Discover AI Agent Skills

Check BIM model consistency: naming conventions, parameter completeness, spatial relationships, and data integrity across model elements.

Writes OpenSCAD code and drives the `openscad` command-line compiler to produce STL/3MF/AMF/DXF/SVG/PNG outputs from parametric `.scad` models. This skill should be used when the user asks to design a 3D-printable part, generate a laser-cut 2D plate, render a preview image of a CAD model, export STL for 3D printing, batch-render parametric variants, or convert between mesh formats. Invoked via "/hardware:use-openscad".

Design LLM-as-Judge evaluators for subjective criteria that code-based checks cannot handle. Use when a failure mode requires interpretation (tone, faithfulness, relevance, completeness). Do NOT use when the failure mode can be checked with code (regex, schema validation, execution tests). Do NOT use when you need to validate or calibrate the judge — use validate-evaluator instead.

Classroom Video Editor — Edit Lecture Recordings and Lesson Videos for Teachers. The district mandated asynchronous video lessons last semester and gave teachers exactly zero editing software to make them with. You have a forty-five-minute Zoom recording where the first eight minutes are students joining late and the last three are you saying goodbye to an empty grid. Upload the file. The AI trims the dead ends, splits the lecture into topic segments matching your slide transitions, overlays key vocabulary as pop-up definitions when you first mention a term, and burns in closed captions that meet ADA accessibility requirements. Insert a five-second "pause and think" card before each discussion question. Export to Google Classroom, Canvas, or Schoology as a standard mp4 that plays on any student device. Re-record one section when the curriculum updates without re-editing the entire lesson. Built for K-12 teachers flipping their classrooms, university professors converting in-person lectures to async modules, substitute teachers preparing video plans, and curriculum coordinators assembling district-wide instructional libraries. Supports mp4, mov, avi, webm, mkv.

Claim a taskwarrior task as in-flight (+ACTIVE) and write a coworker marker. Use when picking up a task from task-coordinate output before starting implementation.

Finds content gaps and opportunities from Google SERP analysis using apidojo's Google Search scraper on Apify. Triggers when the user asks to: find content gaps in Google search results, identify topics that are poorly covered in Google SERPs, discover content opportunities where competitors are ranking but coverage is weak, analyze what is missing from the top search results for a keyword, find underserved topics in a niche from Google search, or identify where existing content could easily outrank weak competitors. Returns keyword opportunities, SERP quality scores, content gap analysis, and recommended topics. Ideal for SEO strategists, content marketers, and blog editors prioritizing content investments.

Integrates Hardware Security Modules (HSMs) via the PKCS#11 interface using python-pkcs11, performing key generation, signing, encryption, verification, and token/slot queries against SoftHSM2, AWS CloudHSM, or YubiHSM2. Use when implementing HSM-backed key management or validating HSM configuration for FIPS 140-2/3 compliance.

Execute build, test, lint, serve, and other tasks in an Nx workspace using single runs, run-many, and affected commands. Use when user says "run tests", "build my app", "lint affected", "serve the project", "run all tasks", or "nx affected". Do NOT use for code generation (use nx-generate) or workspace configuration (use nx-workspace).

Complete Next.js data fetching system (Next.js 15.5/16). PROACTIVELY activate for: (1) Server Component data fetching, (2) Parallel and sequential fetching, (3) Streaming with Suspense, (4) Route Handlers (API routes), (5) Client-side fetching with SWR/TanStack Query, (6) generateStaticParams for static generation, (7) Revalidation strategies, (8) Error handling for data, (9) Async params/searchParams (Next.js 16), (10) Cache Components with 'use cache'. Provides: Fetch patterns, caching options