when then", "RestAssured", "HTTP test", "JSON validation" DO NOT USE FOR: Unit tests - use `junit`; E2E browser tests - use Selenium; WebSocket testing - use dedicated tools; Non-Java projects - use language-specific HTTP clients

REST API design principles. Covers resources, methods, and status codes. Use when designing or reviewing REST APIs. USE WHEN: user mentions "REST API", "RESTful", "HTTP methods", "status codes", "resource naming", "API endpoints", "pagination", "versioning", asks about "how to design REST API", "REST best practices", "API documentation", "HTTP verbs" DO NOT USE FOR: GraphQL APIs - use `graphql` instead; tRPC - use `trpc` instead; OpenAPI specs - use `openapi` instead; Spring Boot REST - combine with `springdoc-openapi`

Application resilience patterns. Circuit breakers, retries with backoff, bulkheads, timeouts, fallbacks, and health checks. Polly (.NET), resilience4j (Java), cockatiel (Node.js). USE WHEN: user mentions "circuit breaker", "retry", "backoff", "bulkhead", "resilience", "fault tolerance", "Polly", "resilience4j", "fallback" DO NOT USE FOR: error handling basics - use language skills; monitoring - use `opentelemetry`

Reranking retrieved documents with cross-encoders and LLM rerankers. Cohere Rerank v3, Voyage rerank-2, BGE reranker, ColBERT late interaction, Jina reranker. Cost and latency tradeoffs, top-K in / top-N out strategy. USE WHEN: user mentions "rerank", "reranker", "cross-encoder", "Cohere Rerank", "Voyage rerank", "BGE reranker", "ColBERT", "Jina reranker", "bi-encoder" DO NOT USE FOR: initial retrieval - use `advanced-retrieval` or `hybrid-search`; query rewriting - use `query-transformations`; agent decisions - use `agentic-rag`

Reproducible builds — bit-for-bit identical artifacts from the same source, independently verifiable. Covers the reproducible-builds.org methodology, Bitcoin Core's Guix-based reproducible builds (the gold standard for cryptocurrency software), Nix Flakes for deterministic environments, source-date-epoch (SOURCE_DATE_EPOCH), build flag normalization (file ordering, locale, paths), .reproducible-builds.org diff tooling (diffoscope), and how to apply this to Rust + Gradle + mobile builds. USE WHEN: user mentions "reproducible builds", "deterministic builds", "bit-for-bit", "Guix builds", "diffoscope", "SOURCE_DATE_EPOCH", "Bitcoin Core build", "Nix flake build", "verify binary identical", "supply-chain attestation" DO NOT USE FOR: Artifact signing - use `security/sigstore-cosign` DO NOT USE FOR: Cross-compile mechanics - use `build-tools/rust-cross-compile` DO NOT USE FOR: General Gradle - use `build-tools/gradle-kmp`

Remix full-stack React framework. Covers loaders, actions, nested routing, and progressive enhancement. Use when building Remix applications. USE WHEN: user mentions "Remix", asks about "loaders", "actions", "Remix forms", "nested routes in Remix", "progressive enhancement", "defer in Remix", "useFetcher", "Remix deployment" DO NOT USE FOR: React without Remix - use `frontend-react` instead; Next.js - use `nextjs-app-router` instead; Nuxt - use `nuxt3` instead; SvelteKit - use `sveltekit` instead

Redux Toolkit for React state management. Covers slices, thunks, and RTK Query. Use for complex global state. USE WHEN: user mentions "redux", "redux toolkit", "RTK", "createSlice", asks about "complex state management", "time-travel debugging", "middleware", "thunks", "RTK Query", "global state with DevTools", "enterprise state management" DO NOT USE FOR: simple state - use `zustand`; server data - prefer `tanstack-query`; Vue apps - use `pinia`; small projects - overhead not justified

Redis Stack vector search. FT.CREATE with VECTOR field, HNSW vs FLAT, hybrid with other field types, RedisVL Python library, Redis Enterprise scaling, pipelines for bulk ingest, TTL for ephemeral vectors (cache use case), Redis JSON + vectors pattern. USE WHEN: user mentions "Redis vector", "Redis Stack", "FT.CREATE", "RedisVL", "Redis HNSW", "Redis JSON vector", "semantic cache Redis" DO NOT USE FOR: other vector stores - use `vector-stores/*` siblings; embedding caching theory - use `rag/caching-retrieval`

Redis Pub/Sub and Streams for messaging. Covers publish/subscribe, streams with consumer groups, and real-time patterns. Use for lightweight messaging and real-time features. USE WHEN: user mentions "redis pub/sub", "redis streams", "real-time messaging", "lightweight messaging", "pattern subscriptions", asks about "fast messaging", "simple pub/sub", "event streams with redis" DO NOT USE FOR: guaranteed delivery - use `kafka`, `rabbitmq`, or `pulsar`; complex routing - use `rabbitmq`; high durability needs - use `kafka`; enterprise features - use `activemq`; cloud-native - use cloud providers

Redis in-memory data store. Covers data structures, caching, and pub/sub. Use for caching and real-time features. USE WHEN: user mentions "redis", "caching", "session storage", "rate limiting", "pub/sub", "sorted sets", "in-memory database", "cache invalidation" DO NOT USE FOR: relational data - use `postgresql` or `mysql` instead, document storage - use `mongodb` instead, full-text search - use `elasticsearch` instead

WebSocket integration patterns for React applications. Covers custom hooks, context providers, Socket.IO, and real-time state synchronization with TanStack Query. USE WHEN: user mentions "WebSocket in React", "real-time React", "Socket.IO React", "useWebSocket hook", "live updates", "chat application", "real-time notifications", asks about "how to connect WebSocket in React" DO NOT USE FOR: NestJS WebSocket gateways - use `nestjs-websocket` instead, Spring WebSocket - use `spring-websocket` instead

React component testing with Testing Library and Vitest. Covers unit tests, integration tests, async testing, mocking, user events, accessibility testing, and test patterns. USE WHEN: user mentions "React testing", "Testing Library", "Vitest", "component tests", "userEvent", "screen queries", "MSW", asks about "testing React components", "mocking in tests", "accessibility testing", "React test patterns" DO NOT USE FOR: E2E testing - use Playwright skill instead, backend testing - use framework-specific testing skills, general testing concepts - use testing framework skills

React Suspense for data fetching, code splitting, and async operations. Covers Suspense boundaries, lazy loading, streaming SSR, Error Boundaries, suspense-enabled data libraries, and progressive loading patterns. USE WHEN: user mentions "Suspense", "lazy loading", "React.lazy", "code splitting", "streaming SSR", "loading states", asks about "async components", "fallback UI" DO NOT USE FOR: React 17 and earlier (limited Suspense support), Class components, Non-React frameworks

React Server Components (RSC) for server-side rendering without client JS. Covers Server vs Client components, data fetching patterns, Server Actions, streaming, caching, and Next.js App Router integration. USE WHEN: user mentions "Server Components", "RSC", "Next.js App Router", "use server", "Server Actions", "async components", asks about "server-side React", "zero bundle impact" DO NOT USE FOR: Client-only React apps (CRA, Vite), Next.js Pages Router, React < 18, Non-Next.js frameworks without RSC support

React Router v6+ for client-side routing. Covers BrowserRouter, Routes, navigation, data loading, nested routes, protected routes, and code splitting. USE WHEN: user mentions "React Router", "routing", "navigation", "BrowserRouter", "Routes", "useNavigate", "Link", "nested routes", asks about "client-side routing", "protected routes", "route parameters", "loaders" DO NOT USE FOR: Next.js routing - use Next.js skill instead, Server-side routing - use framework-specific skills, basic React navigation - use `react` skill for simple conditional rendering

React performance optimization techniques and best practices. Covers memoization, virtualization, code splitting, profiling, React DevTools, bundle optimization, and avoiding common performance pitfalls. USE WHEN: user mentions "React performance", "slow React app", "memoization", "virtualization", "code splitting", "lazy loading", "bundle size", asks about "optimizing React", "React DevTools Profiler", "preventing re-renders" DO NOT USE FOR: React 19 Compiler - use `react-19` skill instead, basic React concepts - use `react` skill instead, testing performance - use `react-testing` skill instead

React component patterns and architectural best practices. Covers compound components, render props, higher-order components, custom hooks, composition, state machines, and container/presentational patterns. USE WHEN: user mentions "compound components", "render props", "HOC", "higher-order component", "composition pattern", "component architecture", asks about "reusable components", "component patterns", "slots pattern", "polymorphic components" DO NOT USE FOR: Basic React components - use `react` skill instead, hooks implementation - use `react-hooks` skill instead, performance patterns - use `react-performance` skill instead

React Native mobile development. Core components, navigation (React Navigation), platform-specific code, native modules, performance optimization, and debugging. USE WHEN: user mentions "React Native", "react-native", "mobile app with React", "cross-platform mobile", "RN", "react-native-cli" DO NOT USE FOR: Expo-specific features - use `expo`; Flutter - use `flutter`; web React - use `react` skills

React Hooks patterns, rules, and custom hook development. Covers all built-in hooks (useState, useEffect, useContext, etc.), performance hooks, and patterns for creating reusable custom hooks. USE WHEN: user mentions "custom hooks", "hook rules", "useState", "useEffect", "useReducer", "useCallback", "useMemo", asks about "hook dependencies", "creating hooks", "hook patterns" DO NOT USE FOR: React 19 use() hook - use `react-19` skill instead, Context API details - use `react-context` skill instead, form-specific hooks - use `react-forms` or `react-hook-form` skills instead

React Hook Form with Zod validation. Covers form setup, validation schemas, field components, error handling, and submission with shadcn/ui integration. USE WHEN: user mentions "React Hook Form", "RHF", "Zod validation", "shadcn/ui forms", "zodResolver", "FormField", asks about "form validation with Zod", "shadcn form components" DO NOT USE FOR: React 19 Server Actions - use `react-19` skill instead, basic form handling - use `react-forms` skill instead, controlled/uncontrolled patterns - use `react-forms` skill instead

React form handling patterns and best practices. Covers controlled vs uncontrolled forms, React Hook Form, form validation, complex form patterns, and Server Actions forms. USE WHEN: user mentions "React forms", "controlled inputs", "uncontrolled inputs", "form validation", "multi-step form", asks about "form handling", "form state", "React Hook Form basics" DO NOT USE FOR: React Hook Form with Zod - use `react-hook-form` skill instead, React 19 Server Actions - use `react-19` skill instead, basic input handling - use `react` skill instead

React Context API for state sharing across component trees. Covers createContext, useContext, Provider patterns, performance optimization, context composition, and when to use vs other state solutions. USE WHEN: user mentions "React Context", "createContext", "useContext", "Provider", "Context API", "dependency injection", asks about "avoiding prop drilling", "global state in React", "context composition" DO NOT USE FOR: React 19 use() hook with Context - use `react-19` skill instead, state management libraries - use specific library skills (Zustand, Redux, etc.), server state - use TanStack Query skill instead

React Concurrent Features for responsive UIs. Covers useTransition, useDeferredValue, Suspense, startTransition, concurrent rendering patterns, and priority-based updates. USE WHEN: user mentions "useTransition", "useDeferredValue", "startTransition", "concurrent rendering", "non-urgent updates", asks about "keeping UI responsive", "priority updates in React" DO NOT USE FOR: React 17 and earlier (concurrent mode not available), Simple applications without heavy rendering, Non-React frameworks

React patterns for API consumption. Covers custom hooks, Suspense, SWR, error boundaries, and real-time updates. USE WHEN: user mentions "data fetching in React", "useFetch", "SWR", "fetch hook", "API integration", "REST API", asks about "React data loading", "custom fetch hooks" DO NOT USE FOR: TanStack Query specific features - use `state-tanstack-query`, GraphQL - use GraphQL-specific libraries, Non-React frameworks

React 19 new features and APIs. Covers Actions, useActionState, useFormStatus, useOptimistic, use() hook, Server Components, Server Actions, improved ref handling, document metadata, and new compiler. USE WHEN: user mentions "React 19", "useActionState", "useFormStatus", "useOptimistic", "use() hook", "Server Components", "Server Actions", "React Compiler", asks about "React 19 features", "Actions in React", "ref as prop" DO NOT USE FOR: React 18 and earlier - use `react` skill instead, forms in general - use `react-forms` or `react-hook-form` skills instead

React 18+ library for building user interfaces. Covers components, hooks, state management, and rendering patterns. USE WHEN: user mentions "React component", "useState", "useEffect", "hooks", asks about "building UI", "component lifecycle", "React rendering", "JSX" DO NOT USE FOR: React 19 features - use `react-19` instead, React Router - use `react-router` instead, performance optimization - use `react-performance` instead

Rate limiting and throttling. Token bucket, sliding window, fixed window algorithms. Express rate limit, Spring rate limiting, Redis-based distributed rate limiting, and API quota management. USE WHEN: user mentions "rate limit", "throttle", "API quota", "too many requests", "429", "express-rate-limit", "sliding window", "token bucket" DO NOT USE FOR: circuit breaker patterns - use `resilience-patterns`; DDoS protection - use infrastructure/WAF solutions

LLM-as-reranker patterns. RankGPT listwise / pairwise / pointwise prompting, sliding window for long candidate lists, cost-latency vs Cohere Rerank, calibration tricks, structured output for rank lists. Code uses the Anthropic SDK. USE WHEN: user mentions "LLM reranker", "RankGPT", "listwise reranking", "pairwise reranking", "pointwise reranking", "GPT reranker", "Claude reranker" DO NOT USE FOR: standard cross-encoder reranking - use `rag/reranking`; fine-tuning cross-encoders - use `retrieval/cross-encoder-training`; ColBERT - use `retrieval/colbert-retrieval`

RAGatouille — a high-level wrapper around ColBERTv2 for late-interaction retrieval. Covers RAGPretrainedModel, index creation with PLAID, training custom ColBERT checkpoints with hard negatives, serving as a retriever, integration with LangChain/LlamaIndex. USE WHEN: user mentions "RAGatouille", "ColBERT", "ColBERTv2", "PLAID", "late interaction", "token-level retrieval", "RAGPretrainedModel" DO NOT USE FOR: dense single-vector retrieval - use `rag-architecture`; sparse BM25/SPLADE - use `hybrid-search`; reranking with cross-encoders - use `reranking`

Security controls for RAG. Indirect prompt-injection via retrieved documents, PII detection/redaction (Microsoft Presidio, AWS Comprehend), multi-tenant isolation, ACL-aware retrieval with row-level/metadata filtering, data-leakage prevention, jailbreak hardening on retrieved context, GDPR right-to-be-forgotten in vector DBs. USE WHEN: user mentions "prompt injection RAG", "indirect prompt injection", "PII redaction", "Presidio", "ACL RAG", "row-level security", "multi-tenant RAG isolation", "GDPR vector DB", "right to be forgotten", "jailbreak", "data leakage RAG" DO NOT USE FOR: hallucination detection - use `rag-guardrails`; tenancy scaling patterns - use `rag-production`; audit tracing schema - use `rag-observability`

Operational concerns for RAG at scale. Incremental indexing (CDC, doc diffing), blue-green re-indexing, index aliases/versioning, embedding-model hot-swap, cost optimization (dimension reduction, cheaper embed models), capacity and token budgets, p50/p95/p99 SLAs, horizontal scaling, multi-tenant isolation, async ingestion (Kafka/Pub-Sub). USE WHEN: user mentions "incremental indexing", "reindex", "index alias", "blue-green reindex", "RAG cost optimization", "multi-tenant RAG", "RAG capacity planning", "async ingestion", "CDC for RAG", "embedding model swap" DO NOT USE FOR: caching - use `rag-caching`; tracing/metrics - use `rag-observability`; access control / PII - use `rag-security`

Retrieval-Augmented Generation architecture patterns. Chunking strategies, retrieval pipelines, re-ranking, hybrid search, evaluation, and production RAG system design. USE WHEN: user mentions "RAG", "retrieval augmented generation", "document Q&A", "knowledge base chatbot", "semantic search pipeline", "chunking strategy" DO NOT USE FOR: vector database specifics - use `vector-databases`; LangChain implementation - use `langchain`; direct LLM API calls - use Claude/OpenAI SDK skills

Tracing, evaluation, and alerting for RAG systems. LangSmith, Langfuse, Arize Phoenix, Comet Opik, OpenTelemetry GenAI conventions. What to log (query, chunks+scores, rerank scores, answer, citations), retrieval debugging workflows, alerts for empty/low-score retrieval. USE WHEN: user mentions "LangSmith", "Langfuse", "Phoenix", "Opik", "OpenTelemetry LLM", "LLM tracing", "retrieval debugging", "RAG metrics", "RAG dashboard", "RAG alerting" DO NOT USE FOR: hallucination validators - use `rag-guardrails`; caching layer metrics - use `rag-caching`; security audit logs - use `rag-security`

Trust-and-safety layer for RAG. Hallucination detection (LLM self-check, NLI entailment, TRUE metric), groundedness scoring, forced-citation prompting, out-of-scope refusal, NeMo Guardrails, Guardrails AI, Pydantic structured outputs with source verification, LLM-as-judge validators. USE WHEN: user mentions "hallucination detection", "groundedness", "citation enforcement", "NeMo Guardrails", "Guardrails AI", "LLM-as-judge", "refusal", "faithfulness", "TRUE metric", "answer verification" DO NOT USE FOR: prompt-injection via retrieved docs - use `rag-security`; retrieval quality metrics (recall/precision) - use `rag-observability`; caching of verified answers - use `rag-caching`

Evaluating RAG systems. RAGAS, DeepEval, TruLens, custom LLM-as-judge, golden datasets, synthetic test generation, A/B testing, retrieval-only metrics (Hit@K, MRR, NDCG), and answer quality metrics. USE WHEN: user mentions "RAGAS", "RAG evaluation", "faithfulness", "answer relevancy", "context precision", "hit rate", "MRR", "NDCG", "LLM as judge", "golden dataset", "synthetic data" DO NOT USE FOR: runtime telemetry only - use standard monitoring; chunking decisions - use `chunking-strategies`; overall design - use `rag-architecture`

Caching strategies across the RAG stack. Semantic caching with GPTCache and LangChain, Redis-based embedding-similarity cache, cache key design, TTL/invalidation, partial caching (cache retrieval only), provider-native prompt caching (Anthropic, OpenAI), and hierarchical L1/L2 caches. USE WHEN: user mentions "semantic cache", "GPTCache", "LLM cache", "prompt caching", "Redis vector cache", "cache invalidation for RAG", "reduce LLM cost", "latency reduction LLM" DO NOT USE FOR: retrieval accuracy - use `rag-patterns`; groundedness checks - use `rag-guardrails`; incremental indexing - use `rag-production`

RAG system architecture and design decisions. Covers naive vs advanced vs agentic RAG, decision trees for RAG vs fine-tuning vs long context, production topology, latency budgets, and component sequencing. USE WHEN: user mentions "RAG architecture", "RAG design", "naive RAG", "advanced RAG", "agentic RAG", "RAG vs fine-tuning", "RAG vs long context", "production RAG" DO NOT USE FOR: chunking details - use `chunking-strategies`; query rewriting - use `query-transformations`; retrieval algorithms - use `advanced-retrieval`; evaluation - use `rag-evaluation`; agent loops - use `agentic-rag`

Radix UI unstyled accessible React components. Headless primitives. USE WHEN: user mentions "Radix", "Radix UI", "headless components", "unstyled primitives", asks about "accessible components", "Radix primitives" DO NOT USE FOR: shadcn/ui (use shadcn-ui skill), styled component libraries (Material-UI, Chakra), Vue/Svelte (use Headless UI)

RabbitMQ message broker with AMQP protocol. Covers exchanges, queues, bindings, and messaging patterns. Use for reliable message delivery and complex routing scenarios. USE WHEN: user mentions "rabbitmq", "amqp", "exchanges", "routing patterns", "topic exchange", "fanout", asks about "message routing", "work queues", "request/reply", "flexible routing" DO NOT USE FOR: high-throughput streaming - use `kafka` or `pulsar`; cloud-native - use `nats`; AWS-native - use `sqs`; JMS required - use `activemq`; simple pub/sub - use `redis-pubsub`

R2R (RAG to Riches) by SciPhi — a production-ready RAG engine with built-in hybrid search, automatic knowledge graph construction, agentic workflows, multi-tenant support, REST + Python SDK, and self-hosted or cloud deployment. USE WHEN: user mentions "R2R", "RAG to Riches", "SciPhi", "R2R SDK", "R2R knowledge graph", "R2R ingestion pipeline" DO NOT USE FOR: DIY retrieval pipelines - use `rag-architecture`; Pinecone-specific stacks - use `canopy`; lightweight embeddings on edge - use `txtai`

Pre-retrieval query rewriting techniques. HyDE, multi-query, step-back, RAG-fusion with RRF, sub-query decomposition, query routing, and expansion. Full Python code per technique with LangChain and native Anthropic SDK. USE WHEN: user mentions "HyDE", "hypothetical document", "multi-query", "step-back prompting", "RAG-fusion", "query rewriting", "query decomposition", "query routing" DO NOT USE FOR: post-retrieval reranking - use `reranking`; sparse+dense fusion on retrieved docs - use `hybrid-search`; agent loops - use `agentic-rag`

Universal code quality principles applicable to all languages. Covers Clean Code, SOLID, complexity metrics, and quality standards. USE WHEN: user mentions "clean code", "SOLID", "code smells", "refactoring", "complexity", asks about "cyclomatic complexity", "cognitive complexity", "code review", "maintainability" DO NOT USE FOR: language-specific linting - use ESLint/Biome skills, security - use OWASP skills, testing - use testing skills

Advanced Qdrant features. Payload indexing, scalar/binary/product quantization, named vectors (multi-vector), sparse vectors, multi-tenancy, snapshots, sharding, gRPC vs HTTP, pre- vs post-filtering, and oversampling/rescoring. USE WHEN: user mentions "Qdrant", "named vectors", "sparse vectors", "scalar quantization qdrant", "qdrant filtering", "qdrant sharding", "qdrant multi-tenant" DO NOT USE FOR: basic Qdrant upsert/query - use `ai-integration/vector-databases`; other vector DBs - use other `vector-stores/*`; quantization theory - use `vector-quantization`

Python security patterns for Django, FastAPI, and Flask. Covers Bandit, Safety, secure coding practices, and OWASP for Python ecosystem. USE WHEN: user works with "Python", "Django", "FastAPI", "Flask", asks about "Python vulnerabilities", "pip security", "Bandit", "Python injection", "Python authentication" DO NOT USE FOR: general OWASP concepts - use `owasp` or `owasp-top-10` instead, Node.js/Java security - use language-specific skills

Reviewing Python code - what to flag, and what ruff, mypy and the interpreter already flag for you USE WHEN: you are reviewing, critiquing or auditing existing Python code - a "code review", a "review" of a .py file, a diff, a PR or a pull request; deciding what to comment on in Python; avoiding false positives on Python code DO NOT USE FOR: writing, explaining or learning Python - use `languages/python`; anything ruff's default rules or a configured mypy already reports (this skill lists those so you can stay silent about them); Django/FastAPI specifics - use the framework skills; test review - use the pytest skills

Python code quality with Ruff, Black, mypy, and Pylint. Covers linting, formatting, type checking, and best practices. USE WHEN: user works with "Python", "Django", "FastAPI", "Flask", asks about "Ruff", "Black", "mypy", "Pylint", "Python linting", "Python type hints" DO NOT USE FOR: SonarQube - use `sonarqube` skill, testing - use pytest skills, security - use `python-security` skill

Python performance profiling with cProfile, tracemalloc, and line_profiler. Use for identifying bottlenecks and memory issues. USE WHEN: user mentions "Python profiling", "cProfile", "memory profiling", asks about "Python performance", "tracemalloc", "line_profiler", "py-spy", "Python optimization", "Python memory leak" DO NOT USE FOR: Java/Node.js profiling - use respective skills instead

Python package management with uv, poetry, PDM, and pyproject.toml. USE WHEN: "uv", "poetry", "pdm", "dependencies", "virtual environment", "pyproject.toml", "pip", "package management", "lockfile", "venv", "pip install", "requirements.txt", "pip freeze" DO NOT USE FOR: pip commands for running installed tools (use Bash) DO NOT USE FOR: conda/mamba environments - different ecosystem

Python logging with the standard library logging module and structlog. Covers log levels, handlers, formatters, structured logging, and production best practices for FastAPI/Django applications. USE WHEN: user mentions "python logging", "fastapi logging", "django logging", asks about "how to log in python", "python logging module", "logging configuration python" DO NOT USE FOR: Node.js logging - use `nodejs-logging` instead, Java logging - use `slf4j` or `logback`, structlog-specific - use `structlog` skill for deep dive

Python integration testing orchestration skill. Covers test pyramid strategy, conftest.py architecture, pytest markers for integration tests, GitHub Actions CI/CD integration, parallel execution with pytest-xdist, and test isolation patterns. USE WHEN: user mentions "python integration test", "integration test strategy", "conftest architecture", "CI integration tests", asks about test pyramid, or needs to set up integration testing infrastructure in Python. DO NOT USE FOR: Unit tests - use `pytest`; Django-specific - use `pytest-django`; FastAPI-specific - use `fastapi-testing`; Container setup - use `testcontainers-python`

Python language (3.10-3.14). Covers typing, async, and modern patterns. Use when writing Python applications. USE WHEN: user mentions "python", "type hints", "dataclasses", "async/await", asks about "asyncio", "context managers", "match statement", "walrus operator", "PEP 695", "type parameter", "generic" DO NOT USE FOR: reviewing existing Python code - use `review/python`, which covers the defects ruff and mypy do not report DO NOT USE FOR: FastAPI framework - use `backend-fastapi` skill instead DO NOT USE FOR: Django framework - use Django-specific skill DO NOT USE FOR: Package management - use `python-packaging` skill DO NOT USE FOR: Linting/type checking config - use `python-quality` skill

pytest-django integration testing specialist. Covers all fixtures (db, transactional_db, client, rf, settings, mailoutbox, django_user_model), @pytest.mark.django_db options, DRF APIClient, factory_boy integration, async views, signals, management commands, and multi-database testing. USE WHEN: user mentions "pytest-django", "django test", "@pytest.mark.django_db", asks about "django client fixture", "DRF APIClient", "django signals test", "management command test", "django async view test". DO NOT USE FOR: Non-Django Python tests - use `pytest` or `python-integration`; FastAPI - use `fastapi-testing`; Pure container setup - use `testcontainers-python`

pytest Python testing framework. Covers fixtures, parametrize, and mocking. Use for Python testing. USE WHEN: user mentions "pytest", "python test", "fixture", asks about "@pytest.fixture", "@pytest.mark.parametrize", "conftest.py", "pytest coverage", "python unit test" DO NOT USE FOR: JavaScript/TypeScript - use `vitest` or `jest`; Java - use `junit`; E2E web tests - use `playwright`; Load testing - use locust

Pydantic v2 data validation library. Covers BaseModel, field validators, custom types, serialization, and schema generation. Use when validating data structures, parsing configs, or defining typed data models in Python. USE WHEN: user mentions "pydantic", "BaseModel", "Field()", "model_validator", "field_validator", "Annotated", "model_dump", "model_validate", "pydantic settings", "pydantic v2" DO NOT USE FOR: TypeScript types/interfaces, SQLAlchemy ORM models, dataclasses

Progressive Web App development. Service workers, Web App Manifest, offline-first strategies, caching with Workbox, push notifications, and installability. USE WHEN: user mentions "PWA", "Progressive Web App", "service worker", "offline-first", "Web App Manifest", "Workbox", "installable web app", "cache-first", "add to home screen" DO NOT USE FOR: native mobile apps - use `react-native`, `flutter`, `expo`; push notification server-side - use `push-notifications`

Push notifications for web and mobile. Firebase Cloud Messaging (FCM), Apple Push Notification Service (APNs), Web Push API, Expo Notifications, and notification service architecture. USE WHEN: user mentions "push notification", "FCM", "Firebase messaging", "APNs", "web push", "service worker notification", "Expo notifications" DO NOT USE FOR: email notifications - use `email-sending`; in-app real-time updates - use `socket-io` or `sse`

Apache Pulsar cloud-native messaging and streaming. Covers topics, subscriptions, Pulsar Functions, and geo-replication. Use for multi-tenant, geo-distributed messaging systems. USE WHEN: user mentions "pulsar", "bookkeeper", "multi-tenancy", "geo-replication", "pulsar functions", asks about "cloud-native streaming", "tenant isolation", "global messaging" DO NOT USE FOR: simple queues - use `rabbitmq` or `sqs`; AWS-native - use `sqs`; Azure-native - use `azure-service-bus`; GCP-native - use `google-pubsub`; lightweight - use `nats`; JMS - use `activemq`

proptest — property-based testing for Rust (Hypothesis-style). Generates thousands of random inputs to find counterexamples to invariants, with shrinking to minimal failing case. Critical for crypto, parsers, state machines, and finance code where edge cases matter. Includes strategies (gen functions), regression tracking, and integration with cargo test. Alternative: quickcheck (simpler API, less powerful). USE WHEN: user mentions "proptest", "property-based test", "proptest!", "Strategy", "Arbitrary", "shrink", "quickcheck", "regression file", "fuzz-light", "proptest-derive" DO NOT USE FOR: Generic Rust unit tests - use `testing/rust-testing` DO NOT USE FOR: Fuzzing with mutator (cargo-fuzz, AFL) - use bitcoin/testing/fuzz DO NOT USE FOR: KMP property testing - use `testing/kotest` (has built-in property)

Prisma ORM for Node.js/TypeScript. Covers schema definition, migrations, and type-safe queries. Use when working with Prisma. USE WHEN: user mentions "prisma", "schema.prisma", "prisma migrate", "prisma generate", "prisma studio", "@prisma/client", asks about "how to define models in prisma", "prisma relations", "prisma transactions", "type-safe database queries" DO NOT USE FOR: raw SQL queries - use `database-query` MCP; Drizzle ORM - use `drizzle` skill; TypeORM - use `typeorm` skill; SQLAlchemy - use `sqlalchemy` skill

PostgreSQL relational database. Covers SQL queries, indexes, constraints, and performance. Use when working with PostgreSQL. USE WHEN: user mentions "postgres", "postgresql", "pg_", asks about "JSONB queries", "window functions", "recursive CTE", "row level security", "full text search", "partitioning", "pgBouncer", "replication" DO NOT USE FOR: MySQL syntax - use `mysql` instead, MongoDB - use `mongodb` instead, Oracle PL/SQL - use `plsql` instead, SQL Server T-SQL - use `tsql` instead

pnpm package manager. Fast, disk-efficient with excellent monorepo support. Use when managing dependencies or setting up monorepos. USE WHEN: user mentions "pnpm", "pnpm workspace", "pnpm-workspace.yaml", asks about "pnpm commands", "pnpm install", "workspace protocol" DO NOT USE FOR: npm (use standard npm commands), yarn (use yarn commands), bun package manager

Creates Claude Code plugins that package skills, agents, hooks, and MCP servers into distributable bundles. Covers plugin.json manifest, directory structure, namespacing, and distribution. Follows official Anthropic best practices. USE WHEN: user mentions "create plugin", "plugin", "plugin.json", "distribute skills", "share agents", "plugin marketplace", "package extension", ".claude-plugin" DO NOT USE FOR: creating standalone skills - use `skill-authoring`; creating standalone agents - use `agent-authoring`; creating standalone hooks - use `hook-authoring`

Oracle PL/SQL procedural language. Covers stored procedures, functions, packages, triggers, cursors, collections, and exception handling. Use for Oracle database server-side programming. USE WHEN: user mentions "plsql", "Oracle procedures", "Oracle packages", "Oracle triggers", "BULK COLLECT", "FORALL", "DBMS_OUTPUT", "Oracle functions" DO NOT USE FOR: basic Oracle SQL - use `oracle` instead, PostgreSQL - use `plpgsql` instead, T-SQL - use `tsql` instead

PostgreSQL procedural language (PL/pgSQL). Covers stored procedures, functions, triggers, exception handling, and control structures. Use for PostgreSQL server-side programming. USE WHEN: user mentions "plpgsql", "PostgreSQL functions", "PostgreSQL procedures", "PostgreSQL triggers", "RETURNS TABLE", "RETURNS SETOF", "RAISE NOTICE" DO NOT USE FOR: basic PostgreSQL SQL - use `postgresql` instead, PL/SQL (Oracle) - use `plsql` instead, T-SQL - use `tsql` instead

Playwright E2E testing framework. Covers browser automation, assertions, and test generation. Use for end-to-end testing. USE WHEN: user mentions "playwright", "e2e test", "browser test", "end-to-end", asks about "page.goto", "page.click", "locators", "cross-browser testing", "visual regression" DO NOT USE FOR: Unit tests - use `vitest` or `jest`; Component tests - use `testing-library`; API-only tests - use framework HTTP clients; Mobile apps - use specific mobile testing tools

Pino - extremely fast and low overhead Node.js logger with JSON-native structured logging. 10x faster than Winston. Optimized for high-performance APIs and production environments. USE WHEN: user mentions "pino", "fast logging", "high performance logging", "fastify logging", asks about "fastest node.js logger", "JSON structured logging", "low overhead logging" DO NOT USE FOR: Winston logging - use `winston` instead, Python logging - use `python-logging` instead, Complex transport requirements - use `winston` instead

Pinia state management for Vue. Covers stores, actions, and getters. Use for Vue 3 state management. USE WHEN: user mentions "pinia", "vue state", "vue store", asks about "defineStore", "vue 3 state management", "composition stores", "vue global state", "storeToRefs", "pinia plugin" DO NOT USE FOR: React apps - use `zustand` or `redux-toolkit`; server data - use composables with fetch/axios; Vuex projects - migrate to Pinia first

Pinecone advanced features. Serverless vs pods architecture, hybrid search with sparse-dense vectors, namespaces for multi-tenancy, metadata filtering performance, upsert batching limits, collections (snapshot/restore), Pinecone-integrated inference, Python SDK v5+, Assistants API. USE WHEN: user mentions "Pinecone", "Pinecone serverless", "Pinecone namespaces", "sparse-dense Pinecone", "Pinecone Assistants", "Pinecone inference" DO NOT USE FOR: other managed vector DBs - use `vector-stores/milvus`, `vector-stores/mongodb-atlas-vector`, `vector-stores/pinecone-advanced` siblings; hybrid fusion math - use `rag/hybrid-search`

PHP application security: vulnerability review and secure implementation patterns. USE WHEN: securing PHP applications, reviewing code for vulnerabilities, or implementing security best practices DO NOT USE FOR: code quality issues (use `php-quality`), general PHP development patterns

PHP code quality: static analysis, coding standards and best-practice enforcement for PHP codebases. USE WHEN: working with PHP codebases requiring code quality analysis, static analysis, or best practices enforcement DO NOT USE FOR: security-specific issues (use `php-security`), runtime debugging, or deployment

Advanced pgvector 0.7+ on PostgreSQL. HNSW vs IVFFlat tuning, halfvec / bit / sparsevec types, binary quantization, hybrid search with pg_trgm + tsvector, parallel index builds, partitioning for multi-tenancy, replication caveats, and Supabase-specific patterns. USE WHEN: user mentions "pgvector", "postgres vector", "HNSW in postgres", "IVFFlat", "halfvec", "supabase vector", "pgvector hybrid search", "pgvector tuning" DO NOT USE FOR: non-Postgres vector DBs - use other `vector-stores/*` skills; embedding model choice - use `embedding-models`

User-specific retrieval. Per-user namespaces/filters, preference embeddings, collaborative signals, reranking with user context (role, history, favorites), privacy-preserving design (encrypted metadata, differential privacy), GDPR- compliant personalization, long-term user memory with mem0/Zep/Letta, graph- based user-entity memory. USE WHEN: user mentions "personalized RAG", "user-specific RAG", "per-user retrieval", "mem0", "Zep", "Letta", "long-term memory", "user preferences RAG" DO NOT USE FOR: per-session chat memory - use `conversational-rag`; feedback-driven model updates - use `feedback-loops`; multi-tenant isolation only - use `rag-architecture`

Web performance optimization. Covers frontend, backend, and database optimization. Use for performance reviews. USE WHEN: user mentions "performance", "slow", "optimization", "Core Web Vitals", "LCP", "INP", "CLS", "bundle size", "lazy load", "caching", "N+1 query", "memory leak", asks about "how to speed up", "improve performance", "reduce load time", "database optimization" DO NOT USE FOR: Algorithm complexity - use computer science fundamentals, Code quality/readability - use `clean-code` instead, Security optimization - use security-specific skills

PDF generation and manipulation. Puppeteer/Playwright HTML-to-PDF, PDFKit, jsPDF, React-PDF, iText (Java), ReportLab (Python). Invoices, reports, and document generation. USE WHEN: user mentions "PDF", "generate PDF", "HTML to PDF", "invoice PDF", "PDFKit", "jsPDF", "Puppeteer PDF", "React-PDF", "iText", "ReportLab" DO NOT USE FOR: PDF parsing/reading - different concern; image generation - different format

PDF text, layout, and figure extraction for RAG pipelines. Covers PyMuPDF (fitz), pdfplumber, Docling (IBM layout-aware), LlamaParse (LLM-based), Marker (markdown conversion). Page metadata, heading heuristics, figure/image extraction. USE WHEN: user mentions "PDF extraction", "parse PDF", "PyMuPDF", "fitz", "pdfplumber", "Docling", "LlamaParse", "Marker", "PDF to markdown" DO NOT USE FOR: scanned PDFs requiring OCR - use `ocr`; table-only extraction - use `table-extraction`; general filetype partitioning - use `unstructured-io`

Python data processing with pandas, openpyxl, and lxml. Covers DataFrame operations, Excel I/O, XML parsing, bulk data transformation, and large-file handling. Use when processing tabular data, spreadsheets, or XML in Python. USE WHEN: user mentions "pandas", "DataFrame", "openpyxl", "read_excel", "lxml", "XPath", "CSV processing", "Excel parsing", "bulk data", "large file", "data transformation", "UTF-16", "codecs" DO NOT USE FOR: SQL databases (use sql-expert), NumPy-only math, ML/training

API pagination patterns. Offset-based, cursor-based, keyset pagination. Filtering, sorting, and page metadata. REST and GraphQL pagination implementations. USE WHEN: user mentions "pagination", "paginate", "cursor", "offset", "page size", "next page", "infinite scroll API", "list endpoint" DO NOT USE FOR: frontend infinite scroll UI - use frontend framework skills; database query optimization - use database skills

OWASP Top 10:2025 security vulnerabilities. Covers access control, injection, supply chain, cryptographic failures, and more. Use for security reviews. USE WHEN: user mentions "OWASP 2025", "Top 10", "security review", "vulnerability assessment", asks about "broken access control", "injection", "supply chain", "cryptographic failures", "exception handling" DO NOT USE FOR: general OWASP (2021) - use `owasp` instead, secrets - use `secrets-management`, dependencies - use `supply-chain`

OWASP security guidelines and Top 10 vulnerabilities USE WHEN: user mentions "OWASP", "security audit", "vulnerability scan", asks about "injection", "XSS", "CSRF", "access control", "authentication security" DO NOT USE FOR: OWASP Top 10:2025 specific - use `owasp-top-10` instead

OSV-Scanner — language-agnostic vulnerability scanner by Google, queries the OSV.dev database (aggregates RustSec, GHSA, PyPA, npm advisories, Go vulndb, etc.). Scans Cargo.lock, package-lock.json, pnpm-lock.yaml, Pipfile.lock, go.sum, Gradle dependency tree, container images, and Git submodules. Replaces multiple language-specific scanners with one tool. CI integration with SARIF output. USE WHEN: user mentions "osv-scanner", "osv.dev", "OSV scanner", "OSV database", "GHSA", "language-agnostic vuln scan", "supply chain vulnerability scan", "deps.dev", "Google OSV" DO NOT USE FOR: Rust-specific advisory enforcement (policy) - use `quality/rust-supply-chain` DO NOT USE FOR: Container scanning depth - use Trivy / Grype skills DO NOT USE FOR: Code SAST (CodeQL, Semgrep) - use security-specific skills

Operating-system and kernel architecture decisions: monolithic vs microkernel vs hybrid vs unikernel/exokernel, scheduler design, virtual memory & paging, IPC mechanisms, syscall/ABI boundaries, and interrupt handling. Architect-level trade-offs, not driver implementation. USE WHEN: designing or evaluating an OS/kernel, RTOS-vs-GPOS choice, kernel structure, scheduler/memory/IPC subsystem design, syscall/ABI surface, "monolithic", "microkernel", "unikernel", "exokernel", "scheduler", "virtual memory", "IPC". DO NOT USE FOR: Windows driver implementation (use windows driver skills); app-level concurrency (use language skills); container internals (use `virtualization`).

Oracle Database specific features. Covers data types, sequences, synonyms, partitioning, and Oracle-specific SQL syntax. Use for Oracle database work. USE WHEN: user mentions "oracle", "oracle database", "sequences", "synonyms", "DUAL", "SYSDATE", "NVL", "DECODE", "Oracle partitioning", "Oracle specifics" DO NOT USE FOR: PostgreSQL - use `postgresql` instead, SQL Server - use `sqlserver` instead, PL/SQL programming - use `plsql` instead

OpenTelemetry - vendor-neutral observability framework for distributed systems. Provides traces, metrics, and logs with standardized instrumentation and exporters. USE WHEN: user mentions "opentelemetry", "otel", "distributed tracing", "observability", asks about "how to trace microservices", "opentelemetry setup", "jaeger integration", "prometheus metrics" DO NOT USE FOR: Application logging only - use logging skills instead, APM vendor-specific - use vendor docs, Simple monitoring - Prometheus/Grafana may be sufficient

Amazon OpenSearch k-NN plugin. nmslib vs faiss vs lucene engine, HNSW vs IVF + PQ, radial search, neural search with remote embedding, hybrid search (BM25 + kNN with weighted sum), OpenSearch 2.13+ features, memory estimation, sizing. Full index mapping. USE WHEN: user mentions "OpenSearch", "OpenSearch k-NN", "knn_vector", "neural search", "nmslib", "faiss engine OpenSearch", "AWS vector search" DO NOT USE FOR: other vector stores - use `vector-stores/*` siblings; Elasticsearch (proprietary) - OpenSearch diverged from Elasticsearch 7.10; classical BM25 tuning - use `retrieval/bm25-tuning`

OpenAPI Generator - generate clients and servers from OpenAPI specs USE WHEN: user mentions "OpenAPI Generator CLI", "generate Java client", "generate Spring server", "openapi-generator-cli", "openapi-generator-maven-plugin", asks about "generate server from OpenAPI", "OpenAPI Generator templates" DO NOT USE FOR: TypeScript-only generation - use `openapi-codegen` instead; Writing OpenAPI specs - use `openapi` instead; GraphQL - use `graphql-codegen` instead

OpenAPI contract validation between frontend and backend. Covers type sync, endpoint validation, and contract-first development. USE WHEN: user asks about "OpenAPI validation", "API contract", "swagger sync", "frontend backend types", "API mismatch", "contract testing" DO NOT USE FOR: GraphQL - use `graphql-contract` skill, authentication - use `auth-flow-validation` skill

OpenAPI client code generation. Covers openapi-typescript, openapi-generator-cli, swagger-typescript-api, and trpc-openapi. Use for generating type-safe API clients. USE WHEN: user mentions "OpenAPI codegen", "generate API client", "openapi-typescript", "swagger-typescript-api", "openapi-generator", asks about "generate types from OpenAPI", "type-safe API client", "OpenAPI client generation" DO NOT USE FOR: Writing OpenAPI specs - use `openapi` instead; GraphQL codegen - use `graphql-codegen` instead; tRPC - use `trpc` instead; Manual API client code

OpenAPI/Swagger specification. Covers schema definition, paths, and documentation. Use for API documentation. USE WHEN: user mentions "OpenAPI", "Swagger", "API spec", "API documentation", "schema definition", "OpenAPI 3.0", "Swagger UI", asks about "how to write OpenAPI spec", "document REST API", "API contract", "schema validation" DO NOT USE FOR: GraphQL schemas - use `graphql` instead; tRPC - use `trpc` instead; Generating clients from OpenAPI - use `openapi-codegen` instead; Spring Boot OpenAPI - use `springdoc-openapi` instead

Open source readiness best practices. Covers licensing, documentation, community health, CI/CD, compliance, legal, and packaging. USE WHEN: user mentions "open source", "license", "LICENSE", "CONTRIBUTING", "CODE_OF_CONDUCT", "CHANGELOG", "open source readiness", "community health", "OSS compliance", "SPDX", "CLA", "DCO", "OpenSSF", "SBOM", "release automation", "npm publish", "make project open source", "prepare for open source" DO NOT USE FOR: Git workflow and branching - use git-workflow skill, Code quality and linting - use qa-expert agent, CI/CD pipeline design - use devops-expert agent

Ontology-aware RAG. Leveraging domain ontologies (SNOMED CT, FIBO, schema.org, Gene Ontology, custom OWL) to expand queries with synonyms, hyponyms, and broader concepts; boost retrieval for ontology-matched entities; hybrid SPARQL + vector pipelines; RDFLib + embeddings. Examples with medical and financial ontologies. USE WHEN: user mentions "ontology", "SNOMED", "FIBO", "schema.org", "OWL", "SKOS", "RDF", "SPARQL RAG", "taxonomy-guided", "concept expansion", "hyponym retrieval" DO NOT USE FOR: building a KG from text - use `knowledge-graph-construction`; deduping entities - use `entity-resolution`; generic graph RAG - use `graph-rag`

Office document ingestion for RAG: DOCX (python-docx, mammoth to markdown), PPTX (python-pptx with image extraction), XLSX (openpyxl, pandas, table-aware chunking), plus Notion/Confluence/Quip export to markdown. Preserves headings, lists, comments, and embedded images. USE WHEN: user mentions "DOCX", "Word document", "python-docx", "mammoth", "PPTX", "PowerPoint", "python-pptx", "XLSX", "Excel", "openpyxl", "spreadsheet", "Notion export", "Confluence export", "Quip export", "office documents" DO NOT USE FOR: generic multi-format partitioning - use `unstructured-io`; PDF exports of office docs - use `pdf-extraction`; structured markdown vaults - use `markdown-structured`; emails with office attachments (handle extraction here, ingestion via `email-ingestion`)

Optical Character Recognition for scanned documents and images. Covers Tesseract, EasyOCR, PaddleOCR, AWS Textract, Azure Document Intelligence, Google Document AI, and Anthropic Claude vision. Preprocessing (deskew, denoise, binarize). USE WHEN: user mentions "OCR", "scanned PDF", "Tesseract", "Textract", "EasyOCR", "PaddleOCR", "Document AI", "Claude vision OCR", "image to text" DO NOT USE FOR: born-digital PDFs with selectable text - use `pdf-extraction`; table-only extraction - use `table-extraction`

OAuth 2.0 authorization framework. Covers flows, tokens, and provider integration. Use for third-party authentication. USE WHEN: user mentions "OAuth", "Google login", "GitHub auth", "social login", "authorization code flow", "PKCE", asks about "third-party auth", "provider integration" DO NOT USE FOR: JWT tokens (use jwt skill), NextAuth.js (use nextauth skill), API keys, simple password auth

Oak Deno middleware framework inspired by Koa. Covers routing, middleware, context, WebSocket, and static files. Use for Koa-like Deno APIs. USE WHEN: user mentions "Oak", "oak", "Deno middleware", "Koa for Deno", asks about "Deno web framework", "Deno API server", "context-based routing in Deno", "Koa alternative for Deno" DO NOT USE FOR: Node.js apps - use `express` or `nestjs` instead, Fresh framework - use `fresh` skill instead, Edge runtimes - use `hono` instead, React SSR in Deno - use `fresh` instead

Nx build system and monorepo tools. Advanced task orchestration, generators, and plugins. Use for complex enterprise monorepos with multiple technologies. USE WHEN: user mentions "Nx", "nx.json", "Nx monorepo", "Nx generators", asks about "Nx workspace", "affected commands", "module boundaries" DO NOT USE FOR: Turborepo (use turborepo skill), simple monorepos (Turborepo is simpler), single-package projects

Nuxt 3 full-stack Vue framework. Covers file-based routing, data fetching, server routes, and auto-imports. Use when building Nuxt applications. USE WHEN: user mentions "Nuxt", "Nuxt 3", asks about "useFetch", "Nuxt server routes", "Nitro", "Nuxt auto-imports", "Nuxt composables", "Nuxt middleware", "SSR with Vue" DO NOT USE FOR: Vue without Nuxt - use `frontend-vue` instead; Next.js - use `nextjs-app-router` instead; Nuxt 2 - consult KB for migration; Astro - use `astro` instead

NUnit testing framework with TestCase, SetUp/TearDown, assertions, and parameterized tests for .NET applications. USE WHEN: user mentions "NUnit", "TestCase", "TestFixture", "NUnit assertions", "NUnit parameterized tests", ".NET NUnit" DO NOT USE FOR: xUnit - use `xunit`, MSTest, JavaScript testing frameworks

Reviewing Node.js runtime code - what to flag beyond the language, and what the toolchain already flags USE WHEN: you are reviewing, critiquing or auditing existing Node.js code - a "code review" of server code, a CLI, a script, a diff or a PR - and the concern is the RUNTIME: the event loop, streams, processes, file handles, EventEmitter, unhandled rejections DO NOT USE FOR: language-level review - use `review/typescript` for typed code; Express/NestJS/Fastify routing - use the framework skills; writing or learning Node - use `languages/nodejs`; browser JavaScript, which has none of this

Node.js performance profiling with V8 CPU profiler, heap analysis, and perf_hooks. Use for identifying bottlenecks and memory leaks. USE WHEN: user mentions "Node.js performance", "profiling", "memory leak", asks about "V8 profiler", "heap snapshot", "CPU profile", "perf_hooks", "event loop lag", "Node.js optimization" DO NOT USE FOR: Java/Python profiling - use respective skills instead

Node.js logging with Winston, Pino, and built-in console. Covers structured logging, log levels, transports, async logging, and production best practices for Express/NestJS applications. USE WHEN: user mentions "node.js logging", "express logging", "nestjs logging", asks about "how to log in node", "winston vs pino", "node logging best practices" DO NOT USE FOR: Python logging - use `python-logging` instead, Java logging - use `slf4j` or `logback`, Browser logging - different environment and APIs

Node.js runtime best practices. Covers event loop, async patterns, streams, worker threads, memory management, and production optimization. USE WHEN: user mentions "node.js", "event loop", "streams", "worker threads", asks about "process.nextTick", "memory leaks", "cluster mode", "async patterns" DO NOT USE FOR: reviewing existing Node code - use `review/nodejs`, which covers event loop, stream and process defects that have no diagnostic DO NOT USE FOR: Express/NestJS frameworks - use framework-specific skills DO NOT USE FOR: Language syntax - use `javascript` or `typescript` skills DO NOT USE FOR: Package management - use npm/pnpm/yarn skills

NgRx Store, Effects, Entity, and ComponentStore for Angular state management. Covers reactive patterns with signals integration. USE WHEN: user mentions "NgRx", "Angular state management", "NgRx Store", "NgRx Effects", "NgRx Entity", "ComponentStore", "Angular Redux" DO NOT USE FOR: Redux Toolkit - use `redux-toolkit`, Zustand - use `zustand`, Pinia - use `pinia`, simple Angular signals state

Nginx reverse proxy and web server configuration skill. USE WHEN: - Configuring Nginx as a reverse proxy in front of application servers (Node.js, Python, Ruby, Java) - Setting up HTTPS/TLS termination with certificates - Configuring virtual hosts, upstream load balancing, and rate limiting - Optimising static file serving, gzip compression, and cache headers - Adding security headers (HSTS, CSP, X-Frame-Options, X-Content-Type-Options) - Setting up WebSocket proxying - Diagnosing 502, 504, 413, or SSL handshake errors DO NOT USE FOR: - Application-level logic (belongs in the app server, not Nginx) - Container orchestration routing (use Kubernetes Ingress or a service mesh skill instead) - Full API gateway features (rate-limit-by-user, auth, JWT — use api-gateway skill) - Apache httpd configuration

Next.js 14+ App Router. Covers Server Components, routing, data fetching, caching, and deployment. Use when building Next.js applications with the App Router. USE WHEN: user mentions "Next.js", "App Router", "Server Components", "RSC", asks about "server actions", "Next.js routing", "Next.js caching", "Next.js deployment", "streaming", "Suspense in Next.js" DO NOT USE FOR: React (non-Next.js) - use `frontend-react` instead; Nuxt - use `nuxt3` instead; Remix - use `remix` instead; Pages Router (old Next.js) - consult KB for migration

NextAuth.js authentication for Next.js. Covers providers, sessions, and callbacks. Use for Next.js authentication. USE WHEN: user mentions "NextAuth", "Next.js auth", "Auth.js", asks about "Next.js authentication", "App Router auth", "next-auth", "authentication providers" DO NOT USE FOR: generic OAuth (use oauth2 skill), JWT implementation (use jwt skill), non-Next.js projects, Express/Fastify auth

WebSocket integration for NestJS using Socket.IO. Covers gateways, rooms, authentication guards, exception filters, and Redis adapter for scaling. USE WHEN: user mentions "NestJS WebSocket", "NestJS gateway", "Socket.IO NestJS", "real-time NestJS", "NestJS chat", "WebSocket authentication NestJS", asks about "how to implement WebSocket in NestJS" DO NOT USE FOR: React WebSocket hooks - use `react-websocket` instead, Spring WebSocket - use `spring-websocket` instead, raw Node.js WebSocket - use `nodejs` skill

NestJS enterprise Node.js framework. Covers modules, controllers, services, guards, and dependency injection. Use when building scalable Node.js applications. USE WHEN: user mentions "NestJS", "nest", "@nestjs", "@Module", "@Controller", "@Injectable", asks about "dependency injection in Node.js", "enterprise Node.js framework", "TypeScript backend framework", "decorators in backend", "guards and pipes", "modular Node.js architecture" DO NOT USE FOR: Express (minimalist framework) - use `express` instead, Fastify (performance-focused) - use `fastify` instead, Hono (edge runtimes) - use `hono` instead, Deno frameworks - use `oak` or `fresh` instead

NATS cloud-native messaging system. Covers Core NATS, JetStream persistence, and request/reply patterns. Use for lightweight, high-performance microservices communication. USE WHEN: user mentions "nats", "jetstream", "cloud-native messaging", "request/reply", "subject wildcards", asks about "lightweight messaging", "microservices communication", "nats streaming" DO NOT USE FOR: complex routing - use `rabbitmq`; AWS-native - use `sqs`; Azure-native - use `azure-service-bus`; JMS compliance - use `activemq`; persistent queues only - use dedicated broker

MySQL relational database. Covers queries, indexes, and optimization. Use when working with MySQL databases. USE WHEN: user mentions "mysql", "mariadb", asks about "AUTO_INCREMENT", "ON DUPLICATE KEY UPDATE", "GROUP_CONCAT", "mysql specific syntax" DO NOT USE FOR: PostgreSQL - use `postgresql` instead, MongoDB - use `mongodb` instead, Oracle - use `oracle` instead, SQL Server - use `sqlserver` instead

Multi-tenant architecture patterns. Database-per-tenant, schema-per-tenant, shared-schema with tenant ID, row-level security, tenant resolution, and data isolation. USE WHEN: user mentions "multi-tenant", "multitenancy", "SaaS architecture", "tenant isolation", "row-level security", "tenant ID", "subdomain routing" DO NOT USE FOR: general database design - use database skills; authentication - use auth skills

Retrieval over images, PDFs with figures and tables, audio, and video. Vision-language embeddings (CLIP, SigLIP, ImageBind, VoyageAI multimodal, BGE-M3), vision-model ingestion (Claude Vision, GPT-4o Vision), table-aware retrieval, Whisper-based audio RAG, keyframe + transcript video RAG. USE WHEN: user mentions "multimodal RAG", "image search", "PDF with figures", "table extraction", "audio RAG", "video RAG", "CLIP", "SigLIP", "VoyageAI multimodal", "BGE-M3", "Claude Vision RAG", "GPT-4o Vision" DO NOT USE FOR: pure text RAG - use `rag-patterns`; graph reasoning - use `graph-rag`; grounding/citation enforcement - use `rag-guardrails`

Multilingual and cross-lingual text embeddings. Covers multilingual-e5, LaBSE, BGE-M3, Cohere embed-multilingual-v3, OpenAI cross-lingual behavior, code-mixed text, tokenizer pitfalls, and language-specific retrieval quality. USE WHEN: user mentions "multilingual embeddings", "cross-lingual search", "non-English RAG", "Chinese/Japanese/Arabic retrieval", "LaBSE", "multilingual-e5", "code-mixed", "translated query" DO NOT USE FOR: English-only embedding choice - use `embedding-models`; fine-tuning on domain text - use `embedding-fine-tuning`

Multi-region RAG deployments for latency and resilience. Covers geo-replicated vector stores (Pinecone multi-region, Qdrant cluster, MongoDB Atlas Global, Weaviate), per-region embedding/rerank pools, LLM routing to nearest provider region (Anthropic, OpenAI, Bedrock), eventual-consistency strategies for index updates, and failover patterns. USE WHEN: user mentions "multi-region RAG", "global RAG", "geo replication", "RAG failover", "latency routing", "regional LLM endpoint", "disaster recovery RAG" DO NOT USE FOR: single-region scaling - use `rag-production`; LLM gateway vendor routing - use `llm-gateway`; CDN caching - use `rag-caching`

MongoDB Atlas Vector Search. $vectorSearch aggregation stage, index definition JSON, quantization (scalar, binary), hybrid with Atlas Search text via $rankFusion, dynamic schema benefits, sharding, Atlas Triggers for auto-embedding. USE WHEN: user mentions "Atlas Vector Search", "$vectorSearch", "MongoDB vector", "$rankFusion", "Atlas Triggers embedding", "MongoDB HNSW" DO NOT USE FOR: self-hosted vector stores - use `vector-stores/qdrant-advanced`, `vector-stores/milvus`; MongoDB without Atlas (self-hosted) - vector search is an Atlas-only feature

MongoDB document database. Covers CRUD operations, aggregations, and indexes. Use when working with MongoDB. USE WHEN: user mentions "mongodb", "mongo", "document database", asks about "aggregation pipeline", "embedded documents", "BSON", "replica sets", "sharding", "atlas" DO NOT USE FOR: SQL databases - use `postgresql`/`mysql` instead, Redis - use `redis` instead, Elasticsearch - use `elasticsearch` instead, Relational data - use SQL skills

Model gateway / LLM router architecture: a control point in front of multiple models/providers for routing (cost/quality/latency), fallback, rate limiting, caching, observability, and governance. Architect-level, multi-provider. USE WHEN: designing an LLM gateway/router, "model router", "LLM gateway", "multi-provider", "fallback", "cost routing", "LiteLLM", "Envoy AI Gateway", semantic cache, central key/quota/observability for LLM calls. DO NOT USE FOR: single-engine serving (use `inference-serving-topology`); edge/cascade (use `hybrid-edge-cloud`); agent orchestration (use `agentic-architecture`).

Milvus 2.4+ distributed vector database. Architecture (etcd + MinIO + Pulsar), partitions, index types (IVF_FLAT, HNSW, DiskANN, GPU_IVF_PQ), scalar field indexing, hybrid search (BM25 + vector), Zilliz Cloud managed, dynamic schema, upserts, time travel, pymilvus v2 client. USE WHEN: user mentions "Milvus", "pymilvus", "Zilliz", "DiskANN", "IVF_FLAT", "Milvus partition", "GPU vector index" DO NOT USE FOR: other vector DBs - use `vector-stores/*` siblings; general vector index theory - use `rag/vector-quantization`

Database migration strategies and best practices. Covers schema versioning, zero-downtime migrations, rollback patterns, and data migration techniques. Use for database evolution and deployment planning. USE WHEN: user mentions "database migrations", "schema changes", "versioning", "rollback", "zero-downtime", "expand-contract", "schema evolution" DO NOT USE FOR: Flyway specifics - use `flyway` instead, Prisma migrations - use `prisma` instead, TypeORM migrations - use `typeorm` instead

Distributed tracing and observability with Micrometer and Spring Boot 3

RabbitMQ integration testing with @SpringRabbitTest, RabbitListenerTestHarness, TestRabbitTemplate, and Testcontainers. Covers Java/Spring, Node.js, and Python. USE WHEN: user mentions "rabbitmq test", "@SpringRabbitTest", "RabbitListenerTestHarness", "TestRabbitTemplate", "RabbitMQContainer", "rabbitmq integration test" DO NOT USE FOR: RabbitMQ configuration - use `rabbitmq` skill; Spring AMQP usage - use `spring-amqp` skill; Generic testcontainers - use `testcontainers` skill

Kafka integration testing with @EmbeddedKafka, Testcontainers, and Mock APIs. Covers Java/Spring, Node.js, and Python testing approaches. USE WHEN: user mentions "kafka test", "embedded kafka", "@EmbeddedKafka", "KafkaContainer", "MockConsumer", "MockProducer", "kafka integration test" DO NOT USE FOR: Kafka configuration - use `kafka` skill; Spring Kafka usage - use `spring-kafka` skill; Generic testcontainers - use `testcontainers` skill

Integration testing patterns for messaging brokers: Redis Pub/Sub, NATS, Pulsar, SQS, ActiveMQ, Azure Service Bus, and Google Pub/Sub. Container-based and emulator-based testing for Java, Node.js, and Python. USE WHEN: user mentions "messaging test", "redis pubsub test", "nats test", "pulsar test", "sqs test", "localstack test", "activemq test", "azure service bus test", "google pubsub test", "message queue test" DO NOT USE FOR: Kafka testing - use `messaging-testing-kafka`; RabbitMQ testing - use `messaging-testing-rabbitmq`; Generic testcontainers - use `testcontainers` skill

RO/NF membrane diagnostic methodology — fouling taxonomy (colloidal, biofouling, organic, particulate), scaling by mineral species (CaCO3/CaSO4/BaSO4/SrSO4/SiO2/CaF2/Fe-Mn), integrity loss (O-ring, breach, chlorine oxidation, telescoping), chemical/operational failures, CIP decision matrix, ASTM D4516 trend-based diagnostics, baseline establishment, and decision-tree pseudo-code. Use when analyzing RO/NF plant data to identify root cause of performance deviation.

Reverse Osmosis (RO) and Electrodeionization (EDI) process fundamentals — formulas (recovery, rejection, NDP, osmotic pressure, TCF, NPF/NSP), authoritative standards reference (ASTM/ISO/USP/Ph.Eur./WHO/EN), vendor design windows (DuPont, Hydranautics, Toray, Suez, LANXESS), water chemistry, EDI quick reference, IT/EN glossary. Use when working on RO/EDI plant code, KPI calculations, or normative citations.

RO/NF pretreatment chain — feed type architectures (SWRO open/beach well, BWRO well/surface, tertiary reuse), pretreatment KPI targets (SDI, turbidity, AOC, Fe/Mn, free Cl2), coagulation chemistry (FeCl3/PAC/alum dose math), antiscalant selection by scaling species, dechlorination (SBS stoichiometry + chloramine handling), CO2/pH management for 2-pass RO and EDI feed, biocide strategy (oxidizing pre-membrane vs non-oxidizing on-membrane), monitoring instrumentation. Use when designing or auditing what sits upstream of RO/NF/EDI.

Nanofiltration (NF) reference — separation mechanisms (Donnan + steric + dielectric exclusion via DSPM-DE), pH-dependent membrane charge and isoelectric point, KPIs and selectivity ratio, vendor matrix (DuPont FilmTec NF270/NF90/NF200/NF245, Suez DK/DL/HL, Toray SUL, LANXESS Lewabrane NF, Pentair X-Flow tubular, Synder NFX/NFS), applications (softening, NOM/color removal, offshore sulfate removal, mining brines, dairy, OSN), operating windows, fouling differences vs RO. Use when designing NF processes, selecting NF membranes, or diagnosing NF performance.

RO/EDI economics (SEC, LCOW, lifecycle decision matrix), Electrodeionization deep-dive (cell pair geometry, FCE feed metric, KPIs, 8 failure modes), EDI vs Mixed-Bed DI sizing economics, pharmaceutical UPW/WFI regulatory context (USP/Ph. Eur./21 CFR Part 11/EU Annex 11), produced-water regulatory context (WHO/ISO 16075/EN 12952-12/SEMI F63). Use for energy benchmarks, cost modelling, EDI design/diagnostics, and regulatory citation.

Membrane autopsy lab methodology — autopsy decision matrix (when to autopsy), element sampling protocol (which to pick, preservation, data package), lab method suite (visual / weight-loss / dye test per ASTM D6908 / SEM-EDS / FTIR / swab + plate count / Fujiwara chlorine test / cross-section), findings-to-action interpretation table, independent and vendor-affiliated labs with cost ranges, warranty claim workflow (open BEFORE pulling the element), bilingual glossary. Use when planning or interpreting an autopsy, or filing a manufacturing-defect warranty claim.

Creates MCP (Model Context Protocol) servers for Claude Code. Covers TypeScript implementation with MCP SDK, tool definitions, transport types, metadata.json for dev-suite, and deployment patterns. Follows official MCP specification. USE WHEN: user mentions "MCP server", "create MCP", "model context protocol", "MCP tool", "external tool", "mcp-servers/", "metadata.json", "tool integration" DO NOT USE FOR: configuring existing MCP servers - check MCP docs; creating skills - use `skill-authoring`; creating hooks - use `hook-authoring`

Matryoshka Representation Learning (MRL) for dimension truncation without retraining. Covers OpenAI text-embedding-3 MRL, Nomic, Jina v3, training with MatryoshkaLoss, binary quantization compatibility, and storage/quality tradeoffs. USE WHEN: user mentions "matryoshka", "MRL", "dimension truncation", "shorten embedding", "dimensions parameter", "variable-length embeddings" DO NOT USE FOR: product/scalar quantization - use `vector-stores/vector-quantization`; picking models - use `embedding-models`

Structured markup ingestion for RAG. Covers markdown (markdown-it, tree-sitter), AsciiDoc, reStructuredText, frontmatter (YAML/TOML), header-hierarchy metadata, code-block-aware chunking (never split fenced blocks), tables, internal link resolution, Obsidian/Dendron vaults, and MDX component stripping. USE WHEN: user mentions "markdown chunking", "header splitter", "frontmatter", "code-block chunking", "Obsidian vault", "Dendron", "MDX", "AsciiDoc", "reStructuredText", "markdown-it", "tree-sitter markdown", "MarkdownHeaderTextSplitter" DO NOT USE FOR: HTML from the web - use `web-scraping`; office docs - use `office-docs`; PDF-rendered markdown-looking content - use `pdf-extraction`; generic partitioning of mixed filetypes - use `unstructured-io`

MapStruct Java mapping framework. Covers basic mappers, update mappings, nested objects, collections, custom methods, and Lombok integration. Based on castellino and gestionale-presenze production patterns. USE WHEN: user mentions "mapstruct", "@Mapper", "@Mapping", asks about "DTO mapping", "entity conversion", "@MappingTarget", "nested mapping" DO NOT USE FOR: Java language - use `java` skill instead DO NOT USE FOR: Lombok - use `lombok` skill instead DO NOT USE FOR: JPA entities - use JPA-specific skills

Maestro — declarative E2E mobile UI testing framework by mobile.dev. YAML-based flow files, single tool for Android + iOS (and Compose Multiplatform / Flutter / React Native). Built-in cloud runner, recording mode, JS scripting for complex assertions, screen state diffing, no flakiness from explicit waits. USE WHEN: user mentions "Maestro", "maestro test", "mobile E2E", "cross-platform UI test", "maestro studio", "mobile.dev cloud", ".maestro" folder, "launchApp" YAML DO NOT USE FOR: web E2E - use `testing/playwright` DO NOT USE FOR: unit tests - use `testing/kotest`, `testing/vitest`, etc. DO NOT USE FOR: instrumented Android tests - use Espresso/Compose Test DO NOT USE FOR: snapshot tests - use `testing/compose-snapshot`

Decision framework: when long-context (Gemini 2M, Claude 200k, GPT 128k) beats RAG, hybrid approaches (RAG narrows, long-context reads), cost-quality-latency tradeoffs, lost-in-the-middle / context rot research, needle vs synthesis tasks, prompt caching economics, concrete $ per query math. USE WHEN: user mentions "long context vs RAG", "Gemini 2M", "lost in the middle", "context rot", "when not to use RAG", "stuff the prompt", "prompt caching cost" DO NOT USE FOR: implementing RAG - use `rag-architecture`; evaluating RAG - use `rag-evaluation`; chunking decisions alone - use `chunking-strategies`

Project Lombok for reducing Java boilerplate. Covers annotations for getters, setters, constructors, builders, logging, and more. Based on production patterns from castellino and gestionale-presenze projects. USE WHEN: user mentions "lombok", "@Data", "@Builder", "@Slf4j", asks about "boilerplate reduction", "getters/setters", "@RequiredArgsConstructor", "@Value" DO NOT USE FOR: Java language features - use `java` skill instead DO NOT USE FOR: MapStruct integration - use `mapstruct` skill DO NOT USE FOR: Spring annotations - use `backend-spring-boot` skill

Logback - flexible and powerful logging framework for Java and Spring Boot applications. Successor to Log4j with native SLF4J support, async logging, and automatic file rotation. USE WHEN: user mentions "logback", "spring boot logging", "java logging configuration", asks about "logback-spring.xml", "rolling file appender", "async logging in java" DO NOT USE FOR: SLF4J API usage - use `slf4j` instead, Log4j2 - use separate Log4j2 skill, Node.js logging - use `winston` or `pino` instead, Python logging - use `python-logging` instead

Load and performance testing. k6 (Grafana), Artillery, Apache JMeter, Locust (Python). Scenario design, thresholds, ramp-up patterns, and CI/CD integration. USE WHEN: user mentions "load test", "performance test", "stress test", "k6", "Artillery", "JMeter", "Locust", "throughput", "benchmarking" DO NOT USE FOR: unit/integration testing - use testing skills; monitoring in production - use `opentelemetry`

Load balancing with Nginx and HAProxy. Covers upstream configuration, balancing algorithms, health checks, SSL termination, session persistence, and monitoring. USE WHEN: user mentions "load balancer", "nginx upstream", "haproxy", "nginx load balancing", "round robin", "least_conn", "ip_hash", "haproxy backend", "haproxy frontend", "haproxy acl", "haproxy stats", "ssl termination", "sticky session", "upstream health check", "nginx proxy", "haproxy health check" DO NOT USE FOR: Caddy reverse proxy — use `caddy` skill, Traefik service mesh — use `traefik` skill, Kubernetes Ingress or Service resources — use `kubernetes` skill, DNS-level load balancing (Route 53, Cloudflare LB)

LLM gateways in front of RAG stacks. Covers Portkey (caching, fallbacks, retries, observability), OpenRouter (300+ model routing), LiteLLM Proxy, Kong AI Gateway, semantic caching at gateway layer, cost-based routing (cheap model for easy queries), rate-limit handling, and unified API across providers. Config examples. USE WHEN: user mentions "LLM gateway", "Portkey", "OpenRouter", "LiteLLM", "Kong AI Gateway", "AI gateway", "semantic cache gateway", "provider fallback", "unified LLM API" DO NOT USE FOR: in-app caching - use `rag-caching`; multi-region routing - use `multi-region`; cost tracking/dashboarding - use `cost-allocation`

LlamaIndex 0.12+ for RAG and agent applications. Covers Document/Node model, IngestionPipeline, NodeParser variants, VectorStoreIndex, query engines, sub-question decomposition, router engines, Property Graph Index, LlamaParse integration, and observability callbacks. USE WHEN: user mentions "LlamaIndex", "llama_index", "VectorStoreIndex", "IngestionPipeline", "PropertyGraphIndex", "LlamaParse", "SubQuestionQueryEngine" DO NOT USE FOR: LangChain specifics - use `langchain`; RAG architecture theory - use `rag-patterns`; DSPy compiler workflows - use `dspy`

Linux (Ubuntu/Debian) server initial setup and ongoing administration skill. Covers new server hardening, user management, package management, file permissions, resource limits, log rotation, cron scheduling, and disk management. USE WHEN: - Performing initial setup of a fresh Ubuntu/Debian server (VPS, bare metal, cloud VM) - Hardening SSH, disabling root login, configuring sudo - Configuring system-level resource limits (ulimits, sysctl) for high-concurrency workloads - Managing users, groups, file permissions, and ACLs - Setting up log rotation, journald retention, swap, and NTP - Troubleshooting disk full, FD exhaustion, locale errors, or time drift DO NOT USE FOR: - Container-level administration (use docker or kubernetes skill) - Application deployment pipelines (use deployment-strategies or ci-cd skill) - Firewall/fail2ban configuration (use firewall skill) - Nginx or service configuration (use nginx or systemd skill)

WebLN: browser API for Lightning. window.webln exposed by wallet extensions / mobile webviews. Methods: enable, getInfo, sendPayment, makeInvoice, signMessage. Bitcoin Connect (modern wrapper). USE WHEN: building web apps with Lightning payments, integrating with Alby/getalby, designing WebLN-compatible flows.

Watchtower architecture: encrypted breach blob storage, justice transactions, monitoring outsourced for offline channels. LN-Symmetry (eltoo, BIP 448) alternatives. USE WHEN: deploying a watchtower service, evaluating watchtower vendors, designing self-hosted monitoring.

UMA (Universal Money Address): Lightspark's spec extending Lightning Address with non-USD currencies, KYC compliance, sender attestation, multi-currency exchange via Lightning routing. USE WHEN: integrating with UMA-enabled providers (mostly enterprise), building cross-currency LN payment flows.

Trampoline routing: outsource pathfinding to "trampoline" nodes for clients that lack full graph knowledge. Mobile-friendly. Eclair (ACINQ/Phoenix) is the reference deployment; LDK receives and forwards; still unmerged as BOLTs PR #836 (September 2026). USE WHEN: implementing trampoline-aware sender/receiver, evaluating trampoline vs full pathfinding.

Simple Taproot Channels (feature bits 80/81): MuSig2-aggregated funding output, Tapscript commitment leaves, taproot-native HTLCs. USE WHEN: enabling taproot channels in your impl, evaluating cooperative-spend privacy gains, designing taproot HTLC scripts.

Submarine swaps: atomic on-chain ↔ Lightning conversions via shared HTLC preimage. Boltz protocol, Loop protocol, Peerswap (P2P), trustless variants with adaptor signatures. Boltz swaps are offline (suspended 2026-08-03); Loop, Peerswap and Blockstream Swaps (beta) are the live options as of September 2026. USE WHEN: building swap services, integrating with Loop / Peerswap / Blockstream Swaps, reading Boltz as a protocol reference, designing trust-minimized swap flows.

Channel splicing: splice-in (adding capacity) and splice-out (withdrawing) without closing the channel. Replaces "close and reopen" with one splice tx. USE WHEN: increasing/decreasing channel capacity in production, designing dynamic-balance LSP integrations, planning channel lifecycle.

Lightning pathfinding and routing: cost models, MPP / AMP / trampoline, blinded paths (BOLT 4 update), apriori probability, pickhardt-payments. USE WHEN: implementing/tuning a routing algorithm, debugging "no route" errors, evaluating pathfinding strategies.

Replacement cycling attack on Lightning (Riard 2023): exploits BIP125 rule 5 to indefinitely delay an honest HTLC-timeout, costing the victim. Mitigated by TRUC v3 + ephemeral anchors. USE WHEN: auditing LN security posture, evaluating fee-bumping strategies, understanding why TRUC was activated.

Pinning attacks: low-fee descendant txs block honest fee-bumping by exploiting mempool descendant policy. Anchor outputs (BOLT-3), TRUC v3 (BIP431), P2A + ephemeral dust, and the single shared anchor of `zero_fee_commitments` as defenses. USE WHEN: auditing fee-bump robustness, evaluating channel security, reviewing post-2024 LN deployments.

Phoenixd by ACINQ: headless server build of Phoenix wallet for self-hosting. Single-node Lightning daemon with batteries-included ACINQ swap-in / swap-out, BOLT12 receive, WebSocket payments API. USE WHEN: deploying a self-hosted minimal Lightning daemon for a service (point-of-sale, donation page, micro-merchant), avoiding full LND/CLN complexity.

Sphinx onion routing for Lightning (BOLT 4): packet structure, per-hop encryption, payload TLV, blinded paths, attribution data, onion messages. USE WHEN: implementing onion construction/decryption, debugging routing payloads, designing onion-based off-chain protocols.

Nostr Wallet Connect (NWC, NIP-47): wallet remote control via Nostr relays. App on one device drives wallet on another via signed JSON messages over Nostr. USE WHEN: integrating wallet-side or app-side NWC, designing remote-control flows, evaluating NWC vs WebLN.

LSP (Lightning Service Provider) specifications: BLIPs, JIT channels, on-pay channel open, MPP-trampoline, BOLT12 hosted invoice. Major LSPs: ACINQ (Phoenix backend), Olympus by ZEUS, Megalith, Flashsats, Magma. USE WHEN: integrating with an LSP, designing LSP services, evaluating LSP options for a wallet.

Lightning Labs liquidity tools: Loop (off-chain ↔ on-chain swaps), Pool (auction-based liquidity market), Lightning Terminal (Lit, web UI). Submarine swap mechanics behind Loop. As of September 2026 Loop is the live general-purpose option: Boltz swaps are offline (suspended 2026-08-03) and Peerswap rejects new L-BTC swaps (v7.0.1, 2026-09-07). USE WHEN: managing channel liquidity, evaluating Loop vs Boltz vs Peerswap, deploying Lit for fleet management.

LNURL: bech32-encoded HTTP URL fetched by wallet to enable payment flows. LUDs (LNURL specs): LUD-01 (encoding), LUD-04 (auth), LUD-06 (pay), LUD-09 (success action), LUD-12 (comment), LUD-16 (lightning address), LUD-21 (verify). USE WHEN: implementing LNURL servers/clients, building Lightning Address resolver, designing pay/withdraw/auth flows.

LND (Lightning Network Daemon) by Lightning Labs: gRPC + REST API, macaroons, lncli, autopilot, channel backups (SCB), Tor support, watchtowers, integration with bitcoind/btcd/Neutrino backend. USE WHEN: integrating with LND, scripting lncli, debugging LND-specific issues, designing LND-based services.

LDK (Lightning Dev Kit): modular Rust crates for building custom Lightning apps. ldk-node for opinionated quick-start. ChannelManager, ChainMonitor, Router, async signer, persistence. USE WHEN: embedding Lightning into mobile/desktop apps, building custom Lightning logic, scaling beyond LND-style daemon.

Keysend / spontaneous payments: send Lightning to a destination without an invoice. Receiver derives preimage from sender-supplied TLV record. BOLT 9 bit 50. USE WHEN: implementing tipping flows, designing zero-friction micro-payments, evaluating keysend vs BOLT11 invoice flow.

HTLC (Hash Time-Locked Contract) lifecycle: offered/received, fulfill via preimage, fail/timeout, 2nd-stage txs. Modern variant PTLCs (Point Time-Locked Contracts) with adaptor signatures. USE WHEN: implementing payment forwarding, debugging stuck HTLCs, reasoning about CLTV deltas in routes.

Greenlight by Blockstream: hosted CLN with self-custodial signing. Server runs the full CLN node; user retains private keys via signer protocol. Mobile-friendly without running a full LN node. USE WHEN: building mobile/web LN apps with self-custody but no on-device daemon, integrating with Blockstream's hosted infra.

BOLT 7 gossip: node_announcement, channel_announcement, channel_update. Sync via gossip_queries, channel range queries, gossip rate limiting, pruning stale announcements. USE WHEN: implementing/debugging gossip sync, managing graph storage, designing rate limits.

Eclair Lightning implementation by ACINQ: Scala/Akka, eclair-cli, plugin system, primarily backend service. Powers Phoenix wallet's server side and ACINQ's main routing node. USE WHEN: deploying Eclair as backend, integrating with ACINQ's Phoenix backend, evaluating Scala/JVM Lightning options.

Consumer Lightning wallet integration patterns: Phoenix, Breez SDK, Zeus, BlueWallet (LN), Aqua, Bitkit. Custodial vs non-custodial, LSP partnerships, mobile-specific UX (push notifications, background sync). USE WHEN: integrating with consumer wallets, designing self-custodial mobile UX, evaluating wallet SDK options.

Core Lightning (CLN, formerly c-lightning) by Blockstream: lightningd, lightning-cli, plugin architecture (Python pyln-client, Rust cln-plugin, Go glightning), commando, BOLT12 leadership, xpay/askrene payments. USE WHEN: integrating with CLN, writing plugins, debugging CLN-specific behaviour, leveraging BOLT12 features, migrating payments from pay to xpay.

Lightning channel mechanics: funding tx, commitment tx, anchor outputs, zero-fee commitments (v3/TRUC), to_local / to_remote outputs, dual-funded (v2), zero-conf, wumbo, taproot channels, splicing. Quick refs: state machine, commitment tx structure, force-close flow. USE WHEN: opening/closing channels, debugging force-closes, designing channel UX, evaluating anchor vs static-remote-key tradeoffs.

Channel jamming attacks: slow-jam (long-held HTLCs exhaust slots), fast-jam (rapid hold/release exhausts liquidity). Mitigations: upfront fees, reputation, hold-fee proposals. USE WHEN: assessing LN security model, designing reputation systems, evaluating jamming-resistant routing.

BOLT (Basis of Lightning Technology) specification index. Wire format, channel management, onion routing, gossip, invoices, feature bits. Quick refs: BOLT-by-BOLT summary, message-type tables, feature-bit registry. USE WHEN: implementing/reading Lightning protocol, looking up message types, debugging interop between implementations.

BOLT12 offers: reusable invoices, blinded paths, recurring payments, multi-asset (Taproot Assets layered). Replaces BOLT11 for many use cases. USE WHEN: implementing/integrating offers, designing recurring payments, evaluating BOLT11 vs BOLT12 trade-offs.

Multi-Path Payments (MPP) — split a payment across multiple parallel routes; same payment hash, payment_secret binds parts. AMP (Atomic Multipath) — variant where each part has different hash; receiver derives shared secret. USE WHEN: implementing payment splitting, debugging "couldn't route full amount", evaluating MPP vs AMP.

Lightning Address (LUD-16): email-style identifier resolving to LNURL-pay endpoint. user@domain.com → /.well-known/lnurlp/user. Also covers BIP 353 DNS payment instructions (₿user@domain, DNSSEC TXT record) and bLIP-32 onion-message DNS resolution. USE WHEN: building/registering Lightning Addresses or BIP 353 names, designing resolver / payer wallet logic.

Open source license compliance and SPDX standards. Covers license types, compatibility, auditing with license-checker, and SBOM generation. USE WHEN: user mentions "license", "SPDX", "GPL", "MIT", "Apache", asks about "license compatibility", "license-checker", "copyleft", "proprietary compliance", "OSI approved" DO NOT USE FOR: dependency vulnerabilities - use `supply-chain`, security scanning - use `owasp-top-10`, secrets - use `secrets-management`

libsodium — modern, easy-to-use, audited crypto library. Provides authenticated encryption (XSalsa20-Poly1305, XChaCha20-Poly1305, AES-GCM), public-key cryptography (X25519, Ed25519), key derivation (Argon2id, HKDF, BLAKE2b), password hashing, and authenticated streams (secretstream). Wraps NaCl with better defaults. Bindings for Rust (sodiumoxide, libsodium-sys-stable, dryoc), Python (PyNaCl), JS (libsodium-wrappers), Java/Android (lazysodium-android), Swift (Sodium / Clibsodium). USE WHEN: user mentions "libsodium", "NaCl", "Sodium", "secretbox", "crypto_secretstream", "Argon2", "Argon2id", "X25519", "Ed25519", "PyNaCl", "lazysodium", "ChaCha20-Poly1305", "XSalsa20" DO NOT USE FOR: SQLite encryption - use `databases/sqlcipher` DO NOT USE FOR: File encryption format - use `security/age-encryption` DO NOT USE FOR: Bitcoin/secp256k1 crypto - use `bitcoin/cryptography/*` DO NOT USE FOR: TLS - use `security/rustls` or platform TLS stack

Late chunking (Jina method): embed the full document with a long-context encoder, then mean-pool token embeddings per chunk. Preserves cross-chunk context lost by traditional chunk-then-embed pipelines. USE WHEN: user mentions "late chunking", "Jina late chunking", "long-context embeddings", "cross-chunk context", "mean pool token embeddings", "jina-embeddings-v3", "token-level pooling for retrieval" DO NOT USE FOR: choosing chunk sizes - use `chunking-strategies`; picking an embedder - use `embedding-models`; fine-tuning - use `embedding-fine-tuning`

LangGraph state machines for RAG and agentic flows. Covers typed state, conditional edges for routing (answer/clarify/retrieve/rewrite), checkpointing with SqliteSaver/PostgresSaver, human-in-the-loop interrupts, multi-agent supervisor patterns, Self-RAG and CRAG as explicit graphs, combining with LangChain retrievers. USE WHEN: user mentions "LangGraph", "StateGraph", "agentic RAG", "conditional edges", "checkpointer", "human in the loop", "Self-RAG", "CRAG", "corrective RAG", "supervisor agent", "LangGraph RAG" DO NOT USE FOR: plain LangChain chains - use `langchain`; LlamaIndex workflows - use `llamaindex`; generic agentic RAG theory - use `agentic-rag`; DSPy programs - use `dspy`

LangChain framework for LLM application development. Covers chains, agents, tools, RAG pipelines, vector stores, memory, and LangChain Expression Language (LCEL). Python and TypeScript/JavaScript. USE WHEN: user mentions "langchain", "LLM chain", "AI agent", "LCEL", "retrieval chain", "LangChain tools", "LangSmith", "LangGraph" DO NOT USE FOR: direct API calls without framework - use Claude/OpenAI SDK; vector database specifics - use `vector-databases`; RAG architecture patterns - use `rag-patterns`

LanceDB columnar vector database. Arrow-native storage, versioning and time-travel, merge-on-read, full-text + vector hybrid, pandas/polars integration, object-storage backing, Rust-based performance, embedding function registration, IVF_PQ and HNSW indexes. USE WHEN: user mentions "LanceDB", "Lance format", "Arrow vector store", "embedded vector DB", "pylance", "lance time travel" DO NOT USE FOR: managed vector DBs - use `vector-stores/pinecone-advanced`, `vector-stores/mongodb-atlas-vector`; distributed Milvus - use `vector-stores/milvus`

Kubernetes container orchestration. Covers deployments, services, and configuration. Use for container orchestration. USE WHEN: user mentions "kubernetes", "k8s", "kubectl", "deployment", "pod", "service", "ingress", "configmap", "secret", asks about "container orchestration", "scaling", "rolling updates", "helm", "production cluster", "namespace" DO NOT USE FOR: local development environments - use `docker-compose` skill instead, Dockerfile creation - use `docker` skill instead, CI/CD workflows - use `github-actions` skill instead

Kotlin application security for backend and Android: vulnerability review and secure implementation patterns. USE WHEN: securing Kotlin applications (backend/Android), reviewing code for vulnerabilities, or implementing security best practices DO NOT USE FOR: code quality issues (use `kotlin-quality`), general Kotlin patterns, UI/UX concerns

Reviewing Kotlin code - what to flag, and what the compiler, detekt and ktlint already flag for you USE WHEN: you are reviewing, critiquing or auditing existing Kotlin code - a "code review", a "review" of a .kt file, a diff, a PR or a pull request; deciding what to comment on in Kotlin; avoiding false positives on Kotlin code DO NOT USE FOR: writing, explaining or learning Kotlin - use `languages/kotlin`; anything the compiler, detekt or ktlint already reports (this skill lists those so you can stay silent about them); Android framework specifics - use the Android skills; Spring specifics - use the Spring skills

Kotlin code quality toolchain — detekt (static analysis with rule sets, baseline, custom rules), ktlint (formatter + linter for the Kotlin style guide), and Compose-specific lint rules. Covers Gradle integration (KMP-aware), pre-commit hooks, CI integration, baseline files for legacy code, and config patterns for production apps including Jetpack Compose specifics (detekt-compose-rules). USE WHEN: user mentions "detekt", "ktlint", "ktlint-gradle", "detekt-gradle", "kotlin static analysis", "kotlin formatter", "kotlin lint", "compose-rules detekt", "kotlin code style", "detekt baseline" DO NOT USE FOR: Java-only static analysis - use SpotBugs/Checkstyle skill DO NOT USE FOR: Rust code quality - use `quality/rust-supply-chain` DO NOT USE FOR: Security-specific Kotlin issues - use `security/kotlin-security` DO NOT USE FOR: TypeScript linting - use eslint-specific skill

Kotlin Multiplatform (KMP) — share Kotlin code across Android, iOS, JVM Desktop, and JS/Wasm. Covers Gradle setup, source set hierarchy, expect/actual, target configuration, kotlinx-serialization, ktor-client, SQLDelight, multiplatform resources, and iOS framework export. USE WHEN: user mentions "Kotlin Multiplatform", "KMP", "expect/actual", "shared module", "cross-platform Kotlin", "iOSMain", "commonMain", "Kotlin/Native", "kotlinx-serialization", "SQLDelight" DO NOT USE FOR: Compose UI cross-platform - use `frontend-frameworks/compose-multiplatform` DO NOT USE FOR: Pure Kotlin language features - use `languages/kotlin` DO NOT USE FOR: Jetpack Compose Android-only - use `mobile/jetpack-compose` DO NOT USE FOR: Rust ↔ KMP bindings - use `languages/uniffi`

Kotlin language fundamentals. Covers null safety, coroutines, flow, sealed classes, data classes, scope functions, and Kotlin 2.x features (K2 compiler, context parameters). Use for Kotlin/JVM, Kotlin/Native, Kotlin/JS work. USE WHEN: user mentions "Kotlin", "coroutines", "suspend", "Flow", "sealed class", "data class", "scope functions", "K2 compiler", "ksp", "Kotlin 2.x" DO NOT USE FOR: reviewing existing Kotlin code - use `review/kotlin`, which covers the Java boundary and the concurrency the compiler does not check DO NOT USE FOR: Kotlin Multiplatform setup - use `mobile/kotlin-multiplatform` DO NOT USE FOR: Compose UI - use `frontend-frameworks/compose-multiplatform` DO NOT USE FOR: Spring Boot Kotlin - use `spring-boot` framework skill

Kotest — flexible, idiomatic Kotlin testing framework. Multiple specification styles (StringSpec, FunSpec, BehaviorSpec, DescribeSpec, FeatureSpec, FreeSpec), rich matcher library, property-based testing, data-driven tests, coroutine support, KMP-friendly. Drop-in alternative or complement to JUnit. USE WHEN: user mentions "Kotest", "io.kotest", "shouldBe", "StringSpec", "BehaviorSpec", "DescribeSpec", "kotest property testing", "Arb.list", "forAll", "kotest matchers", "kotlin tests" DO NOT USE FOR: JUnit-specific patterns - use junit skill (or framework-specific test skills) DO NOT USE FOR: Flow testing - use `testing/turbine` DO NOT USE FOR: Compose snapshot tests - use `testing/compose-snapshot` DO NOT USE FOR: Mobile E2E - use `testing/maestro`

Building knowledge graphs from unstructured text. LLM-based triple extraction (subject-predicate-object), schema-guided extraction via Pydantic + structured output, REBEL model, OpenIE, entity linking to Wikidata/DBpedia, validation with LLM judges, incremental KG updates, and exporting to Neo4j / Amazon Neptune / TigerGraph. Full pipeline. USE WHEN: user mentions "knowledge graph construction", "KG construction", "triple extraction", "OpenIE", "REBEL", "Pydantic triples", "entity linking Wikidata", "build knowledge graph", "extract triples" DO NOT USE FOR: graph RAG retrieval - use `graph-rag`; deduping/canonicalizing entities - use `entity-resolution`; ontology-aware retrieval - use `ontology-guided-retrieval`

Apache Kafka event streaming platform. Covers producers, consumers, topics, partitions, Kafka Streams, and Connect. Use for high-throughput event-driven architectures and real-time data pipelines. USE WHEN: user mentions "kafka", "event streaming", "kafka streams", "consumer groups", "topic partitions", asks about "high throughput messaging", "event sourcing", "log aggregation", "real-time pipelines" DO NOT USE FOR: simple queues - use `rabbitmq` or `activemq`; cloud-native lightweight - use `nats`; AWS-native - use `sqs`; Azure-native - use `azure-service-bus`; GCP-native - use `google-pubsub`

JSON Web Tokens for authentication. Covers token structure, signing, and validation. Use for stateless authentication. USE WHEN: user mentions "JWT", "token authentication", "access token", "refresh token", asks about "stateless auth", "token signing", "token validation" DO NOT USE FOR: session-based auth (use session management), OAuth flows (use oauth2 skill), NextAuth.js (use nextauth skill)

JUnit 5 testing framework with Mockito integration. Covers unit tests, mocking, and Spring Boot test integration. USE WHEN: user mentions "junit", "java test", "mockito", asks about "@Test", "@Mock", "@InjectMocks", "unit test java", "spring boot test" DO NOT USE FOR: Integration tests with containers - use `testcontainers`; REST API tests - use `rest-assured`; E2E tests - use Selenium; JavaScript/TypeScript - use `vitest` or `jest`

JSDoc and TSDoc documentation standards. Covers syntax, tags, TypeScript integration, documentation generation, and API documentation best practices. USE WHEN: user mentions "TSDoc", "TypeScript documentation", "API documentation", asks about "documenting TypeScript", "@param", "@returns", "TypeDoc", "API Extractor", "documentation tags" DO NOT USE FOR: JavaScript-only JSDoc - use `jsdoc` skill for plain JavaScript

JSDoc - documentation generator for JavaScript with type annotations. USE WHEN: user mentions "JSDoc", "JavaScript documentation", asks about "documenting JavaScript", "type hints", "jsdoc comments", "API documentation generation" DO NOT USE FOR: TypeScript - use `jsdoc-tsdoc` skill for TypeScript/TSDoc

Background job queue systems. BullMQ (Node.js), Celery (Python), Sidekiq (Ruby), Spring Batch. Job scheduling, retries, priorities, concurrency control, and dead letter queues. USE WHEN: user mentions "job queue", "background job", "BullMQ", "Bull", "Celery", "worker", "async task", "task queue", "Sidekiq" DO NOT USE FOR: cron scheduling without queue - use `cron-scheduling`; message brokers - use messaging skills (Kafka, RabbitMQ)

Jetpack Compose for native Android UI. Covers @Composable functions, state, side effects, ViewModel + Compose, Hilt DI, Navigation Compose, Material 3 with Dynamic Color (Material You), Compose for Wear OS, Compose previews, and Android lifecycle integration (Activity, Fragment interop). USE WHEN: user mentions "Jetpack Compose", "@Composable" in Android-only context, "ViewModel", "Hilt", "Navigation Compose", "Material You", "Dynamic Color", "Compose preview", "AndroidView", "rememberLauncherForActivityResult", "Compose Wear OS" DO NOT USE FOR: Cross-platform Compose - use `frontend-frameworks/compose-multiplatform` DO NOT USE FOR: Kotlin language fundamentals - use `languages/kotlin` DO NOT USE FOR: Android non-UI APIs (Keystore, NFC, etc) - use `mobile/android-native`

Jest testing framework. Covers unit tests, mocking, and snapshots. Use for testing React and Node.js projects. USE WHEN: user mentions "jest", "jest test", "snapshot test", asks about "jest.fn", "jest.mock", "toMatchSnapshot", "React testing" DO NOT USE FOR: E2E tests - use `playwright` or `cypress`; Vite projects - use `vitest` instead; React component testing alone - combine with `testing-library`

JavaScript language fundamentals. Covers ES6+, modules, async patterns. Use when working with plain JS projects without TypeScript. USE WHEN: user mentions "javascript", "ES6", "async/await", "promises", "modules", asks about "destructuring", "spread operator", "arrow functions", "ESM vs CommonJS" DO NOT USE FOR: TypeScript projects - use `typescript` skill instead DO NOT USE FOR: Node.js runtime - use `nodejs` skill instead DO NOT USE FOR: Browser APIs - use framework-specific skills

Java and Spring Boot security patterns. Covers Spring Security, dependency auditing, secure coding practices, and OWASP for Java ecosystem. USE WHEN: user works with "Java", "Spring Boot", "Spring Security", asks about "Java vulnerabilities", "Maven security", "Gradle security", "Java injection", "Java authentication" DO NOT USE FOR: general OWASP concepts - use `owasp` or `owasp-top-10` instead, Node.js/Python security - use language-specific skills

Reviewing Java code - what to flag, and what javac, the IDE and SpotBugs already flag for you USE WHEN: you are reviewing, critiquing or auditing existing Java code - a "code review", a "review" of a .java file, a diff, a PR or a pull request; deciding what to comment on in Java; avoiding false positives on Java code DO NOT USE FOR: writing, explaining or learning Java - use `languages/java`; anything javac warnings, SpotBugs or a standard Checkstyle run already report (this skill lists those so you can stay silent about them); Spring specifics - use the Spring skills; JPA mapping - use `backend-frameworks/spring-data-jpa`

Java code quality with Checkstyle, SpotBugs, PMD, and SonarJava. Covers static analysis, code style, and best practices. USE WHEN: user works with "Java", "Spring Boot", "Maven", "Gradle", asks about "Checkstyle", "SpotBugs", "PMD", "Java code smells", "Java best practices" DO NOT USE FOR: SonarQube generic - use `sonarqube` skill, testing - use Spring Boot test skills, security - use `java-security` skill

JVM performance profiling with Java Flight Recorder (JFR), jcmd, and GC analysis. Use for identifying bottlenecks and memory issues. USE WHEN: user mentions "Java profiling", "JFR", "JVM performance", asks about "Java Flight Recorder", "jcmd", "heap dump", "GC tuning", "thread dump", "Java memory leak" DO NOT USE FOR: Node.js/Python profiling - use respective skills instead

Java logging with SLF4J facade, Logback, and Log4j2 implementations. Covers configuration, log levels, structured logging, async logging, and production best practices for Spring Boot applications. USE WHEN: user mentions "java logging", "spring boot logging", "slf4j setup", asks about "how to log in java", "logback vs log4j2", "java logging best practices" DO NOT USE FOR: Node.js logging - use `nodejs-logging` instead, Python logging - use `python-logging`, Kotlin-specific logging - similar but has nuances

Java Foreign Function & Memory API (JEP 442/454, finalized in JDK 22+) plus jextract tool. Replaces JNI for calling C libraries from JVM/Kotlin without writing native glue. Critical for desktop apps needing OS interop (keyring, system APIs) on Linux/macOS/Windows. Covers Linker, MethodHandle, MemorySegment, Arena, struct layout, jextract code generation, and integration with KMP desktop targets. USE WHEN: user mentions "Foreign Memory API", "FFM API", "jextract", "MemorySegment", "Linker", "java.lang.foreign", "JEP 442", "JEP 454", "JDK 22 FFI", "Java FFI no JNI", "panama", "OS keyring Java" DO NOT USE FOR: Rust ↔ Kotlin/Swift bindings - use `languages/uniffi` DO NOT USE FOR: Mobile Android JNI - use `mobile/android-native` DO NOT USE FOR: Generic Java patterns - use Java-specific skill

Java language (17+). Covers modern features, patterns, and best practices. Use when writing Java applications, Spring Boot backends, or enterprise systems. USE WHEN: user mentions "java", "records", "sealed classes", "streams", asks about "pattern matching", "switch expressions", "Optional", "collections", "generics" DO NOT USE FOR: reviewing existing Java code - use `review/java`, which covers the defects javac and an unconfigured build do not report DO NOT USE FOR: Spring Boot specifics - use `backend-spring-boot` skill instead DO NOT USE FOR: Lombok annotations - use `lombok` skill instead DO NOT USE FOR: MapStruct - use `mapstruct` skill instead

JaCoCo Java code coverage tool USE WHEN: user mentions "JaCoCo", "Java coverage", "code coverage", asks about "coverage threshold", "jacoco-maven-plugin", "coverage report", "LINE coverage", "BRANCH coverage" DO NOT USE FOR: JavaScript/TypeScript coverage - use Vitest skill, SonarQube analysis - use `sonarqube` skill, test execution - use testing skills

ISA-5.1 tag naming, ISA-88 batch control, ISA-95 enterprise integration, ISA-18.2 alarm management, and ISA-101 HMI standards reference. Use when working with instrument tags, naming conventions, or plant hierarchy.

iOS native platform development with SwiftUI 6.x: app architecture (App protocol, Scene, WindowGroup), navigation (NavigationStack, NavigationSplitView), state (@State, @Binding, @Observable, @Environment), Keychain Services with biometric protection, Secure Enclave (P-256 hardware-isolated keys), App Lifecycle (BGTaskScheduler, Background Modes), Universal Links, App Groups, Share Extensions, Privacy Manifest, StoreKit 2. USE WHEN: user mentions "SwiftUI", "@Observable", "NavigationStack", "@AppStorage", "Keychain Services", "Secure Enclave", "BGTaskScheduler", "Universal Links", "App Groups", "Share Extension", "Privacy Manifest", "StoreKit", "iOS native", "@SceneStorage", "@FocusState" DO NOT USE FOR: Compose Multiplatform on iOS - use `frontend-frameworks/compose-multiplatform` DO NOT USE FOR: Swift language patterns - use `languages/swift` DO NOT USE FOR: Rust ↔ Swift bindings - use `languages/uniffi` DO NOT USE FOR: Cross-platform iOS+Android - use `mobile/kotlin-multiplatform`

Interaction design patterns for web interfaces. Covers motion and animation timing, microinteractions, loading states, skeleton screens, optimistic UI, form UX, mobile touch targets, thumb zones, and responsive interaction patterns. USE WHEN: user mentions "animation", "transition", "loading state", "skeleton screen", "microinteraction", "form UX", "touch target", "mobile UX", "thumb zone", "optimistic UI", "perceived performance", "CLS", "reduced motion", "bottom navigation", "hamburger menu", asks "how fast should animations be" DO NOT USE FOR: CSS animation syntax (use styling/tailwindcss), performance profiling (use best-practices/performance), WCAG audit (use accessibility/wcag)

Production ingestion pipelines with Airflow, Prefect 3, Dagster. DAG design for RAG: extract -> parse -> chunk -> embed -> index. Retry policies, idempotency, partial failure, monitoring, backfills, incremental vs full refresh, data lineage, upstream dependencies. Full Dagster and Prefect examples. USE WHEN: user mentions "ingestion pipeline", "Airflow RAG", "Prefect RAG", "Dagster RAG", "DAG for embeddings", "backfill embeddings", "incremental ingestion", "idempotent ingestion" DO NOT USE FOR: real-time streaming ingestion - use `cdc-streaming-ingestion`; chunking details - use `chunking-strategies`; eval - use `rag-evaluation`

LLM/model inference serving architecture: the engine → serving → orchestration layering (vLLM/SGLang/TensorRT-LLM, Triton, KServe/Ray Serve), KV-cache & continuous batching, prefill-decode disaggregation, and scaling. Architect-level topology, not model training. USE WHEN: designing model/LLM serving infra, "vLLM", "SGLang", "TensorRT-LLM", "Triton", "KServe", "Ray Serve", "continuous batching", "KV cache", "prefill decode", "TTFT", multi-GPU/multi-model serving, inference autoscaling. DO NOT USE FOR: on-device (use `edge-inference`); provider routing (use `model-gateway-routing`); RAG app logic (use rag/rag-frameworks skills).

Windows Indirect Display Driver (IDD) framework. UMDF v2-based driver model for adding virtual monitors that the Desktop Window Manager treats as real displays, then capturing the rendered frames in user mode and routing them somewhere else (network, file, encoder) instead of a physical panel. Covers IddCx callbacks, monitor descriptors (EDID/MCCS), swap-chain processing, cursor handling, hot-plug, hardware cursor, multi-monitor, HDR, and integration with NVENC / Rivermax / RDMA NICs for low-latency network streaming. USE WHEN: user mentions "IDD", "Indirect Display", "IddCx", "IddSampleDriver", "virtual monitor", "virtual display driver", "IDDCX_SWAPCHAIN", "AcquireBuffer", "FinishedProcessingFrame", "EDID for virtual display", "stream desktop", "network display" DO NOT USE FOR: WDDM display miniport drivers (real GPU), DXGK kernel work, Miracast (different framework), Remote Desktop / RDP (different stack)

Image processing and optimization. Sharp (Node.js), Pillow (Python), Cloudinary, responsive images, WebP/AVIF conversion, thumbnails, and CDN-based image transformation. USE WHEN: user mentions "image resize", "thumbnail", "image optimization", "Sharp", "Pillow", "Cloudinary", "WebP", "AVIF", "image upload processing" DO NOT USE FOR: file upload handling - use `file-upload`; cloud storage - use `cloud-storage`; PDF generation - use `pdf-generation`

IEC 61131-3 programming languages reference (LD, FBD, ST, IL, SFC), PLCopen standards, program organization units, data types. Use when discussing PLC programming standards or cross-platform compatibility.

Infrastructure-as-Code security for Terraform, CloudFormation, Ansible, Pulumi and similar configuration. USE WHEN: securing Terraform, CloudFormation, Ansible, Pulumi, or other IaC configurations DO NOT USE FOR: general IaC patterns, cloud architecture design, cost optimization

Internationalization and localization. i18next (React, Node.js), next-intl, vue-i18n, ICU message format, pluralization, date/number formatting, and RTL support. USE WHEN: user mentions "i18n", "internationalization", "localization", "l10n", "i18next", "translation", "next-intl", "vue-i18n", "ICU format", "RTL" DO NOT USE FOR: character encoding - general programming; currency/payment formatting - use `stripe`

Combining sparse (BM25, SPLADE) and dense vector retrieval. Reciprocal rank fusion with formula and code, weighted score fusion, alpha tuning, and native hybrid indexes in Pinecone, Qdrant, Weaviate. USE WHEN: user mentions "hybrid search", "BM25", "sparse dense", "RRF", "reciprocal rank fusion", "SPLADE", "learned sparse", "alpha tuning", "sparse dense hybrid" DO NOT USE FOR: rewriting queries before retrieval - use `query-transformations`; reranking after retrieval - use `reranking`; vector DB setup - use `vector-databases`

Hybrid edge-cloud AI architecture: local-first inference with cloud escalation, model cascading, and splitting the workload across device and datacenter to balance latency, cost, privacy, and quality. Architect-level topology. USE WHEN: designing systems that combine on-device and cloud AI, "local-first", "cloud fallback", "model cascade", "escalation", "hybrid inference", routing by confidence/complexity, edge+cloud trade-offs. DO NOT USE FOR: pure on-device (use `edge-inference`); pure cloud serving (use `inference-serving-topology`); multi-provider API routing (use `model-gateway-routing`).

HTTP clients for frontend and Node.js. Covers Axios, Fetch API, ky, and ofetch. Includes interceptors, error handling, retry logic, and auth token management. Use for configuring API clients and HTTP communication. USE WHEN: user mentions "HTTP client", "Fetch API", "ky", "ofetch", "HTTP wrapper", "retry logic", "token refresh", asks about "which HTTP client to use", "HTTP request library", "API client setup", "request interceptors" DO NOT USE FOR: Axios-specific questions - use `axios` instead; GraphQL - use `graphql-codegen` instead; tRPC - use `trpc` instead; WebSocket connections

Creates and configures Claude Code hooks for lifecycle automation. Covers all 17 hook events, 4 hook types (command, prompt, agent, http), matchers, input/output formats, and exit codes. Follows official Anthropic best practices. USE WHEN: user mentions "hook", "hooks", "auto-format", "pre tool use", "post tool use", "session start", "notification hook", "block command", "validate tool", "lifecycle event", "PostToolUse", "PreToolUse" DO NOT USE FOR: creating skills - use `skill-authoring`; creating agents - use `agent-authoring`; webhook endpoints - different concept

Hono ultrafast web framework for edge runtimes. Covers routing, middleware, and multi-runtime support. Use when building edge-first APIs. USE WHEN: user mentions "Hono", "hono", "Cloudflare Workers", "Vercel Edge", "edge runtime", "Bun", asks about "edge-first API", "multi-runtime framework", "ultrafast web framework", "lightweight edge functions" DO NOT USE FOR: Node.js-only apps - use `express`, `nestjs`, or `fastify` instead, Deno-specific features - use `oak` or `fresh` instead, Enterprise DI patterns - use `nestjs` instead

Windows Human Interface Device (HID) stack and filter drivers. Covers HID class architecture, transport drivers (HIDUSB / HIDBTH / HIDI2C), HIDClass, mouse/keyboard filter (Mouclass / Kbdclass) drivers, internal IOCTLs (IOCTL_HID_*), filter placement (upper/lower), event interception, injection, and the Virtual HID Framework (VHF). USE WHEN: user mentions "HID", "HID filter", "mouse filter", "keyboard filter", "touch filter", "pen filter", "HIDClass", "mouclass", "kbdclass", "moufiltr", "kbfiltr", "IOCTL_HID_READ_REPORT", "IOCTL_HID_GET_FEATURE", "VHF", "Vhf.sys", "input intercept", "input injection" DO NOT USE FOR: GPU input redirection (different stack), DirectInput/XInput (user-mode game APIs)

Health check and graceful shutdown patterns. Liveness and readiness probes, dependency health checks, Kubernetes probes, Spring Actuator health, and zero-downtime shutdown. USE WHEN: user mentions "health check", "liveness", "readiness", "probe", "graceful shutdown", "SIGTERM", "health endpoint", "/healthz" DO NOT USE FOR: monitoring dashboards - use `error-tracking` or `opentelemetry`; deployment strategies - use `deployment-strategies`

Haystack 2.x pipeline architecture for RAG and LLM apps. Covers Components, Pipeline as DAG, document stores (InMemory, Elasticsearch, Weaviate, Pinecone, Qdrant), Embedders, Retrievers (BM25, embedding, hybrid), Generators, PromptBuilder, conditional routing, and evaluation components. USE WHEN: user mentions "Haystack", "deepset", "Haystack pipeline", "Component DAG", "DocumentStore", "BM25Retriever", "ConditionalRouter" DO NOT USE FOR: LlamaIndex specifics - use `llamaindex`; LangChain - use `langchain`; DSPy - use `dspy`

Hardware-aware architecture for high performance: memory hierarchy & cache behavior, NUMA, SIMD/vectorization, mechanical sympathy, false sharing, and lock-free vs locked concurrency. Architect-level guidance on designing software that matches the machine. USE WHEN: latency/throughput-critical design, "cache miss", "NUMA", "SIMD", "false sharing", "memory bandwidth", "mechanical sympathy", "lock-free", "cache line", data-oriented design, hot-path performance architecture. DO NOT USE FOR: app-level profiling tasks (use the performance agent/skills); GPU/AI accelerator selection (use `ai-systems` hardware skill); networking (use `systems-networking`).

Deep hard-negative mining for dense retrievers: in-batch vs mined, BM25 / dense / cross-encoder mining, TAS-B, MarginMSE distillation, curriculum schedules, memory banks, false-negative filtering. USE WHEN: user mentions "hard negatives", "negative mining", "TAS-B", "MarginMSE", "distillation from cross-encoder", "curriculum negatives", "memory bank", "MoCo", "false negative filter" DO NOT USE FOR: basic fine-tuning setup - use `embedding-fine-tuning`; reranker training - out of scope; picking a pretrained model - use `embedding-models`

GSAP (GreenSock Animation Platform) — high-performance JavaScript animation engine with a plugin ecosystem. Covers tweens, easing, timelines, ScrollTrigger and the useGSAP React hook. USE WHEN: user mentions "GSAP", "GreenSock", "ScrollTrigger", "useGSAP", "timeline animation", "tween", asks about scroll-driven sequences or complex animation choreography DO NOT USE FOR: React-idiomatic declarative animation (use `framer-motion`), SVG path morphing basics (use `svg-animation`), 3D scenes (use `three-js`)

gRPC service development. Protocol Buffers (protobuf), service definitions, streaming (unary, server, client, bidirectional), interceptors, and code generation for Node.js, Go, Java, and Python. USE WHEN: user mentions "gRPC", "protobuf", "Protocol Buffers", ".proto", "grpc-js", "tonic", "grpc-java", "service mesh RPC" DO NOT USE FOR: REST APIs - use `rest-api`; GraphQL - use `graphql`; WebSocket - use real-time skills

GraphQL Code Generator for TypeScript. Generates typed operations, hooks, and document nodes from GraphQL schemas. Use for type-safe GraphQL in frontend. USE WHEN: user mentions "GraphQL Codegen", "generate GraphQL types", "GraphQL TypeScript", "typed GraphQL", "client preset", "React Query GraphQL", asks about "GraphQL code generation", "type-safe GraphQL client", "fragment masking" DO NOT USE FOR: REST API types - use `openapi-codegen` instead; tRPC - use `trpc` instead; GraphQL schema design - use `graphql` instead; Manual GraphQL queries without codegen

GraphQL API design. Covers schema, queries, mutations, and resolvers. Use when building or consuming GraphQL APIs. USE WHEN: user mentions "GraphQL", "schema definition", "resolvers", "mutations", "queries", "DataLoader", "N+1 problem", asks about "how to design GraphQL API", "GraphQL schema", "GraphQL authentication", "GraphQL pagination", "Apollo Server" DO NOT USE FOR: REST APIs - use `rest-api` instead; tRPC - use `trpc` instead; GraphQL code generation - use `graphql-codegen` instead

Knowledge-graph-augmented retrieval. Entity and triple extraction, graph construction (Neo4j, LlamaIndex PropertyGraphIndex), hierarchical community summarization (Microsoft GraphRAG), personalized PageRank (HippoRAG), multi-hop traversal retrieval, and hybrid graph + vector pipelines. USE WHEN: user mentions "GraphRAG", "HippoRAG", "knowledge graph RAG", "entity extraction", "multi-hop reasoning", "Neo4j RAG", "LlamaIndex property graph", "LangChain graph retriever", "triple extraction", "community summarization" DO NOT USE FOR: vanilla vector RAG - use `rag-patterns`; multimodal inputs - use `multimodal-rag`; production indexing ops - use `rag-production`; hallucination checks - use `rag-guardrails`

Gradle build system for Kotlin Multiplatform projects. Covers settings.gradle.kts, version catalogs (libs.versions.toml), KMP plugin configuration, source set hierarchy, target binaries (JAR, AAR, XCFramework, JS bundle), publishing (Maven Central, GitHub Packages), CI presets (build matrix, caching, parallel execution), composite builds, and dependency management. USE WHEN: user mentions "Gradle KMP", "settings.gradle.kts", "version catalog", "libs.versions.toml", "XCFramework Gradle", "publishToMavenCentral", "Gradle composite build", "Gradle build cache", "configuration cache", "Gradle CI" DO NOT USE FOR: Cross-compiling Rust crates - use `build-tools/rust-cross-compile` DO NOT USE FOR: Reproducible builds spec - use `infrastructure/reproducible-builds` DO NOT USE FOR: KMP source code patterns - use `mobile/kotlin-multiplatform`

Google Test (GTest) and Google Mock for C++ unit testing. Covers test fixtures, parameterized tests, typed tests, death tests, matchers, mocks (EXPECT_CALL), and CMake integration via gtest_discover_tests. USE WHEN: user mentions "Google Test", "GTest", "gmock", "EXPECT_EQ", "TEST_F", "INSTANTIATE_TEST_SUITE_P", "EXPECT_CALL", "MOCK_METHOD", "C++ unit test" DO NOT USE FOR: Catch2 (different framework), doctest, Boost.Test, CppUnit

Google Cloud Pub/Sub messaging service. Covers topics, subscriptions, push/pull delivery, and dead-letter handling. Use for GCP-native event-driven architectures and real-time analytics. USE WHEN: user mentions "google pub/sub", "pubsub", "gcp messaging", "push subscription", "pull subscription", asks about "cloud pub/sub", "ordering keys", "bigquery subscription" DO NOT USE FOR: AWS-native - use `sqs`; Azure-native - use `azure-service-bus`; event streaming - use `kafka` or Dataflow; on-premise - use `rabbitmq` or `activemq`; multi-cloud - use `kafka` or `pulsar`

Go testing with go test, testify, and gomock. Covers unit tests, table-driven tests, benchmarks, mocking, and test coverage. USE WHEN: user mentions "go test", "golang test", "testify", asks about "table-driven test", "gomock", "go benchmark", "testing.T", "httptest" DO NOT USE FOR: JavaScript/TypeScript - use `vitest` or `jest`; Java - use `junit`; Python - use `pytest`; E2E browser tests - use Playwright; Rust - use `rust-testing`

Go security patterns for web applications. Covers dependency auditing, secure coding practices, crypto, and OWASP for Go ecosystem. USE WHEN: user works with "Go", "Golang", "Gin", "Fiber", "Echo", asks about "Go vulnerabilities", "Go modules security", "Go injection", "Go authentication" DO NOT USE FOR: general OWASP concepts - use `owasp` or `owasp-top-10` instead, other language security - use language-specific skills

Reviewing Go code - what to flag, and what the toolchain already flags for you USE WHEN: you are reviewing, critiquing or auditing existing Go code - a "code review", a "review" of a .go file, a diff, a PR or a pull request; deciding what to comment on in Go; avoiding false positives on Go code DO NOT USE FOR: writing, explaining or learning Go - use `languages/go`; anything `go vet` or a default golangci-lint run already reports (this skill lists those so you can stay silent about them); framework specifics - use the Gin/Echo/Fiber skills

Go code quality with golangci-lint, staticcheck, and go vet. Covers linting, formatting, and best practices. USE WHEN: user works with "Go", "Golang", "Gin", "Fiber", "Echo", asks about "golangci-lint", "staticcheck", "go vet", "Go linting", "Go best practices" DO NOT USE FOR: SonarQube - use `sonarqube` skill, testing - use Go test skills, security - use `go-security` skill

Go programming language. Covers goroutines, channels, interfaces, error handling, and modules. Use for building concurrent, high-performance backend services. USE WHEN: user mentions "go", "golang", "goroutines", "channels", asks about "concurrency", "select statement", "interfaces", "error handling", "go modules" DO NOT USE FOR: reviewing existing Go code - use `review/go`, which covers the defects the compiler and linters do not report DO NOT USE FOR: Gin/Fiber/Echo frameworks - use framework-specific skills DO NOT USE FOR: GORM - use ORM-specific skill DO NOT USE FOR: gRPC - use API design skills

GitHub Actions CI/CD. Covers workflows, jobs, and deployment. Use for automating builds, tests, and deployments. USE WHEN: user mentions "github actions", "workflow", "ci/cd", ".github/workflows", "actions/checkout", "github workflow", asks about "automate tests", "deploy on push", "build pipeline", "ci pipeline", "continuous integration", "github automation" DO NOT USE FOR: GitLab CI/CD - different syntax and features, Jenkins pipelines - different tool, Container orchestration - use `docker` or `kubernetes` skills, Local builds - workflows run on GitHub runners

Git workflow best practices. Covers branching, commits, and collaboration. Use for version control guidance. USE WHEN: user mentions "git", "commit", "branch", "pull request", "PR", "merge", "rebase", "version control", asks about "commit message", "branching strategy", "git best practices", "conventional commits", "how to write PR description" DO NOT USE FOR: Git commands syntax - use git documentation, GitHub Actions CI/CD - use ci-cd skills, Code review quality - use `code-reviewer` agent

Giskard RAGET (RAG Evaluation Toolkit): automatic testset generation (simple / complex / distracting / conversational), component-level scoring (retriever / generator / rewriter), hallucination and bias tests, CI integration. Compared to RAGAS and DeepEval. USE WHEN: user mentions "Giskard", "RAGET", "Giskard RAG toolkit", "automatic testset generation", "component-level RAG scoring", "hallucination test Giskard" DO NOT USE FOR: general RAGAS usage - use `rag-evaluation`; Stanford ARES - use `ares-framework`; CI/CD wiring - use `continuous-evaluation`

Gin Go web framework. Covers routing, middleware, binding, validation, and rendering. Use for fast, minimalist Go APIs. USE WHEN: user mentions "gin", "gin-gonic", "go web framework", "go rest api", asks about "gin middleware", "gin binding", "gin validation", "gin router", "fast go api", "gin context" DO NOT USE FOR: Echo projects - use `echo` instead, Fiber projects - use `fiber` instead, Chi projects - use `chi` instead, non-Go backends

GDPR compliance implementation. Data subject rights (access, deletion, portability), consent management, data processing records, PII handling, and privacy by design patterns. USE WHEN: user mentions "GDPR", "data privacy", "right to be forgotten", "data deletion", "consent management", "PII", "data subject request", "privacy policy", "cookie consent" DO NOT USE FOR: authentication - use auth skills; encryption - use `cryptography`; audit logging - use `audit-logging`

Google Cloud Platform SDK integration. Cloud Functions, Firestore, Cloud Storage, Pub/Sub, BigQuery, and Cloud Run. Node.js and Python client libraries. USE WHEN: user mentions "GCP", "Google Cloud", "Cloud Functions", "Firestore", "Cloud Storage", "Pub/Sub", "BigQuery", "Cloud Run", "Firebase" DO NOT USE FOR: AWS services - use `aws`; Azure services - use `azure`; Firebase Auth - use auth skills

Visual effects in 2D: frame patterns for smoke / fire / water / electricity, hitstop and hit pause, screen shake intensity curves, particle frames vs procedural particles, juice principles (Vlambeer "Art of Screenshake"), trail effects, color flash, debris, decals. USE WHEN: authoring effect sprites, deciding pre-baked vs procedural particles, designing impact / juice for actions.

Tool ecosystem for 2D game art: Aseprite (de facto pixel art DCC), Tiled, LDtk, Tilesetter (autotile generation), Pixelorama (FOSS), Spine / DragonBones (skeletal 2D), TexturePacker, Sprite Lamp / Sprite DLight (normal maps), PSD Importer / Aseprite Importer, Krita / Procreate / Photoshop for higher-res 2D. USE WHEN: choosing tools for a 2D project, integrating tool output with engine, scripting Aseprite Lua, evaluating LDtk vs Tiled.

Tile design for 2D games: autotiling math (Wang 4-bit, 16-bit, 47-tile, 256-tile blob), grid types (square / hex flat-top / hex pointy-top / staggered iso / true iso), terrain blending, transitional pieces, modular vs composite tilesets, 9-slice rendering. USE WHEN: planning tilesets, choosing autotile schemes, mixing terrains, designing isometric or hex maps, debugging tile transitions. DO NOT USE FOR: engine-specific tilemap APIs (Unity Tilemap component, Godot TileMap node) - use the engine skill (e.g., `unity-2d-tilemap`).

Seamless / tileable textures for 2D: offset-and-paint trick, mirror techniques, repetition reduction (variant tiles + decoration overlays), transitional tiles (corner / edge / T-junction), normal map authoring for 2D lighting (Sprite Lamp / Sprite DLight / Materialize), procedural base + hand-pixel overlay, roof/floor/wall specializations. USE WHEN: painting tilesets that don't visibly seam, fixing repetition, adding normal maps to 2D for dynamic lighting, mixing procedural and hand-painted texture.

Pixel art fundamentals: resolution choice, anti-aliasing rules, dithering (Bayer / Floyd-Steinberg / hand-placed), outline philosophy, pixel hinting / sub-pixel rules, common mistakes (pillow shading, PSD-soft rendering, jaggies). USE WHEN: starting a pixel-art project, evaluating sprite quality, fixing soft / blurry pixel art, choosing resolution. DO NOT USE FOR: vector / painterly 2D art (different rules entirely); AI sprite generation (see `unity-2d-core` AI section).

Color palettes for 2D games: color theory practical (warm/cool, complementary, analogous), restricted palettes ready-made (PICO-8, GameBoy DMG, DB16, DB32, AAP-64, NES, C64), hue shifting (warm-cool ramps), palette swaps for character variants and time-of-day, indexed mode workflow, .gpl/.pal/.ase/.json export. USE WHEN: starting a project's palette, choosing restricted palette, designing color ramps for shading, planning palette swaps.

Painting 2D art for dynamic lighting: workflow for Unity 2D Lights / Godot CanvasLight, normal map authoring (Sprite Lamp / hand-painted), separation in layers (diffuse / normal / emissive / mask), self- shadowing in pixel art, day/night palette swaps vs realtime light mixing, glow / emissive layers. USE WHEN: integrating 2D Lights with hand-painted sprites, deciding baked vs dynamic lighting, painting normal maps for pixel art.

Environmental art for 2D games: parallax planning (3-5 layers, depth distribution, scroll-speed ratios), foreground/background composition, atmospheric perspective via palette desaturation, silhouette readability, vignettes / framing, tile density vs negative space, environmental storytelling via tiles. USE WHEN: planning level art, designing parallax layers, fixing cluttered or unreadable scenes, telling story through environment.

Character design for 2D games: silhouette-first methodology, character- to-tile size ratio, expressions in low resolution (eye / mouth pixel placement), anatomy shortcuts in pixel art, faction/role visual language (silhouette + palette identifying class), walk cycle conveying weight and attitude. USE WHEN: designing a new character, fixing unreadable / cluttered characters, distinguishing factions visually, assessing animation weight.

Frame-by-frame animation for 2D games: typical frame counts (idle 2-4f / walk 6-8f / run 6-8f / attack 4-6f), squash/stretch limits in pixel art, looping cycles, sub-pixel motion problem, anticipation/impact/ recovery beats, sprite sheet layout (Aseprite tags, TexturePacker JSON, Unity Sprite Editor), frame timing easing. USE WHEN: animating sprites, choosing frame counts, debugging "stiff" or "floaty" motion, organizing sprite sheets. DO NOT USE FOR: skeletal 2D animation (Spine/DragonBones, Unity 2D Animation) - different rules. See `unity-2d-animation` skill.

AI-assisted 2D / pixel-art generation tools and services. Covers pixel-art-specific generators (PixelLab, Retro Diffusion), game-asset generators (Scenario, Leonardo.AI), DIY Stable Diffusion + LoRAs, and general models with pixel-art prompting (Midjourney, DALL-E, Imagen). Trade-off framework: control vs. speed, palette consistency, animation coherence, tile-ability, commercial license, runs locally vs. cloud, cost per asset / per month. USE WHEN: deciding which AI tool fits a project, generating placeholder assets, generating final assets at scale, integrating an AI sprite pipeline, evaluating commercial license, comparing API costs. DO NOT USE FOR: hand-painted-only workflows (use `tools` skill), 3D / model generation (out of scope), engine integration of finished sprites (use `tools` + engine-specific skill).

Game-engine architecture, engine-agnostic: the game loop (fixed vs variable timestep), ECS vs scene-graph/OOP, the render pipeline, core subsystems (physics, audio, animation, assets, memory), and netcode models. Architect- level, beyond any specific engine. USE WHEN: designing/evaluating a game engine or game's architecture in general, "game loop", "ECS", "entity component system", "render pipeline", "forward vs deferred", "rollback netcode", "lockstep", custom engine vs off-the-shelf, data-oriented game design. DO NOT USE FOR: Unity-specific work (use the `gamedev/unity-*` skills); low-level cache/SIMD detail (use `hardware-aware-design`); web graphics (use graphics skills).

Fresh Deno web framework. Covers islands architecture, file-based routing, handlers, signals, and plugins. Use for server-rendered Deno applications. USE WHEN: user mentions "Fresh", "fresh", "islands architecture", "Deno SSR", "file-based routing in Deno", asks about "Preact SSR", "server-rendered Deno apps", "Deno web framework with hydration", "zero-config Deno framework" DO NOT USE FOR: Node.js apps - use `nextjs` or `remix` instead, Pure API servers - use `oak` instead, Edge runtimes - use `hono` instead, Static sites - use SSG tools like Astro

Complete ABB Freelance DCS file format reference for DMF, PRT, and CSV project files. Use when analyzing, parsing, or generating Freelance engineering files.

Framer Motion animation library for React. Declarative, physics-based and gesture-aware: variants and orchestration, AnimatePresence, FLIP layout animation, scroll-linked motion, spring configuration and gestures. USE WHEN: user mentions "Framer Motion", "motion.div", "AnimatePresence", "variants", "layout animation", "spring animation", asks about animating a React component, exit animations, drag or gesture handling DO NOT USE FOR: timeline-based or non-React animation (use `gsap`), SVG-specific animation (use `svg-animation`), pure CSS effects (use `advanced-css-effects`)

Flyway database migrations for Spring Boot applications. Covers migration scripts, versioning, callbacks, and rollback strategies. Based on production patterns from castellino and gestionale-presenze projects. USE WHEN: user mentions "flyway", "database versioning", "Java migrations", "Spring Boot migrations", "V1__", "migration checksum" DO NOT USE FOR: general migration strategies - use `migrations` instead, Liquibase - use specific tool skill, Prisma/TypeORM - use respective skills

Flutter cross-platform development with Dart. Widgets, state management (Riverpod, BLoC), navigation, platform channels, and production patterns. USE WHEN: user mentions "Flutter", "Dart", "flutter widget", "Riverpod", "BLoC", "flutter build", "pubspec.yaml" DO NOT USE FOR: React Native - use `react-native`; Expo - use `expo`; native iOS/Android

Flask lightweight Python framework. Covers routing, blueprints, and extensions. Use for simple Python APIs and microservices. USE WHEN: user mentions "flask", "flask blueprints", "python microservice", asks about "flask-restful", "flask extensions", "lightweight python api", "flask-sqlalchemy", "flask-jwt", "flask middleware" DO NOT USE FOR: Django projects - use `django` instead, FastAPI with type validation - use `fastapi` instead, async-first APIs, applications requiring built-in admin panel

Linux firewall configuration skill: UFW (Uncomplicated Firewall), iptables, nftables fundamentals, and fail2ban intrusion prevention. USE WHEN: - Setting up UFW on a new server (default deny-in, allow-out, selective port opens) - Configuring rate limiting and per-IP connection limits with UFW or iptables - Installing and tuning fail2ban for SSH, Nginx, and custom application jails - Writing iptables NAT rules (MASQUERADE for WireGuard/VPN, DNAT for port forwarding) - Diagnosing lockouts, fail2ban false positives, or blocked legitimate traffic - Setting up cloud security groups as the first layer of defence DO NOT USE FOR: - Application-level authentication / authorisation (use authentication skill) - SSL/TLS certificate management (use ssl-tls skill) - Kubernetes NetworkPolicy rules (use kubernetes skill) - WAF (Web Application Firewall) rules — Nginx rate limiting covers basic cases

Server-side file upload handling. Covers Multer (Node.js/Express), FastAPI UploadFile (Python), Spring MultipartFile (Java). File validation, streaming, size limits, and storage strategies. USE WHEN: user mentions "file upload", "multipart", "multer", "upload endpoint", "form data", "file validation", "image upload", "MultipartFile", "UploadFile" DO NOT USE FOR: cloud storage (S3/GCS/Azure) - use `cloud-storage`; file download/export - use `data-export`

Fiber Go web framework inspired by Express. Covers routing, middleware, context, WebSocket, and prefork. Use for Express-like Go development. USE WHEN: user mentions "fiber", "gofiber", "express-like go", "fasthttp go", asks about "fiber middleware", "fiber context", "fiber prefork", "fiber websocket", "go express", "fast go framework" DO NOT USE FOR: Gin projects - use `gin` instead, Echo projects - use `echo` instead, Chi projects - use `chi` instead, standard net/http compatibility required

User feedback signals for RAG improvement: thumbs up/down, click-through, dwell time, explicit ratings. Implicit vs explicit signals, logging schema, feedback -> retraining pipelines (embedding fine-tuning with hard negatives, reranker fine-tuning from CTR), A/B testing RAG variants, Langfuse/LangSmith feedback APIs, feature stores for online learning. USE WHEN: user mentions "user feedback", "thumbs up down", "CTR", "dwell time", "RAG evaluation feedback", "hard negatives", "reranker fine-tune", "A/B test RAG" DO NOT USE FOR: offline eval metrics - use `rag-evaluation`; retriever algorithms - use `advanced-retrieval`; observability as such - use `rag-observability`

Feature flag management. LaunchDarkly, Unleash, Flagsmith, and custom implementations. Gradual rollouts, A/B testing, kill switches, and flag lifecycle management. USE WHEN: user mentions "feature flag", "feature toggle", "LaunchDarkly", "Unleash", "Flagsmith", "gradual rollout", "A/B test", "canary release", "kill switch" DO NOT USE FOR: CI/CD deployment strategies - use `github-actions`; environment config - use environment variable patterns

Fastify high-performance Node.js framework. Covers routing, plugins, validation, and serialization. Use when building fast Node.js APIs. USE WHEN: user mentions "Fastify", "fastify", "TypeBox", "schema validation", asks about "fast Node.js framework", "high-throughput API", "JSON schema validation", "performance-critical backend", "plugin-based architecture" DO NOT USE FOR: Enterprise DI patterns - use `nestjs` instead, Minimalist approach - use `express` instead, Edge runtimes - use `hono` instead, Deno - use `oak` or `fresh` instead

FastAPI integration testing specialist. Covers synchronous TestClient, async httpx AsyncClient, dependency injection overrides, auth testing (JWT, OAuth2, API keys), WebSocket testing, file uploads, background tasks, middleware testing, and HTTP mocking with respx, responses, and pytest-httpserver. USE WHEN: user mentions "FastAPI test", "TestClient", "httpx async test", "dependency override test", "respx mock", asks about testing FastAPI endpoints, authentication in tests, or HTTP client mocking. DO NOT USE FOR: Django - use `pytest-django`; pytest internals - use `pytest`; Container infrastructure - use `testcontainers-python`

FastAPI modern Python web framework. Covers routing, Pydantic models, dependency injection, and async support. Use when building Python APIs. USE WHEN: user mentions "fastapi", "pydantic", "async python api", "python rest api", asks about "dependency injection python", "python openapi", "python swagger", "async endpoints", "python api validation", "fastapi middleware" DO NOT USE FOR: Django apps - use `django` instead, Flask apps - use `flask` instead, synchronous Python APIs without type hints, GraphQL-only APIs

factory_boy test data generation specialist. Covers Factory, DjangoModelFactory, SQLAlchemyModelFactory, all field declarations (Faker, LazyAttribute, Sequence, SubFactory, RelatedFactory, post_generation, Trait, Maybe, Dict, List), batch creation, pytest integration, and Celery task testing patterns. USE WHEN: user mentions "factory_boy", "test factory", "DjangoModelFactory", "SQLAlchemyModelFactory", asks about "test data generation", "factory traits", "SubFactory", "factory fixtures". DO NOT USE FOR: pytest internals - use `pytest`; Django setup - use `pytest-django`; Hypothesis property testing - use `pytest` with Hypothesis

Express.js minimal Node.js web framework. Covers routing, middleware, error handling, and API design. Use when building Express APIs. USE WHEN: user mentions "Express", "express.js", "app.use", "middleware", "express Router", asks about "minimalist Node.js framework", "simple REST API", "lightweight web server", "Node.js middleware pattern" DO NOT USE FOR: Enterprise applications with DI - use `nestjs` instead, High-performance APIs - use `fastify` instead, Edge runtimes - use `hono` instead, Deno - use `oak` or `fresh` instead

Expo framework for React Native. Managed and bare workflows, Expo Router, EAS Build/Submit/Update, config plugins, and Expo SDK modules. USE WHEN: user mentions "Expo", "expo-router", "EAS Build", "expo-cli", "app.json", "expo-config-plugin", "Expo Go" DO NOT USE FOR: bare React Native without Expo - use `react-native`; Flutter - use `flutter`

Event Sourcing and CQRS patterns. Event stores, projections, snapshots, command handlers, query models, and eventual consistency. Covers EventStoreDB, Axon Framework, and custom implementations. USE WHEN: user mentions "event sourcing", "CQRS", "event store", "projection", "command handler", "read model", "write model", "EventStoreDB", "Axon" DO NOT USE FOR: simple event-driven architecture - use `event-driven`; message brokers - use messaging skills; DDD basics - use `ddd`

Event-driven architecture patterns and best practices. Covers Saga, Outbox, CQRS, Event Sourcing, and messaging patterns for distributed systems. USE WHEN: user mentions "event-driven", "Saga", "Outbox pattern", "CQRS", "Event Sourcing", "distributed transactions", "eventual consistency", "message broker", "event bus", asks about "microservices communication", "async patterns", "compensating transactions" DO NOT USE FOR: Simple pub/sub - use messaging framework skills (Kafka, RabbitMQ), REST APIs - use API design skills, Real-time updates - use WebSocket skills, Basic async/await - use language-specific skills

ETL/ELT data pipeline patterns. Extract from APIs/databases, transform with streaming or batch, load to data warehouses. Node.js streams, Python pandas/Polars, Apache Airflow DAGs, and database-native ELT. USE WHEN: user mentions "ETL", "ELT", "data pipeline", "data ingestion", "Airflow", "data warehouse", "batch processing", "data migration" DO NOT USE FOR: real-time event streaming - use messaging skills; data export to CSV/Excel - use `data-export`

ESLint 9 flat config and Biome linter configuration. Covers typescript-eslint, rule categories, migration from legacy config, and performance optimization. USE WHEN: user mentions "ESLint 9", "Biome", "flat config", "eslint.config.mjs", asks about "typescript-eslint", "migration to ESLint 9", "linter performance", "Biome vs ESLint" DO NOT USE FOR: legacy ESLint - use `eslint` skill, Java/Spring - use SonarQube, basic linting concepts - use `quality-common`

ESLint - pluggable JavaScript/TypeScript linter USE WHEN: user mentions "ESLint", "JavaScript linting", ".eslintrc", asks about "eslint config", "linting rules", "eslint plugins", "flat config" DO NOT USE FOR: Biome - use `eslint-biome` skill, TypeScript-specific - use `typescript-eslint` skill, code quality principles - use `quality-common`

esbuild extremely fast JavaScript bundler. Used internally by Vite. Use for simple bundling, library builds, or understanding Vite internals. USE WHEN: user mentions "esbuild", "fast bundler", asks about "esbuild config", "library bundling", "esbuild API" DO NOT USE FOR: Complex apps (use Vite), Webpack projects (use webpack skill), need extensive plugins (use Rollup/Webpack)

Error tracking and monitoring integration. Sentry, Datadog RUM, Bugsnag. Source maps, breadcrumbs, release tracking, performance monitoring, and alerting configuration. USE WHEN: user mentions "Sentry", "error tracking", "Bugsnag", "Datadog RUM", "crash reporting", "source maps", "release tracking", "error monitoring" DO NOT USE FOR: application logging - use logging skills; APM/tracing - use `opentelemetry`; structured error responses - use `error-handling`

Error handling patterns across languages and frameworks. Custom error classes, global exception handlers, Problem Details (RFC 9457), error boundaries (React), Result types, and structured error responses. USE WHEN: user mentions "error handling", "exception handler", "error boundary", "custom error", "Problem Details", "error response", "global error handler" DO NOT USE FOR: logging errors - use logging skills; error tracking services - use `error-tracking`

Standardized error response handling between frontend and backend. Covers error structure, status codes, and consistent error handling. USE WHEN: user asks about "error handling", "API errors", "error response format", "status codes", "error messages", "validation errors" DO NOT USE FOR: logging - use logging skills, exception handling - use language-specific skills

Entity resolution (ER) for multi-source RAG and knowledge graphs. Dedup entities across documents ("Acme Corp" = "Acme, Inc." = "Acme Corporation"). Covers blocking, probabilistic linking (Splink), Dedupe.io, embedding-based matching, LLM-assisted resolution with rules, graph-based resolution (merged nodes), canonical IDs, and mapping tables. USE WHEN: user mentions "entity resolution", "record linkage", "dedup", "deduplication", "Splink", "Dedupe.io", "canonicalization", "entity matching", "coreference resolution" (corpus-level) DO NOT USE FOR: building a KG from scratch - use `knowledge-graph-construction`; retrieval tactics - use `graph-rag`; ontology-aware retrieval - use `ontology-guided-retrieval`

Entity Framework Core with DbContext, migrations, LINQ queries, relationships, and performance optimization. Covers EF Core 8+ patterns. USE WHEN: user mentions "Entity Framework", "EF Core", "DbContext", "migrations", "LINQ", "EF relationships", "database first", "code first" DO NOT USE FOR: Prisma - use `prisma`, Drizzle - use `drizzle`, Spring Data JPA - use `spring-data-jpa`, Dapper (raw SQL)

Embedding model selection across providers (OpenAI, Voyage, Cohere, BGE, E5, Jina, Nomic, mixedbread). Covers MTEB benchmarks, dimensions, cost, latency, multilingual support, instruction-tuning, and query-vs-document modes. USE WHEN: user mentions "which embedding model", "text-embedding-3", "voyage-3", "cohere embed", "BGE", "E5", "nomic-embed", "mxbai", "MTEB", "embedding benchmark", "embedding dimensions", "embedding cost" DO NOT USE FOR: multilingual-specific tradeoffs - use `multilingual-embeddings`; fine-tuning models - use `embedding-fine-tuning`; MRL truncation - use `matryoshka-embeddings`; vector database choice - use `vector-stores/*`

Fine-tuning sentence embedding models with sentence-transformers. Contrastive objectives (MultipleNegativesRankingLoss, TripletLoss, CoSENT), domain adaptation, synthetic query generation (GPL), hard negative mining, and downstream retrieval evaluation. USE WHEN: user mentions "fine-tune embeddings", "domain adaptation", "sentence-transformers training", "contrastive loss", "hard negatives", "GPL", "synthetic queries", "MNR loss", "triplet loss" DO NOT USE FOR: picking a pretrained model - use `embedding-models`; MRL truncation - use `matryoshka-embeddings`; reranker training - out of scope

Embedded, firmware, and real-time systems architecture: bare-metal vs RTOS (FreeRTOS/Zephyr), real-time scheduling (RMS/EDF), WCET and schedulability, priority inversion, interrupt latency, memory/energy budgets, MMU-less design. USE WHEN: designing firmware/embedded/IoT/MCU systems, real-time deadlines, "RTOS", "FreeRTOS", "Zephyr", "bare-metal", "WCET", "hard real-time", "priority inversion", "interrupt latency", "deadline", microcontroller architecture. DO NOT USE FOR: general OS/kernel design (use `os-kernel-architecture`); cloud/server perf (use `hardware-aware-design`); app code (use language skills).

Email sending integration. Covers Nodemailer (Node.js), Spring Mail (Java), smtplib (Python). Transactional email services: SendGrid, Amazon SES, Resend. Template engines: MJML, React Email. USE WHEN: user mentions "send email", "nodemailer", "SMTP", "SendGrid", "SES", "Resend", "transactional email", "email template", "MJML", "React Email", "spring mail" DO NOT USE FOR: push notifications - use `push-notifications`; SMS - different channel; email parsing/reading

Email ingestion for RAG. Covers EML (Python email module, mailparser), MSG (extract-msg), Gmail and Outlook APIs, thread reconstruction via In-Reply-To / References, recursive attachment handling, signature/quote redaction, chain deduplication, and metadata (sender, date, subject) preservation. USE WHEN: user mentions "email ingestion", "EML", "MSG file", "mailparser", "extract-msg", "Gmail API", "Outlook API", "Microsoft Graph mail", "email thread", "reply-to header", "email attachments", "signature stripping" DO NOT USE FOR: PDF attachments inside emails (extract here, then route to `pdf-extraction`); office attachments (route to `office-docs`); image attachments needing OCR - route to `ocr`; calendar ICS files - not covered here

Email deliverability and DNS-based email authentication covering SPF, DKIM, DMARC, MX, PTR, and BIMI records, SMTP relay service configuration (SendGrid, SES, Postmark, Mailgun), self-hosted Postfix relay basics, and deliverability testing. USE WHEN: - Setting up or auditing email DNS records (SPF, DKIM, DMARC, MX, PTR) - Configuring a transactional email relay service (SendGrid, Amazon SES, Postmark) - Rolling out a DMARC policy from p=none to p=reject - Debugging emails landing in spam or being rejected - Generating DKIM key pairs for a custom domain - Setting up Postfix as a smart relay host - Checking email blacklists and Google Postmaster Tools DO NOT USE FOR: - Building a full mail server (Dovecot IMAP, Postfix + Dovecot stack — scope is relay/deliverability) - Marketing email platform setup (Mailchimp, Klaviyo campaign workflows) - Email template design or HTML email rendering - Inbound email parsing pipelines (use SendGrid Inbound Parse, Mailgun Routes, etc.)

Electron framework for building cross-platform desktop applications with JavaScript, HTML, and CSS. Covers architecture, IPC, security, packaging, auto-updates, and backend integration patterns. USE WHEN: user mentions "Electron", "desktop app", "cross-platform application", asks about "IPC", "main process", "renderer process", "Electron packaging", "auto-updates", "code signing", "Electron security" DO NOT USE FOR: Tauri applications - use `tauri` skill instead

Elasticsearch 8.15+ vector search. dense_vector with HNSW, kNN search, hybrid BM25 + kNN with RRF, reranker integration, ELSER learned-sparse, sparse_vector, int8 scalar quantization, and index performance tuning. USE WHEN: user mentions "elasticsearch vector", "dense_vector", "kNN search", "ELSER", "sparse_vector elastic", "elasticsearch RRF", "elasticsearch hybrid search" DO NOT USE FOR: classic full-text only - use Elasticsearch search skills; other vector DBs - use other `vector-stores/*`

Elasticsearch search and analytics engine. Full-text search, aggregations, document store. Use when implementing search functionality or log analytics. USE WHEN: user mentions "elasticsearch", "full-text search", "search indexing", "log analytics", "ELK stack", "aggregations", "faceted search", "autocomplete", "suggestions" DO NOT USE FOR: primary database - use `postgresql` or `mongodb` instead, caching - use `redis` instead, ACID transactions - use SQL databases instead

Edge / on-device AI inference architecture: running models on MCUs, NPUs, mobile, and mini-PCs; quantization for edge, TOPS/memory/energy budgets, TinyML, and the latency case for on-device vs cloud. Architect-level. USE WHEN: designing on-device/edge AI, "edge inference", "on-device", "NPU", "TinyML", "quantization", "Jetson", "Coral", "Hailo", local LLM on small hardware, offline/low-latency inference, energy-constrained ML. DO NOT USE FOR: cloud GPU serving (use `inference-serving-topology`); choosing datacenter accelerators (use `ai-hardware-selection`); RAG app code (use rag skills).

Echo Go web framework. Covers routing, middleware, binding, context, and WebSocket. Use for high-performance, minimalist Go APIs. USE WHEN: user mentions "echo", "labstack echo", "go echo framework", asks about "echo middleware", "echo context", "echo binding", "echo websocket", "high performance go api", "echo router" DO NOT USE FOR: Gin projects - use `gin` instead, Fiber projects - use `fiber` instead, Chi projects - use `chi` instead, non-Go backends

Patterns for synchronizing DTOs between frontend and backend. Covers shared types, code generation, and validation sync. USE WHEN: user asks about "DTO sync", "shared types", "frontend backend types", "type consistency", "API models" DO NOT USE FOR: type generation tools - use `type-generation` skill, validation rules - use validation skills

DSPy 2.5+ for programming (not prompting) LMs. Covers Signatures, Modules (Predict, ChainOfThought, ReAct, Retrieve), compilers/optimizers (BootstrapFewShot, MIPROv2, BootstrapFinetune), retrievers, evaluation, and production deployment of compiled programs. USE WHEN: user mentions "DSPy", "dspy.Module", "dspy.Signature", "MIPROv2", "BootstrapFewShot", "ChainOfThought optimization", "program > prompt" DO NOT USE FOR: manual prompt templates - use `langchain`; LlamaIndex query engines - use `llamaindex`; generic RAG architecture - use `rag-patterns`

Drizzle ORM for TypeScript. Covers schema definition, queries, and migrations. Use for type-safe SQL with minimal overhead. USE WHEN: user mentions "drizzle", "drizzle-orm", "drizzle-kit", "pgTable", "mysqlTable", asks about "lightweight orm", "sql-like orm", "drizzle schema", "drizzle migrations", "drizzle studio", "type-safe sql builder" DO NOT USE FOR: Prisma projects - use `prisma` skill; TypeORM - use `typeorm` skill; raw SQL - use `database-query` MCP; SQLAlchemy - use `sqlalchemy` skill; NoSQL databases - use `mongodb` skill

Windows driver signing and certification: EV (Extended Validation) code-signing certificates, Microsoft Hardware Dev Center attestation signing, WHQL/HLK certification, INF Section requirements, dual-signing, kernel driver signing policy (Win10 1607+), test signing, cross-signing legacy notes, and signtool/signability validation. USE WHEN: user mentions "driver signing", "EV cert", "attestation signing", "WHQL", "HLK", "Hardware Dev Center", "Partner Center", "signtool", "test signing", "DSE bypass", "cross-signed driver", "INF compliance", "dual-signed kernel driver" DO NOT USE FOR: Authenticode signing of normal apps, certificate management unrelated to drivers, macOS / Linux signing

Windows driver debugging end-to-end: WinDbg / WinDbg-Preview, KDNET kernel debugging setup over Ethernet/USB, Driver Verifier, Application Verifier (UMDF), bugcheck analysis with !analyze -v, common kernel commands (!process, !thread, !irp, !devstack, !wdfdevice, !wdfkd.wdfdriverinfo), live and post-mortem (kernel dumps), symbol setup, and WPP / ETW trace analysis. USE WHEN: user mentions "WinDbg", "kd", "KDNET", "kernel debugger", "Driver Verifier", "verifier.exe", "Application Verifier", "appverif", "!analyze", "!irp", "bugcheck", "0x9f DRIVER_POWER_STATE_FAILURE", "kernel dump", "MEMORY.DMP", "DebugView", "tracefmt", "tracerpt", "WPP decode" DO NOT USE FOR: Visual Studio managed/.NET debugging, web app debugging

Detecting distributional drift in production embeddings. Metrics (KL, PSI, MMD, cosine-to-centroid), alerting thresholds, query-vs-corpus divergence, root-cause analysis, and embedding observability tooling (Arize, Fiddler). USE WHEN: user mentions "embedding drift", "distribution shift", "PSI", "KL divergence", "MMD", "embedding monitoring", "embedding observability", "model staleness", "production embedding quality" DO NOT USE FOR: evaluation of answer quality - use `rag-evaluation`; retraining embeddings - use `embedding-fine-tuning`; general model drift on tabular features - use an ML monitoring skill

.NET and ASP.NET Core security patterns. Covers Identity, authentication, dependency auditing, secure coding practices, and OWASP for .NET ecosystem. USE WHEN: user works with "C#", ".NET", "ASP.NET Core", "Entity Framework", asks about ".NET vulnerabilities", "NuGet security", ".NET authentication", "Blazor security" DO NOT USE FOR: general OWASP concepts - use `owasp` or `owasp-top-10` instead, Java/Python security - use language-specific skills

.NET code quality with Roslyn analyzers, StyleCop, and dotnet format. Covers linting, formatting, and best practices for C#/.NET. USE WHEN: user works with "C#", ".NET", "ASP.NET Core", asks about "Roslyn analyzers", "StyleCop", "dotnet format", ".NET linting", "C# best practices" DO NOT USE FOR: SonarQube - use `sonarqube` skill, testing - use .NET test skills, security - use `dotnet-security` skill

Production RAG templates for five domains: customer-support, developer-docs, legal, medical, financial. Each covers corpus shape, chunking, embedding model choice, metadata schema, domain-specific guardrails (hallucination tolerance, PII, compliance), and evaluation criteria. USE WHEN: user mentions "RAG for support", "legal RAG", "medical RAG", "developer docs RAG", "financial RAG", "domain template RAG" DO NOT USE FOR: general architecture - use `rag-architecture`; evaluation methodology - use `rag-evaluation`; security specifics - use `rag-security`

Documentation toolchain for multi-language projects: mdBook (Markdown books with Rust ecosystem support — used by Bitcoin Core, Rust Book), rustdoc (Rust API docs auto-gen), Dokka (Kotlin API docs, JVM + KMP + multiplatform sections), Showkase (Compose component browser). Covers single-source-of-truth setup, CI publication to GitHub Pages, cross-linking between API docs and prose books, versioning strategies for releases. USE WHEN: user mentions "mdBook", "Dokka", "rustdoc", "Showkase", "API documentation", "documentation site", "GitHub Pages docs", "docs.rs", "docs publishing", "Kotlin API docs" DO NOT USE FOR: Code-level inline docs syntax (KDoc, rustdoc comments) - that's part of language skills DO NOT USE FOR: README authoring - generic markdown DO NOT USE FOR: Sphinx (Python) - separate Python docs skill DO NOT USE FOR: TypeDoc (TS) - already in `documentation` (typedoc-specific)

Docker Compose for multi-container apps. Covers services, networks, and volumes. Use for local development environments. USE WHEN: user mentions "docker-compose", "docker-compose.yml", "multi-container", "service dependencies", "docker compose up", asks about "local dev environment", "microservices setup", "database + app setup", "docker networks", "docker volumes" DO NOT USE FOR: single container Dockerfiles - use `docker` skill instead, production orchestration - use `kubernetes` skill instead, CI/CD pipelines - use `github-actions` skill instead

Docker containerization. Covers Dockerfile, images, and best practices. Use for containerizing applications. USE WHEN: user mentions "dockerfile", "docker build", "docker run", "containerize", "docker image", "multi-stage build", asks about "how to dockerize", "container security", "docker optimization", "image size", "docker layers" DO NOT USE FOR: docker-compose multi-service setups - use `docker-compose` skill instead, Kubernetes orchestration - use `kubernetes` skill instead

DNS concepts, record types, and management skill: Cloudflare, Route 53, DNSSEC, debugging with dig/nslookup, TTL strategy, and split-horizon DNS. USE WHEN: - Adding or modifying DNS records for a web application, mail system, or API - Configuring Cloudflare proxy (orange cloud) or DNS-only mode - Setting up Route 53 hosted zones, health checks, and routing policies - Debugging DNS propagation, CNAME loops, MX failures, or SPF/DKIM issues - Planning a migration with minimal downtime (TTL strategy) - Configuring DNSSEC, CAA records, or reverse DNS (PTR) - Setting up split-horizon DNS for internal vs external resolution DO NOT USE FOR: - SSL/TLS certificate issuance (use ssl-tls skill) - Nginx or application-level routing (use nginx or api-gateway skill) - Service mesh internal DNS (use kubernetes or service-mesh skill) - Email server configuration beyond DNS records (use a dedicated email skill)

Django batteries-included Python framework. Covers models, views, templates, ORM, and admin. Use when building full-featured Python web applications. USE WHEN: user mentions "django", "django orm", "django admin", "django templates", asks about "python cms", "django rest framework", "drf", "django models", "django migrations", "django channels", "django forms" DO NOT USE FOR: FastAPI projects - use `fastapi` instead, Flask projects - use `flask` instead, async-first Python APIs, microservices without admin panel

Distributed-ledger / blockchain architecture in general (engine-agnostic): when a ledger beats a database, consensus families (PoW/PoS/BFT), L1 vs L2 (rollups, channels, sidechains), permissioned vs permissionless, UTXO vs account models, and the scalability trilemma. Architect-level, not coin-specific. USE WHEN: designing/evaluating a blockchain or DLT system in general, "L2", "rollup", "zk vs optimistic", "PoS vs PoW", "permissioned ledger", "consortium chain", "UTXO vs account", "do we even need a blockchain", token/state design. DO NOT USE FOR: Bitcoin-specific work (use the `bitcoin/*` skills); raw consensus internals (use `distributed-consensus`); ordinary app data (use database / data-intensive skills).

Distributed-systems architecture at the protocol level: consensus (Raft, Paxos, BFT), replication and quorums, consistency models, clock synchronization, and the CAP/PACELC trade-offs. Architect-level — how to make state agree and survive failures. USE WHEN: designing replicated/consensus systems, "Raft", "Paxos", "BFT", "quorum", "leader election", "consistency model", "linearizability", "CAP", "PACELC", "split-brain", replication topology, distributed state machines. DO NOT USE FOR: app microservice wiring (use web/enterprise patterns); message queues (use messaging skills); blockchain specifics (use bitcoin skills).

Design system architecture and design tokens. Covers W3C Design Token spec, atomic design methodology, component documentation, theming, dark/light mode, and modern CSS custom property patterns. USE WHEN: user mentions "design system", "design tokens", "component library", "theming", "dark mode", "light mode", "CSS variables", "atomic design", "color palette", "token architecture", "shadcn theming", "brand tokens" DO NOT USE FOR: specific component APIs (use styling/shadcn-ui or styling/radix-ui), animation timing (use ux/interaction-design), WCAG audit (use accessibility/wcag)

Production deployment strategies. Blue-green, canary, rolling update, recreate. Zero-downtime deployments, rollback procedures, database migration coordination, and deployment automation. USE WHEN: user mentions "blue-green", "canary deployment", "rolling update", "zero-downtime", "deployment strategy", "rollback", "deploy pipeline" DO NOT USE FOR: CI/CD pipeline syntax - use `github-actions`; container orchestration - use `kubernetes`; IaC - use `terraform`

Deno testing with Deno.test and std/testing. Covers unit tests, async tests, mocking, snapshots, and BDD-style testing. USE WHEN: user mentions "deno test", "deno testing", asks about "Deno.test", "assertSnapshot", "FakeTime", "spy", "stub", "BDD deno" DO NOT USE FOR: Node.js projects - use `vitest` or `jest`; Browser-only code - use Playwright; Python - use `pytest`; Java - use `junit`; Non-Deno TypeScript - use `vitest`

Deno runtime for TypeScript/JavaScript. Covers permissions, standard library, testing, and Deploy. Use for secure, TypeScript-native backend development. USE WHEN: user mentions "deno", "permissions", "Deno.serve", asks about "deno test", "deno deploy", "standard library", "top-level await", "npm compatibility" DO NOT USE FOR: Node.js runtime - use `nodejs` skill instead DO NOT USE FOR: Fresh/Oak frameworks - use framework-specific skills DO NOT USE FOR: Language syntax - use `typescript` skill

Domain-Driven Design patterns. Bounded contexts, aggregates, entities, value objects, domain events, repositories, and application services. Strategic and tactical DDD for complex business domains. USE WHEN: user mentions "DDD", "Domain-Driven Design", "bounded context", "aggregate", "value object", "domain event", "ubiquitous language", "aggregate root", "domain service" DO NOT USE FOR: database schema design - use database skills; CQRS/Event Sourcing specifics - use `event-sourcing-cqrs`

Reference for major DCS/PLC platforms - ABB Freelance, Siemens PCS7/TIA Portal, Emerson DeltaV, Honeywell Experion. Use when comparing platforms, mapping function blocks across vendors, or designing cross-platform solutions.

Data-intensive / data-platform architecture: warehouse vs lakehouse, OLTP vs OLAP, batch vs streaming (lambda/kappa), change-data-capture, and data mesh. Architect-level platform-shape decisions, not SQL or ETL code. USE WHEN: designing a data platform/pipeline architecture, "data warehouse", "lakehouse", "OLAP vs OLTP", "lambda/kappa", "streaming vs batch", "CDC", "data mesh", "medallion", analytics platform, columnar store, ingestion topology. DO NOT USE FOR: writing SQL/ORM (use database skills); a specific ETL tool (use data/data-processing skills); storage-engine internals (use `storage-engines`).

Data export to CSV, Excel (XLSX), and JSON. ExcelJS, SheetJS (xlsx), Papa Parse, Apache POI (Java), openpyxl (Python). Streaming exports for large datasets. USE WHEN: user mentions "export CSV", "export Excel", "XLSX generation", "download spreadsheet", "ExcelJS", "SheetJS", "Papa Parse", "data export" DO NOT USE FOR: PDF generation - use `pdf-generation`; file upload/download - use `file-upload`/`cloud-storage`

Cypress E2E testing framework. Covers commands, assertions, and component testing. Use for end-to-end testing. USE WHEN: user mentions "cypress", "e2e test", "cy.get", "cy.visit", asks about "cypress intercept", "component testing", "cypress commands" DO NOT USE FOR: Unit tests - use `vitest` or `jest`; Multi-tab scenarios - Cypress doesn't support; Native mobile apps - use Appium; Performance testing - use dedicated tools

Cyber-physical / industrial control system (ICS-SCADA) architecture in general: the Purdue model levels, control loops, IT/OT convergence, OT security (IEC 62443, segmentation, zero-trust for OT), safety, determinism, and redundancy. Architect-level, beyond any specific DCS/PLC product. USE WHEN: designing/evaluating industrial control, SCADA, robotics, energy, automotive, or IoT-at-scale systems, "OT security", "Purdue model", "PLC/RTU/ SCADA architecture", "IT/OT convergence", "IEC 62443", "control loop", safety instrumented systems. DO NOT USE FOR: specific DCS platforms / IEC 61131 / ISA formats (use the `industrial/*` skills); pure RTOS scheduling (use `embedded-rtos`); app security (use `security-architecture`).

Reviewing C# code - what to flag, and what Roslyn analyzers and nullable reference types already flag for you USE WHEN: you are reviewing, critiquing or auditing existing C# code - a "code review", a "review" of a .cs file, a diff, a PR or a pull request; deciding what to comment on in C#; avoiding false positives on C# code DO NOT USE FOR: writing, explaining or learning C# - use `languages/csharp`; anything the built-in Roslyn analyzers or nullable reference types already report (this skill lists those so you can stay silent about them); ASP.NET Core specifics - use the ASP.NET skills; EF Core mapping - use the ORM skills

C# 12 language features including records, pattern matching, nullable reference types, LINQ, async/await, and modern language patterns. USE WHEN: user mentions "C#", "C# records", "pattern matching", "LINQ", "async/await", "nullable reference types", "C# generics", "C# language features" DO NOT USE FOR: reviewing existing C# code - use `review/csharp`, which covers async, disposal and the guarantees that are opt-in per project DO NOT USE FOR: TypeScript - use `typescript`, Java - use Java skills, F# or VB.NET specific features

Application-level cryptography. Password hashing (bcrypt, argon2), encryption (AES-GCM), digital signatures, key management, and secure random generation. USE WHEN: user mentions "encryption", "hashing", "bcrypt", "argon2", "AES", "cryptography", "digital signature", "key management", "HMAC" DO NOT USE FOR: TLS/HTTPS configuration - use infrastructure skills; JWT tokens - use `jwt`; OAuth flows - use `oauth2`

Fine-tuning cross-encoders for domain-specific reranking. Training data (query-doc relevance labels, MS MARCO format), sentence-transformers CrossEncoder API, loss functions (BCE, margin), hard negative mining from BM25 and dense retrievers, distillation from strong teacher rerankers (BGE-reranker-v2, Cohere) into small models, NDCG@10 evaluation. USE WHEN: user mentions "fine-tune cross-encoder", "train reranker", "hard negative mining", "MS MARCO triples", "knowledge distillation reranker", "CrossEncoder", "cross-encoder training" DO NOT USE FOR: zero-shot reranking with existing APIs - use `rag/reranking`; LLM reranker - use `retrieval/rank-gpt`; ColBERT training - use `retrieval/colbert-retrieval`; SPLADE training - use `retrieval/splade-deep`

Cron and scheduled task management. node-cron, cron expressions, Spring @Scheduled, APScheduler (Python), and distributed scheduling patterns. USE WHEN: user mentions "cron", "scheduled task", "cron job", "node-cron", "@Scheduled", "APScheduler", "periodic task", "crontab" DO NOT USE FOR: job queues with workers - use `job-queues`; one-off delayed tasks - use `job-queues`

C++ memory and concurrency safety: AddressSanitizer (ASan), UndefinedBehaviorSanitizer (UBSan), ThreadSanitizer (TSan), MemorySanitizer (MSan), MSVC `/sdl` and `/guard:cf`, CERT C++ secure coding rules, integer-overflow safe arithmetic, and Control Flow Integrity. USE WHEN: user mentions "ASan", "AddressSanitizer", "UBSan", "TSan", "MSan", "use-after-free", "buffer overflow", "undefined behavior", "data race", "CERT C++", "secure C++", "/sdl", "/GS", "ASLR", "DEP", "stack canary" DO NOT USE FOR: Web/app security (use `owasp`), .NET security (`dotnet-security`), cryptography APIs (use `cryptography`)

Reviewing C++ code - what to flag, and what the compiler, clang-tidy and sanitizers already flag for you USE WHEN: you are reviewing, critiquing or auditing existing C++ code - a "code review", a "review" of a .cpp/.hpp/.cc/.h file, a diff, a PR or a pull request; deciding what to comment on in C++; avoiding false positives on C++ DO NOT USE FOR: writing, explaining or learning C++ - use `languages/cpp`; anything `-Wall -Wextra`, clang-tidy or a sanitizer run already reports (this skill lists those so you can stay silent about them); build system questions - use the CMake material; embedded specifics - use `systems/embedded-rtos`

C++ static analysis and formatting tooling: clang-tidy, clang-format, cppcheck, include-what-you-use (IWYU), and CI integration patterns. USE WHEN: user mentions "clang-tidy", "clang-format", "cppcheck", "iwyu", "include-what-you-use", ".clang-tidy", ".clang-format", "C++ static analysis", "C++ linter" DO NOT USE FOR: SonarQube C++ rules (tool-agnostic), Coverity (commercial), PVS-Studio (commercial)

Modern C++ (C++17/20/23) language and standard library. Covers RAII, move semantics, smart pointers, templates, concepts, ranges, coroutines, modules, std::expected, std::format, std::span, std::string_view. USE WHEN: user mentions "C++", "modern C++", "C++17/20/23", "RAII", "smart pointers", "templates", "concepts", "ranges", "move semantics", "std::expected", "std::span", "coroutines", "modules", "STL" DO NOT USE FOR: reviewing existing C++ code - use `review/cpp`, which covers the lifetime and ownership claims the compiler does not check DO NOT USE FOR: C (use a C-specific skill), C# (use `csharp`), Objective-C++, Carbon, kernel/no-exception subset (use `cpp-systems`)

Per-tenant, per-feature, per-query RAG cost tracking. Covers token counting (tiktoken, Anthropic count_tokens), structured metadata logging, aggregation in BigQuery/Snowflake/ClickHouse, dashboards (Grafana, Metabase), LangSmith and Langfuse native cost reports, and budget alerts. Schema + example queries. USE WHEN: user mentions "RAG cost", "cost per tenant", "cost per query", "token counting", "chargeback", "showback", "LangSmith cost", "Langfuse cost", "budget alerts" DO NOT USE FOR: reducing cost - use `rag-production`; batch-discount strategy - use `batch-inference`; routing for cheaper models - use `llm-gateway`

CORS configuration and HTTP security headers. CORS middleware, preflight requests, Content-Security-Policy, CSRF protection, Helmet.js, and secure cookie configuration. USE WHEN: user mentions "CORS", "cross-origin", "CSP", "Content-Security-Policy", "CSRF", "security headers", "Helmet", "preflight", "Access-Control" DO NOT USE FOR: authentication tokens - use `jwt` or `oauth2`; encryption - use `cryptography`

Multi-turn RAG: chat history management, context window compaction (summarization, sliding window, vector memory), query rewriting with coreference resolution, follow-up vs new-query routing, LangChain ConversationalRetrievalChain, LlamaIndex ChatEngine, Redis/Postgres message history stores. USE WHEN: user mentions "conversational RAG", "multi-turn RAG", "chat history", "follow-up question", "chat memory", "ChatEngine", "ConversationalRetrievalChain", "coreference in RAG" DO NOT USE FOR: single-turn pipelines - use `rag-architecture`; query rewriting in isolation - use `query-transformations`; user-level long-term memory - use `personalization-rag`

Contract testing for API consumers and providers. Pact framework, Spring Cloud Contract, consumer-driven contracts, provider verification, and contract broker setup. USE WHEN: user mentions "contract testing", "Pact", "consumer-driven contract", "Spring Cloud Contract", "API contract", "provider verification" DO NOT USE FOR: OpenAPI validation - use `openapi-contract`; integration testing - use integration test skills

CI/CD for RAG quality: golden dataset fixtures, RAGAS/DeepEval in pytest, regression thresholds, GitHub Actions workflows, merge-blocking gates, weekly scheduled eval, LangSmith/Langfuse in CI. USE WHEN: user mentions "RAG CI", "eval in CI", "regression gate", "golden dataset fixture", "PR quality check", "scheduled RAG evaluation", "LangSmith CI", "Langfuse CI" DO NOT USE FOR: RAGAS metric internals - use `rag-evaluation`; ARES - use `ares-framework`; Giskard internals - use `giskard-rag`; shadow deploys - use `shadow-mode-deployment`

Anthropic's Contextual Retrieval technique in depth. Prepend LLM-generated chunk-specific context (Claude Haiku) to each chunk before indexing. Combines contextual BM25 + contextual embeddings + reranking for up to 67% retrieval failure reduction. Full production pipeline with prompt caching (90% cost cut), batch processing, and eval numbers. USE WHEN: user mentions "contextual retrieval", "contextual embeddings", "Anthropic contextual retrieval", "chunk context", "contextual BM25", "49% retrieval improvement" DO NOT USE FOR: generic chunking - use `chunking-strategies`; hybrid search fundamentals - use `hybrid-search`; reranking on its own - use `reranking`

Container and Kubernetes security: hardening images, runtime configuration and deployment manifests. USE WHEN: securing Docker containers, Kubernetes deployments, or reviewing container configurations DO NOT USE FOR: general Docker usage (use the `docker` skill), Kubernetes architecture (use the `kubernetes` skill)

Compose snapshot testing — pixel-by-pixel verification of @Composable output. Covers Paparazzi (JVM, fast, no emulator) and Roborazzi (Robolectric-based, emulator-free or device). Catches regressions in design system, theming, dark mode, font scaling, and locale rendering. CI integration with image diff reporting. USE WHEN: user mentions "Paparazzi", "Roborazzi", "Compose snapshot", "screenshot test", "visual regression", "pixel comparison", "showkase paparazzi", "compose preview test" DO NOT USE FOR: Mobile E2E - use `testing/maestro` DO NOT USE FOR: SwiftUI snapshots - use swift-snapshot-testing (separate) DO NOT USE FOR: Compose Multiplatform iOS snapshots - immature; use Paparazzi for shared composables on JVM DO NOT USE FOR: Logic tests - use `testing/kotest` or `testing/turbine`

Compose Multiplatform (CMP) by JetBrains — declarative UI framework that runs on Android, iOS, JVM Desktop, and Web (Wasm). Built on top of Jetpack Compose. Covers @Composable functions, state hoisting, side effects, navigation (Voyager, Decompose), Material 3, theming, and platform-specific UI bridging on iOS. USE WHEN: user mentions "Compose Multiplatform", "@Composable", "remember", "MutableState", "Compose iOS", "Compose Desktop", "Compose Wasm", "JetBrains Compose", "Voyager", "Decompose", "compose-multiplatform-resources" DO NOT USE FOR: KMP module setup (gradle, expect/actual) - use `mobile/kotlin-multiplatform` DO NOT USE FOR: Jetpack Compose Android-only - use `mobile/jetpack-compose` DO NOT USE FOR: SwiftUI native - use `mobile/ios-native` or `languages/swift` DO NOT USE FOR: Pure Kotlin language - use `languages/kotlin`

ColBERT / ColBERTv2 late interaction as a first-stage retriever — not just a reranker. MaxSim scoring, PLAID index, Ragatouille for deployment, storage cost of token-level embeddings, when to pick ColBERT over dense-plus-rerank, and fine-tuning for domain. USE WHEN: user mentions "ColBERT", "ColBERTv2", "late interaction", "MaxSim", "PLAID", "Ragatouille", "token-level embeddings", "multi-vector retrieval" DO NOT USE FOR: single-vector dense retrieval - use `vector-stores/qdrant-advanced` or similar; cross-encoder reranking - use `rag/reranking`; SPLADE sparse - use `retrieval/splade-deep`; cross-encoder fine-tuning - use `retrieval/cross-encoder-training`

Refining AUTO-GENERATED code produced by deterministic generators (openapi-generator, asyncapi-generator, tsp compile, protoc, bpmn-engine) so it matches the target project's conventions without changing the API contract or structural design. USE WHEN: adapting generated clients, models or stubs to project style, reviewing generator output before committing it, user mentions "openapi-generator", "protoc", "generated code cleanup" DO NOT USE FOR: writing new code from scratch, changing an API contract or schema, configuring the generator itself

AST-aware chunking for source code RAG. Covers tree-sitter, LangChain Language splitter, LlamaIndex CodeSplitter, preserving function/class boundaries, keeping docstrings with implementations, and code-specific embeddings (voyage-code-2, CodeBERT). USE WHEN: user mentions "code chunking", "tree-sitter", "code splitter", "AST chunking", "code embedding", "voyage-code-2", "code RAG", "repo Q&A" DO NOT USE FOR: plain prose chunking - use `rag-patterns`; PDF extraction - use `pdf-extraction`

CMake build system for C/C++ projects. Modern CMake (3.20+) with targets, properties, presets (CMakePresets.json), FetchContent, find_package, generator expressions, install rules, vcpkg/Conan integration. USE WHEN: user mentions "CMake", "CMakeLists.txt", "CMakePresets", "find_package", "FetchContent", "target_link_libraries", "vcpkg", "Conan", "C++ build" DO NOT USE FOR: Make, autotools, Bazel, Meson, Visual Studio .vcxproj direct editing

Cloud object storage integration with AWS S3, Azure Blob Storage, and Google Cloud Storage. Covers presigned URLs, multipart uploads, bucket policies, lifecycle rules, and CDN integration. USE WHEN: user mentions "S3", "blob storage", "cloud storage", "object storage", "presigned URL", "file upload to cloud", "GCS", "Azure Blob", "bucket" DO NOT USE FOR: local file uploads - use `file-upload`; database BLOB columns; local filesystem operations

Clean code principles. Covers naming, functions, and readability. Use when writing or reviewing code for quality. USE WHEN: user mentions "code quality", "readability", "refactor", "clean up code", "naming", "magic numbers", asks about "how to write better code", "code smells", "DRY", "KISS", "YAGNI", "single responsibility" DO NOT USE FOR: SOLID principles - use `solid-principles` instead, Git workflow - use `git-workflow` instead, Performance optimization - use `performance` instead

Class-validator decorator-based validation for TypeScript. Standard in NestJS. Use when building APIs with NestJS or needing class-based validation. USE WHEN: user mentions "class-validator", "NestJS validation", "DTO validation", "decorator validation", asks about "NestJS DTOs", "ValidationPipe" DO NOT USE FOR: Zod/Yup projects (use zod/yup skills), non-decorator patterns, client-side forms (prefer Zod), non-NestJS backends

Document chunking techniques for RAG. Fixed-size, recursive, semantic, token-based, document-aware, proposition, parent-child, sliding window, and Anthropic contextual retrieval. Tradeoff tables, LangChain and LlamaIndex code. USE WHEN: user mentions "chunking", "text splitter", "split documents", "semantic chunking", "contextual retrieval", "parent-child chunks", "proposition chunking" DO NOT USE FOR: retrieval after chunking - use `advanced-retrieval`; query-side transforms - use `query-transformations`; overall design - use `rag-architecture`

ChromaDB 0.5+ advanced features. Persistent vs ephemeral clients, collection-level HNSW tuning (space, construction_ef, M), multi-tenancy via collections, metadata filtering, embedding function plugins (OpenAI, Cohere, Voyage, custom), Chroma Cloud, recall tuning, migration patterns to production stores. USE WHEN: user mentions "Chroma", "ChromaDB", "chromadb-client", "Chroma Cloud", "Chroma collection", "chroma embedding function" DO NOT USE FOR: production-scale vector stores - use `vector-stores/qdrant-advanced`, `vector-stores/milvus`, or `vector-stores/pinecone-advanced`; hybrid search theory - use `rag/hybrid-search`

Chi lightweight Go HTTP router. Covers routing, middleware, context, and patterns. Use for idiomatic, stdlib-compatible Go APIs. USE WHEN: user mentions "chi", "go-chi", "lightweight go router", "stdlib go router", asks about "chi middleware", "chi router", "chi context", "idiomatic go api", "net/http compatible router", "chi patterns" DO NOT USE FOR: Gin projects - use `gin` instead, Echo projects - use `echo` instead, Fiber projects - use `fiber` instead, non-Go backends

Chart and data visualization libraries. Recharts, Chart.js, D3.js, Victory, Nivo, ECharts. Common chart types, responsive design, and real-time updates. USE WHEN: user mentions "chart", "graph", "data visualization", "Recharts", "Chart.js", "D3", "ECharts", "Victory", "bar chart", "line chart", "dashboard" DO NOT USE FOR: PDF report generation - use `pdf-generation`; data export - use `data-export`

Real-time RAG ingestion. CDC (Debezium, Postgres logical replication), Kafka/ Pulsar topics for doc events, stream processing (Flink, Kafka Streams) to embedding service, exactly-once semantics, late-arriving updates, tombstones (deletes), upsert to vector DB, schema evolution. Full Debezium + Kafka -> vector DB example. USE WHEN: user mentions "CDC RAG", "Debezium RAG", "Kafka RAG", "real-time embeddings", "streaming ingestion", "Flink embeddings", "Pulsar RAG", "logical replication RAG" DO NOT USE FOR: batch scheduled ingestion - use `ingestion-orchestration`; query-time freshness weighting - use `time-aware-retrieval`; evaluation - use `rag-evaluation`

Browser graphics via the Canvas 2D API, WebGL and creative-coding libraries. Covers React canvas setup, the 2D API, particle systems, pixel manipulation, OffscreenCanvas in a worker, raw WebGL, p5.js and noise functions. USE WHEN: user mentions "canvas", "getContext('2d')", "WebGL", "p5.js", "particle system", "pixel manipulation", "OffscreenCanvas", asks about drawing or generative graphics in the browser DO NOT USE FOR: 3D scene graphs (use `three-js`), vector graphics and SVG (use `svg-animation`), DOM animation (use `framer-motion` or `gsap`)

Pinecone's Canopy framework — a pre-packaged RAG stack on top of Pinecone. Covers Canopy CLI, REST server (OpenAI-compatible), chunking, embedding, retrieval, chat-history management, and customization hooks (custom chunkers/records). USE WHEN: user mentions "Canopy", "Pinecone Canopy", "canopy start", "canopy new", "Pinecone out-of-the-box RAG" DO NOT USE FOR: custom pipelines on non-Pinecone stores - use `rag-architecture`; Postgres-based stacks - use `r2r`; LangChain/LlamaIndex abstractions - use `langgraph-rag`/`llamaindex`

Caddy v2 reverse proxy with automatic HTTPS. Covers Caddyfile syntax, directives, TLS configuration, DNS challenges, and API-based management. USE WHEN: user mentions "caddy", "caddyfile", "caddy server", "xcaddy", "caddy reverse proxy", asks about "automatic https", "let's encrypt caddy", "caddy tls", "caddy load balancing", "caddy websocket proxy", "caddy dns challenge", "caddy cloudflare", "caddy api", "caddy systemd" DO NOT USE FOR: Nginx-based setups - use `load-balancer` or a dedicated nginx skill, Traefik-based setups - use `traefik` skill, Kubernetes ingress controllers - use `kubernetes` skill, Application-level TLS termination inside app code

Application caching patterns. Redis caching, in-memory caches, HTTP caching, cache invalidation strategies, cache-aside, write-through, and CDN caching. USE WHEN: user mentions "caching", "cache invalidation", "Redis cache", "HTTP cache", "CDN caching", "cache-aside", "write-through", "TTL", "stale-while-revalidate" DO NOT USE FOR: Redis as database/queue - use `redis` or `job-queues`; browser storage - use frontend skills

Bun JavaScript runtime. Fast all-in-one toolkit with bundler, test runner, package manager. Use when working with Bun projects or considering Node.js alternatives. USE WHEN: user mentions "bun", "bun test", "bun build", asks about "Bun.serve", "bun install", "SQLite in Bun", "bunx", "performance comparison" DO NOT USE FOR: Node.js runtime - use `nodejs` skill instead DO NOT USE FOR: Hono/Elysia frameworks - use framework-specific skills DO NOT USE FOR: Language syntax - use `typescript` or `javascript` skills

Bulk engineering approaches, tools, and implementation strategies for mass-generating PLC/DCS control logic, HMI displays, and I/O configurations from engineering databases. Use when planning or implementing automation of DCS engineering workflows.

BM25 deep tuning. k1 and b parameters with defaults per collection, field boosts, stopwords, language-specific analyzers (Italian, French, German, non-English), stemming vs lemmatization, tokenization gotchas, Elasticsearch vs Lucene vs rank_bm25. When BM25 alone beats vectors. USE WHEN: user mentions "BM25", "BM25 tuning", "k1 b parameter", "Elasticsearch analyzer", "stemming", "lemmatization", "rank_bm25", "TF-IDF", "lexical search" DO NOT USE FOR: learned sparse - use `retrieval/splade-deep`; hybrid fusion - use `rag/hybrid-search`; dense retrieval - use `vector-stores/*`

HD wallet implementation: BIP32 derivation, BIP39 mnemonic seed (with passphrase), BIP44/49/84/86 derivation paths, account structure, gap limit, watch-only via xpub, BIP352 silent payment scan/spend derivation and BIP392 sp() descriptors. USE WHEN: building/restoring an HD wallet, choosing derivation paths, debugging address generation, importing mnemonics.

BIP329 wallet labels portability: standard JSON Lines format for exporting/importing labels (addresses, txs, UTXOs, xpubs, inputs, outputs) across wallet software. USE WHEN: importing/exporting label sets, integrating with multiple wallets that should share annotations.

BIP85 deterministic entropy: derive child entropy/seeds from a parent BIP32 path. Used for sub-wallets, cross-app keys, deterministic randomness without separate backups. USE WHEN: spawning sub-wallets from one master seed, generating encryption keys deterministically, building a "memory" of one seed.

Wallet backup formats: BIP39 mnemonic, SLIP-39 Shamir Backup, SeedQR, CompactSeedQR, Coldcard's CTL-format, paper backup hygiene, metal backup vendors and threat models. USE WHEN: designing backup UX, evaluating backup security, helping recover a backed-up seed.

Bitcoin vault patterns: timelocked cooldown, hot/cold path with CSV, multisig vaults with quorum reduction over time, OP_VAULT proposal (BIP345), Revault architecture. USE WHEN: designing high-value custody, treasury setups, recovery schemes with publish-and-cooldown semantics.

Bitcoin payment URI scheme (BIP21), Lightning URIs, BIP70/72 (mostly deprecated), PayJoin URI extension (BIP78), unified URIs combining on-chain + Lightning. USE WHEN: parsing/generating bitcoin: URIs, building QR codes, designing wallet payment requests.

Bitcoin transaction structure: inputs, outputs, witness, version, locktime, serialization (legacy + segwit + wtxid), sighash modes, malleability, TRUC v3, ephemeral anchors. Quick-ref docs cover sighash combinatorics, serialization wire format, malleability classes, RBF/CPFP rules. USE WHEN: building/decoding transactions, choosing sighash flags, understanding txid vs wtxid, fee bumping logic.

Bitcoin time-locks: nLockTime (BIP65 absolute), nSequence (BIP68/112 relative), CLTV/CSV opcodes, MTP rule (BIP113). Block-height vs unix-time, encoding rules. USE WHEN: building HTLCs, vaults, scheduled payments, escrow with cooldown, refund paths.

Public mined test networks: testnet3 (deprecated), testnet4 (BIP94) and the testnet5 draft (BIP95). Chain selection, the 20-minute difficulty exception, block storms, and when to prefer signet. USE WHEN: picking a public test network, debugging testnet4 block behaviour, or tracking the testnet5 migration.

Signet: signature-based testnet alternatives. Default signet, custom signets (signetchallenge), Mutinynet (30-sec blocks). Faster + more deterministic than testnet. USE WHEN: testing on a public-style network, avoiding mainnet fees but with realistic block timing.

Regtest mode: instant block generation, deterministic fork, multi-node setup, generatetoaddress, fallbackfee config. USE WHEN: building Bitcoin tests, simulating network conditions, scaffolding integration tests.

Property-based testing: proptest / quickcheck (Rust), hypothesis (Python). Strategies for tx serialization, descriptor round-trip, miniscript satisfaction. USE WHEN: testing Bitcoin parsers, ensuring round-trip invariants, catching edge cases beyond example tests.

Polar: GUI for spinning up Lightning regtest networks. Supports LND, Core Lightning, Eclair, plus Lightning Terminal (litd) and Taproot Assets. Per-node config, payment simulation, channel topology editor, sim-ln activity, MCP server for AI agents. USE WHEN: building / testing Lightning apps, designing regtest channel topologies, demoing LN flows.

Nigiri: regtest stack with Bitcoin + Esplora + electrs + Liquid + optional LN. CLI-based, fast iteration, includes faucet. USE WHEN: regtest with explorer dependency, full-stack E2E testing, dev environment with Esplora API.

Fuzz testing for Bitcoin code: Bitcoin Core's libFuzzer harnesses, rust-bitcoin / bdk / secp256k1 cargo-fuzz, AFL++. Seed corpus bootstrapping, regression tests. USE WHEN: hardening Bitcoin libraries, writing fuzz harnesses, reproducing fuzz-found crashes.

Bitcoin Core's Python functional test framework: BitcoinTestFramework, TestNode, setup_network, sync_blocks, descriptors helpers, miniscript helpers. USE WHEN: writing tests against bitcoind, contributing to Bitcoin Core, testing custom mempool policies.

Taproot soft fork: BIP340 (Schnorr signatures), BIP341 (key tweak + script-path), BIP342 (Tapscript). x-only pubkeys, key-path vs script-path spending, control block, leaf versions, taptweak math. Quick refs: tweak math, control block layout, sighash differences, building a taptree. USE WHEN: building/spending P2TR outputs, designing taptrees, reasoning about Schnorr-only contexts.

Segregated Witness: BIP141 (consensus), BIP143 (sighash), BIP144 (P2P serialization), BIP173 (Bech32 address). Witness segregation, weight units, txid vs wtxid, witness commitment. USE WHEN: working with native segwit (P2WPKH/P2WSH), embedded segwit (P2SH-P2WPKH/P2SH-P2WSH), or understanding the witness discount.

secp256k1 elliptic curve: parameters, group law, key encoding, point serialization, library bindings (libsecp256k1 in C, Rust, Python). USE WHEN: low-level key/point operations, debugging signature failures, understanding why Bitcoin uses this curve specifically.

Bitcoin Script language: stack execution model, opcodes, all output types (P2PK, P2PKH, P2SH, P2WPKH, P2WSH, P2TR, P2A, Tapscript), witness construction, sig encoding (DER/Schnorr). Quick refs: opcode reference, output-type construction, Tapscript diff vs legacy. USE WHEN: writing/decoding scriptPubKey, building scriptSig/witness, understanding "what does this script do", reading raw txs.

BIP340 Schnorr signatures over secp256k1: sign/verify, x-only pubkeys, tagged hashes, batch verification, key tweaking. Building block for Taproot, MuSig2, FROST, adaptor signatures, DLCs. Quick refs: signing pseudocode, batch verification, common mistakes. USE WHEN: signing/verifying Taproot key-path or Tapscript spends, designing aggregation protocols, reading BIP340.

Replace-by-Fee (BIP125, full-RBF) and Child-Pays-For-Parent fee bumping. Cluster mempool policy (Core 31.0+), package CPFP via submitpackage, TRUC v3 (BIP431). Wallet-level fee bump strategies. USE WHEN: implementing fee bumping, debugging "stuck transaction", designing wallet UX for fee acceleration.

Partially Signed Bitcoin Transaction format: BIP174 (v0), BIP370 (v2), BIP371 (Taproot fields). Roles (Creator, Updater, Signer, Combiner, Finalizer, Extractor), required fields per input/output type, Taproot-specific fields (tap_key_sig, tap_script_sig, tap_leaf_script, tap_bip32_derivation), magic bytes, separators. USE WHEN: building/signing/coordinating PSBTs, debugging "why won't my hardware wallet sign", cross-vendor multisig flows.

Soft-fork proposals NOT activated on mainnet: consensus cleanup (BIP54), CTV (BIP119), the BIP448 rebindable-transaction bundle (BIP446/348/349), APO/APOAS (BIP118), OP_CHECKCONTRACTVERIFY (BIP443), OP_CAT (BIP347), the 2026 script/covenant BIP cluster (BIP440-443, 446, 448, 449), post-quantum proposals (BIP360/361), drivechains (BIP300/301), spacechains, CISA. Status, mechanics, controversy per proposal. USE WHEN: discussing covenants, evaluating L2 design that depends on unactivated opcodes, understanding the soft-fork pipeline.

Bitcoin over Tor: Tor v3 hidden services, onion-only nodes, bitcoind torcontrol integration, Lightning over Tor. USE WHEN: hardening node privacy, configuring onion-only setups, debugging Tor + bitcoind interaction.

Stealth addresses: ECDH-based derivation generating a unique output per payment. Pre-BIP47 / BIP352, conceptually similar. USE WHEN: understanding the family of stealth-address schemes, comparing with BIP47 / Silent Payments.

Silent Payments (BIP352): single static address from which sender derives unique output per payment. Schnorr-based blinding; no notification tx needed. USE WHEN: implementing BIP352 client/wallet, evaluating vs BIP47, understanding scan cost trade-offs.

PayJoin (BIP78 + v2): receiver-augmented payment that breaks common-input-ownership heuristic. v2 adds async relay support. USE WHEN: implementing PayJoin sender/receiver, designing privacy- preserving payment flows, integrating with payjoin servers.

P2P KYC-free Bitcoin exchanges: Bisq (desktop, Tor), RoboSats (Tor / browser, Lightning), Hodl Hodl (web, multisig escrow). USE WHEN: evaluating KYC-free buy/sell options, integrating P2P trading.

Dandelion++ (BIP156): tx broadcast privacy. Stem phase (forward to one peer) → fluff phase (gossip to all). Hides origin IP. USE WHEN: evaluating tx-broadcast privacy, implementing Dandelion- aware relay logic.

CoinJoin: collaborative tx where multiple users combine inputs to break common-input-ownership heuristic. Wabisabi (Wasabi 2.0), Whirlpool (Samourai), JoinMarket maker/taker. USE WHEN: implementing CoinJoin coordinator/client, evaluating privacy gain, designing post-CoinJoin hygiene.

BIP47 PayNyms — reusable payment codes via notification tx + Diffie-Hellman derivation. See also the wallet-side reference at ../../wallets/payment-codes/. USE WHEN: integrating PayNyms, evaluating against Silent Payments.

Cross-chain atomic swaps: BTC ↔ LTC / BTC ↔ Liquid / BTC ↔ Monero via HTLC or adaptor signature schemes. Trustless swaps without centralized exchange. USE WHEN: building atomic swap services, evaluating cross-chain bridges, integrating with COMIT / submarine-swap variants.

BIP47 reusable payment codes (PayNyms): notification transactions, derived per-counterparty addresses, Diffie-Hellman shared-secret derivation. Privacy-preserving alternative to address rotation. USE WHEN: implementing PayNyms / Sparrow / Samourai-compatible payment codes, evaluating BIP47 vs Silent Payments.

Package relay and the mempool policy Bitcoin Core actually ships: opportunistic 1p1c relay, package validation, cluster limits, submitpackage RPC, package CPFP, sibling eviction with TRUC v3 (BIP431), P2A anchors (BIP433) and ephemeral dust. Critical for Lightning fee bumping and any multi-tx workflow. USE WHEN: implementing CPFP, designing fee-bump strategies, debugging "why won't my child confirm", reasoning about Lightning anchor pinning.

Bitcoin P2P network protocol: messages, version handshake, addr/addrv2, compact blocks (BIP152), compact block filters (BIP157/158), v2 transport encryption (BIP324), wtxid relay (BIP339), Erlay (BIP330), Dandelion++ (BIP156). USE WHEN: implementing/debugging a node, integrating with bitcoind P2P, understanding address gossip, designing privacy-preserving propagation.

MuSig2 (BIP327): two-round Schnorr key aggregation for n-of-n multisig. Aggregates n public keys into a single 32-byte x-only pubkey indistinguishable from a single-sig. Used in Taproot cooperative spends. Quick refs: protocol round-trip, key aggregation math, common attacks. USE WHEN: implementing n-of-n cooperative Taproot signing, designing Lightning Taproot channels, joint custody.

Miniscript: structured subset of Bitcoin Script with fragment types, satisfaction analysis, malleability resistance. Policy → Miniscript → Script compilation. Used in descriptors (wsh + tr) and modern wallets to express spending conditions safely. USE WHEN: composing complex spending conditions, deriving the cheapest satisfaction, ensuring scripts are non-malleable.

Stratum V2: encrypted, miner-driven mining protocol. Job Declaration, Template Provider, allows miners to choose their own tx set. Defeats pool-level censorship. USE WHEN: deploying SV2-capable mining infrastructure, evaluating V1 vs V2, integrating with Braiins Pool / Datum.

Stratum V1: TCP/JSON protocol between mining pool and miners. Subscribe, authorize, mining.notify, mining.submit. Most-used protocol but security/decentralization weaknesses. USE WHEN: integrating mining hardware, building pool / proxy software, debugging hash submission.

Bitcoin Proof of Work: SHA256d on block header, target, nonce iteration, hashrate, mining math. USE WHEN: explaining mining mechanics, debugging mining software, designing mining-related apps.

Mining pool reward schemes: PPS, FPPS, PPLNS, PPS+, Score, prop. Block generation queue, share variance, payout cycles. Solo mining vs pooled. USE WHEN: comparing pools, designing reward systems, understanding miner economics.

ASIC mining firmware: Braiins OS+, Vnish, BUMa, ESP-Miner/AxeOS (Bitaxe), stock firmware, custom firmware tradeoffs. Overclocking, undervolting, autotuning, efficiency curves. USE WHEN: deploying mining firmware, evaluating efficiency vs hashrate, choosing custom vs stock.

Difficulty adjustment algorithm: 2016-block re-target window, max 4x factor, time-warp considerations, real-world hashrate dynamics. USE WHEN: predicting next adjustment, understanding hashrate/ difficulty cycles, building mining analytics.

Decentralized mining pools: Public-Pool, BraiinsP2Pool, Solo CKPool, Datum (Ocean). Reduce centralization vs traditional pools. USE WHEN: solo mining, evaluating decentralized options, building censorship-resistant infrastructure.

Runes: Casey Rodarmor's UTXO-native fungible token protocol. Activated at halving April 2024. Smaller on-chain footprint than BRC-20, native validation rules. USE WHEN: building Runes apps, comparing with BRC-20 / Atomicals.

Ordinal theory: numbering scheme for individual satoshis (sat ordinals). ord client, sat-tracking, rare sat collecting, foundation for inscriptions / BRC-20 / sub-protocols. USE WHEN: working with ord client, tracking sats, building Ordinals apps.

Inscriptions: arbitrary data committed to specific sats via Taproot envelope structure. Foundation for BRC-20, recursive inscriptions, "Bitcoin NFTs". USE WHEN: creating/parsing inscriptions, debugging inscription flow, evaluating inscription cost / fee impact.

BRC-20: fungible token standard via JSON inscriptions. Deploy / mint / transfer operations. Permissionless and unaudited; large ecosystem post-2023. USE WHEN: building BRC-20 tooling, evaluating token issuance on Bitcoin, comparing with Runes / Taproot Assets.

Atomicals protocol: alternative metaprotocol family with ARC-20 (fungible) and AVM (Atomicals VM) for richer logic. UTXO-bound digital objects. USE WHEN: working with Atomicals, comparing with Ordinals / Runes.

Generic Bitcoin message signing: BIP137 (legacy P2PKH-only) and BIP322 (modern, supports any output type). Used for proof-of-ownership, withdraw verification, federated authentication, exchange KYC-free attestation. USE WHEN: implementing "sign this message with your Bitcoin address", verifying ownership of an address, building auth via signing.

taproot-assets daemon (tapd): Go implementation of Taproot Assets Protocol by Lightning Labs. Companion to LND. USE WHEN: integrating with tapd, building Taproot Assets apps in Go.

rust-secp256k1: Rust bindings to libsecp256k1 (C). ECDSA, Schnorr, ECDH, key tweaking, MuSig2 (BIP327, since 0.33). USE WHEN: low-level crypto in Rust, working with raw secp256k1 operations.

libsecp256k1: the canonical secp256k1 C library. Used by Bitcoin Core, rust-secp256k1, all major language bindings. USE WHEN: low-level crypto in C/C++, building bindings, performance- critical paths.

@scure/btc-signer: modern audited Bitcoin signer in TypeScript. Pure functional, minimal dependencies, browser-friendly. USE WHEN: building modern web/mobile Bitcoin apps, evaluating bitcoinjs-lib alternative.

rust-dlc: Rust DLC implementation. Funding, CET construction, oracle attestation handling, refund logic. USE WHEN: building DLC apps in Rust, integrating oracle-driven Bitcoin contracts.

rust-bitcoin: Rust crate for Bitcoin primitives. Tx, Block, Script, Address, Network, key types, PSBT, BIP32. Foundation for BDK, LDK, miniscript-rs. USE WHEN: building Bitcoin apps in Rust, parsing/constructing txs, working with addresses + scripts.

python-bitcoinlib by Peter Todd: low-level Bitcoin primitives in Python. Tx, Script, Address, key types, RPC client. USE WHEN: scripting Bitcoin operations in Python, low-level manipulation, Bitcoin Core RPC integration.

NBitcoin: comprehensive .NET / C# Bitcoin library. Used by BTCPay Server, NBXplorer, many .NET tools. Tx, Script, PSBT, BIP32, HW wallet integration. USE WHEN: building .NET Bitcoin apps, integrating with BTCPay ecosystem.

rust-miniscript: Rust crate for Miniscript and descriptor handling. Policy compilation, satisfaction analysis, descriptor parsing for legacy + Tapscript. USE WHEN: working with descriptors / miniscript in Rust, building wallets that compose spending conditions.

mempool.js (@mempool/mempool.js): TypeScript client for mempool.space API. REST + WebSocket; address history, fee estimates, mining stats. USE WHEN: integrating mempool.space data, building wallets / explorers.

lnd Go libraries: lnrpc (gRPC client), chantools (channel utilities), loopd (Loop client), poold (Pool client), neutrino (BIP157/158 SPV). USE WHEN: building Go apps integrating with LND, Loop, or running Neutrino light clients.

libwally-core: Blockstream's C library for wallet primitives. BIP32/39, PSBT, Liquid Confidential Transactions, BIP143, Schnorr. Bindings to Python, JS, Java, Swift. USE WHEN: building cross-language wallets via libwally bindings, integrating Liquid CT.

libbitcoin: comprehensive C++ Bitcoin library. Multiple toolkits (libbitcoin-system, libbitcoin-server, libbitcoin-explorer). Alternative implementation focused on cleanliness. USE WHEN: studying alternative Bitcoin codebases, building C++ Bitcoin services.

Lightning Dev Kit (LDK): modular Rust crates for embedding Lightning in apps. ldk-node for opinionated quick-start. Bindings to Swift / Kotlin / Python. USE WHEN: embedding Lightning in mobile/desktop apps, building custom LN logic.

hdwallet (Python): HD wallet generator + key derivation. Multi-coin, BIP32/39/44/49/84/86/141. USE WHEN: deriving keys for many cryptocurrencies, scripting key generation in Python.

embit: Python Bitcoin library designed for embedded / hardware wallets (MicroPython compatible). Used by Specter DIY, Krux, SeedSigner. USE WHEN: building HW signers, MicroPython Bitcoin apps, low-resource Python.

corepc: the rust-bitcoin org's Bitcoin Core JSON-RPC stack. `corepc-types` (per-Core-version response types + version-agnostic `model` types), `corepc-client` (blocking/async test client), `bitcoind` (spin up regtest nodes for integration tests). USE WHEN: talking to bitcoind from Rust, or integration-testing Rust code against a real Bitcoin Core binary.

btcsuite: collection of Go Bitcoin libraries. btcec (secp256k1), btcutil (helpers), txscript (Script engine), wire (P2P). USE WHEN: building Bitcoin Go apps, integrating with LND / btcd.

btcd: full-node Bitcoin implementation in Go by btcsuite. Server, RPC, wallet (btcwallet), Lightning (LND-derived). USE WHEN: building Go-native Bitcoin services, alternative to bitcoind, integrating with btcsuite ecosystem.

bolt11 decoder libraries: parse / encode BOLT11 Lightning invoices in JS, Python, Rust, Go. USE WHEN: parsing LN invoices in app code, building Lightning payment flows.

bitcoinlib (Python): high-level wallet library by 1200WD. HD wallets, multi-currency, address generation, tx construction. USE WHEN: building Python wallets, multi-currency BTC + altcoin apps.

bitcoinjs-lib: TypeScript/JavaScript Bitcoin library. Tx, Script, Address, key types, PSBT, BIP32. Browser + Node. USE WHEN: building Bitcoin apps in JS/TS, server or browser.

bitcoinj: mature Java/Kotlin Bitcoin library. SPV node, wallet, HD derivation, used by BlueWallet (Android), older mobile wallets. USE WHEN: building JVM Bitcoin apps, Android-native wallet code.

libbitcoinkernel: Bitcoin Core's experimental C library exposing the validation engine (block/header validation, block index traversal, block + undo reads, script verification), and the `bitcoinkernel` Rust bindings over `libbitcoinkernel-sys`. USE WHEN: embedding Core's exact consensus semantics in a non-C++ process - indexers, explorers, validation tooling, fuzzing harnesses.

bdkpython: Python bindings to BDK. Same descriptor-first wallet API as Rust BDK. UniFFI-generated. USE WHEN: building Python wallets with BDK quality, multi-language app where Python integrates same logic as Rust/Swift.

bdk-jvm / bdk-android: Kotlin/Java bindings to BDK. Same descriptor- first wallet API. UniFFI-generated. USE WHEN: building JVM / Android wallets with BDK quality.

Bitcoin Dev Kit (BDK): high-level Rust wallet library. Descriptor-based wallets, multiple chain backends (Esplora, Electrum, RPC), PSBT, fee estimation, coin selection. Bindings to Swift / Kotlin / Python / Flutter. USE WHEN: building wallets in Rust or via BDK bindings, integrating descriptor wallets into apps.

bcoin: full-node Bitcoin implementation in JavaScript. Wallets, HTTP API, SPV mode. Alternative to running bitcoind. USE WHEN: needing a Node-native Bitcoin full node, evaluating alternative implementations.

Threshold Network (tBTC): federated BTC bridge to Ethereum/EVM chains with t-of-n threshold signers, random group selection. USE WHEN: bridging BTC to Ethereum DeFi, evaluating tBTC vs wBTC.

Taproot Assets (formerly Taro) by Lightning Labs: client-side validation asset protocol on Bitcoin + Lightning. Multi-asset Lightning channels, AddressV2, multi-hop asset routing. USE WHEN: issuing/transferring assets on Bitcoin, integrating asset Lightning channels, evaluating TAP vs RGB.

Strata by Alpen Labs: ZK rollup on Bitcoin, glock (garbled lock) bridge, EVM-compatible execution. Emerging Bitcoin L2 in 2025-2026. USE WHEN: evaluating Strata for deployment, comparing with Citrea.

Statechains: off-chain UTXO ownership transfer via Statechain Operator (SO) signing. Mercury Layer (CommerceBlock) is the main implementation. 1-of-N security model. USE WHEN: evaluating off-chain UTXO transfer, comparing with Spark/ Ark, designing 1-of-N security models.

Stacks: Bitcoin smart contract layer with Clarity language, sBTC for native peg, Nakamoto upgrade for fast finality, PoX (Proof of Transfer) consensus. USE WHEN: building Bitcoin smart contracts, integrating sBTC, evaluating Stacks vs RSK / EVM alternatives.

Spark by Lightspark: statechain-derived L2 with FROST threshold signatures, leaf architecture, Lightning compatibility. Beta launched April 2025; managed by Spark Operators (SOs). USE WHEN: integrating with Spark, evaluating Spark vs Ark vs Lightning, designing leaf-based UTXO trees.

Solv Protocol: SolvBTC / xSolvBTC tokenized Bitcoin distributed across many chains, custody behind Safe multisigs with a Vault Guardian and FROST signing partners. Migrated bridging from LayerZero to Chainlink CCIP on 7 May 2026. BRO Vault incident, 5 March 2026: 38.0474 SolvBTC (~$2.7M), fully compensated. USE WHEN: integrating SolvBTC, threat-modelling multi-chain wrapped BTC, reviewing BTCFi custody incidents.

Rootstock (RSK): EVM-compatible Bitcoin sidechain with merge mining and federation peg. RBTC native token, 30-second blocks, Solidity smart contracts. USE WHEN: building Bitcoin DeFi via EVM contracts, integrating RSK peg, comparing with Stacks / Liquid.

RGB protocol: client-side validated smart contracts on Bitcoin + Lightning. v0.12 consensus (zk-AluVM, issuers), the diverging v0.11.1 line, rgb-lightning-node for LN integration. USDT-on-RGB rollout. USE WHEN: building RGB contracts, integrating RGB Lightning, comparing with TAP.

Mezo: Thesis's Bitcoin-first Cosmos SDK / CometBFT chain with EVM (Evmos fork), BTC for gas, tBTC bridging and a Proof-of-Authority validator set. Mainnet 28 May 2025. MUSD is its Bitcoin-backed CDP stablecoin, a Threshold USD / Liquity fork with a 110% minimum collateral ratio. Chain TVL ~$71.7M on 15 September 2026. USE WHEN: building on Mezo, integrating MUSD, evaluating a major downstream consumer of tBTC.

Merlin Chain: Polygon-CDK Bitcoin L2 with EVM and a federation peg; its Bitcoin fraud-proof module is still unshipped as of September 2026. Was the TVL leader in 2024; DeFi TVL is down ~98% from that peak as of September 2026. USE WHEN: evaluating Merlin for deployment, BTC DeFi.

MAP Protocol: omnichain interoperability layer with Bitcoin integration. Cross-chain messaging across many chains; positions itself as Bitcoin L2 connector. Butter Bridge V3.1 was exploited on 20 May 2026; read the status note before treating it as production bridge infrastructure. USE WHEN: building cross-chain apps spanning Bitcoin + others.

Lombard: LBTC, a cross-chain yield-bearing wrapped BTC issued by a 10-of-14 institutional notary consortium running a Cosmos appchain (the Lombard Ledger), with HSM key custody (CubeSigner) and an independent Bascule verification layer. LBTC yield moved OFF Babylon staking to a Bitwise covered-call strategy in 2026. USE WHEN: integrating LBTC, threat-modelling consortium-issued wrapped BTC, evaluating BTC "liquid staking" yield claims.

Liquid Network: federated sidechain by Blockstream. Confidential Transactions, asset issuance (LBTC, USDt-Liquid, others), 2-min blocks, n-of-m federation peg-out. Elements codebase. USE WHEN: building on Liquid, peg-in/peg-out integrations, designing CT-based privacy.

Hemi Network: hybrid Bitcoin + Ethereum L2 with "superfinality" via Bitcoin PoW. Chain TVL under $1M across 44 listed protocols (DefiLlama, September 2026), down from a ~$330M peak in June 2025. USE WHEN: building cross-chain DeFi, evaluating Hemi vs BOB.

Fractal Bitcoin: a Bitcoin Core-derived scaling chain with ~30s blocks and Cadence Mining (part merge-mined with Bitcoin, part permissionless, part Index Mining since FIP-101). Mainnet 9 Sept 2024. FIP-102 / fractald v0.4.0 hard-forked at block 2,100,000, combining the first and second FB halvings; the chain passed that height before 15 September 2026. USE WHEN: building on Fractal, indexing BRC-20 on Fractal, reasoning about merge-mined Bitcoin-derived chains.

Fedimint: federated Chaumian e-cash on Bitcoin with Lightning gateway. Multi-sig guardians, blind-signature notes, community-scale custody with privacy. Fedi mobile wallet. USE WHEN: deploying community mints, integrating federated e-cash, evaluating Fedimint vs Cashu.

Drivechains (BIP300/301) and Spacechains (Ruben Somsen): proposals for sidechains pegged via miner-validated locks or via OP_CAT-like primitives. Status: NOT activated on mainnet. USE WHEN: evaluating proposed sidechain mechanisms, understanding why they're not live, comparing with federated/trustless bridges.

Counterparty: legacy Bitcoin meta-protocol (2014) for assets, DEX, betting using OP_RETURN. Usage is largely historic, but the reference implementation still ships protocol upgrades (AMM pools, Taproot envelopes) as of September 2026. USE WHEN: dealing with legacy Counterparty assets, understanding pre-Ordinals asset ecosystem, evaluating obsolete patterns.

Core (Core DAO): EVM sidechain whose Satoshi Plus consensus elects validators from delegated Bitcoin hash power, delegated CORE stake and non-custodial CLTV-timelocked BTC stake. Chain ID 1116, 3s blocks, 24h election rounds. Latest client v1.0.26 (2 Sept 2026); CoreRewardFix hard fork activated 3 Sept 2026. USE WHEN: building on Core, implementing non-custodial BTC staking or hash-power delegation, evaluating BTCFi yield venues.

Citrea: first ZK-rollup on Bitcoin (mainnet 27 Jan 2026), zkEVM, BitVM2 trustless bridge, ctUSD stablecoin, native BTC lending. USE WHEN: building zkEVM apps on Bitcoin, integrating with Citrea, evaluating ZK rollups vs sidechains.

Cashu: single-mint Chaumian e-cash for Bitcoin Lightning. NUTs (Notation, Usage, and Terminology specs) define mint protocol, payment flow, blind signatures. USE WHEN: integrating Cashu mints/wallets, building NUT-compliant apps, comparing with Fedimint.

B² Network (BSquared): hybrid ZK + optimistic Bitcoin L2 with EVM compatibility. Live since 2024; DeFi TVL is down ~97% from its December 2024 peak as of September 2026. USE WHEN: evaluating B² for deployment, integrating with their bridge, comparing Bitcoin L2 options.

Botanix: RETIRED EVM-compatible Bitcoin L2 using "Spiderchain" architecture (federated multisig rotated by orchestrators). stBTC native staking. Mainnet 1 July 2025; wind-down announced 5 June 2026. USE WHEN: studying Spiderchain federation rotation as a design, or explaining why Botanix is no longer a deployment target.

BOB (Build on Bitcoin): hybrid Bitcoin/Ethereum L2 using OP Stack + Bitcoin security. Bridges to Bitcoin via threshold signatures + zk-proofs. USE WHEN: building cross-chain Bitcoin/Ethereum apps, evaluating BOB hybrid model.

BitVM, BitVM2, BitVM3: off-chain computation framework using optimistic challenge games on Bitcoin script. Foundation for trust-minimized bridges to L2s and PoS chains. USE WHEN: building trust-minimized bridges, understanding ZK rollup peg-out mechanisms, evaluating bridge security models.

Bitlayer: Bitcoin L2 with ZK proof system, BTC staking, EVM compatibility. Early BTCFi entrant (2024); TVL down ~99.9% from peak as of September 2026. USE WHEN: evaluating Bitlayer for deployment, BTC staking products.

Babylon: native BTC staking protocol securing PoS chains. Trustless Bitcoin Vaults (public testnet as of September 2026), integration with Cosmos chains. No bridging / wrapping required. USE WHEN: building BTC-secured PoS chains, integrating Babylon staking, evaluating BTCFi yield options.

Ark protocol: VTXOs (Virtual Transaction Outputs) batched off-chain with periodic on-chain settlement. ARKADE (Ark Labs) is the first mainnet implementation. ASP (Ark Service Provider) coordinates rounds; users keep unilateral exit. USE WHEN: building Ark integrations, evaluating Ark vs Lightning, designing batched payment flows.

Bitcoin Knots: Luke Dashjr's Bitcoin Core fork with stricter mempool policy and additional configuration. Since the 2026 BIP-110 and BLAKE2b hardforks it is also a separate consensus network, not only a policy downstream. Differences vs Core, when to consider, compatibility. USE WHEN: evaluating Knots for stricter mempool policy, reviewing a node deployment that uses Knots, understanding policy and consensus divergence between Core and Knots.

Specter Desktop: open-source GUI for Bitcoin Core + multisig coordination + HW wallet. Designed for self-custody power users. USE WHEN: setting up multisig with Specter, evaluating coordinator options.

Sparrow Wallet: power-user desktop wallet for Bitcoin. PSBT-first, HW wallet support, multisig coordination, Silent Payments, PayJoin, BIP47. USE WHEN: power-user wallet workflows, evaluating Sparrow vs Specter / Electrum.

Self-hosted Bitcoin node distros: Umbrel, Start9 StartOS, RaspiBlitz, MyNode, Citadel. Pre-configured Bitcoin + Lightning + apps. USE WHEN: deploying personal node infrastructure, choosing between distros.

mempool.space: open-source mempool explorer + accelerator. Detailed fee tracking, mempool blocks projection, REST + WebSocket APIs. Self-hostable. USE WHEN: integrating mempool.space API, deploying self-hosted variant, evaluating fee estimation services.

Fulcrum: Calin Culianu's Electrum-protocol indexer in C++. Faster than electrs for high-volume queries. Serves Electrum clients + LN nodes. USE WHEN: deploying high-load Electrum server, comparing with electrs.

Esplora: Blockstream's HTTP-based block explorer + indexer. REST API at /api/<endpoint>. Powers blockstream.info, mempool.space's earlier versions, and self-hosted explorers. USE WHEN: deploying a personal block explorer, integrating with Esplora REST API, building wallet / monitoring on Esplora-style endpoint.

Electrum Wallet: classic Python desktop wallet. Lightweight, runs on most platforms, plugin ecosystem, hardware wallet support. USE WHEN: evaluating mature Bitcoin wallet, integrating Electrum protocol clients.

Electrs: Roman Zeyde's Electrum-protocol indexer in Rust. Lightweight, serves Electrum clients; BIP157 filter scan stays on Bitcoin Core. USE WHEN: deploying personal Electrum server, integrating LN with Electrum backend, evaluating indexers.

Caravan: open-source web-based multisig coordinator (no install). Read-only by default; HW wallet support via HWI bridge. USE WHEN: setting up multisig without installing software, educational multisig flows.

BTCPay Server: open-source merchant payment processor. Self-hosted, supports BTC + Lightning + altcoins, plugin ecosystem, Lightning Address resolver, point-of-sale. USE WHEN: deploying merchant payments, integrating with BTCPay, building plugins.

BlueWallet: mobile Bitcoin + Lightning wallet (iOS/Android). Lightning via self-hosted LndHub, plus a gated Ark/Arkade wallet. Multi-wallet support. USE WHEN: mobile wallet integrations, evaluating BlueWallet vs Phoenix / Breez.

Trezor hardware wallets: Model T, Model One, Trezor Safe 3, Safe 5, Safe 7. Trezor Suite, trezorctl, USB protocol, BIP32 derivation, passphrase support, Shamir Backup. USE WHEN: integrating with Trezor, supporting Trezor in app, troubleshooting Trezor signing.

Specter DIY: open-source HW wallet built on STM32 dev board with display. By the Specter team. USE WHEN: building Specter DIY, evaluating DIY HW signing options.

SeedSigner: DIY Bitcoin signing device. Raspberry Pi Zero + camera + screen. Boots from microSD, no permanent state. Stateless airgap signing. USE WHEN: building / supporting SeedSigner, designing stateless signing flows.

PSBT signing flow patterns across HW vendors: USB direct, microSD airgap, QR airgap, NFC, multi-device coordination, silent-payment PSBT fields (BIP375/BIP376). USE WHEN: designing HW signing UX, debugging cross-device PSBT flow, supporting multi-vendor multisig or silent payments.

Foundation Passport: Passport Core is the QR-only airgap HW wallet - no USB connectivity for signing, camera + microSD only. Passport Prime (GA 2026) is the connected KeyOS security platform. Open-source firmware. USE WHEN: integrating Passport, designing strict airgap flows.

Multi-vendor multisig: combining HW wallets from different vendors (Trezor + Ledger + Coldcard) for diversification. Coordinator-mediated setup, descriptor sharing, threat model. USE WHEN: designing multi-vendor custody, implementing 2-of-3 multisig with diverse hardware.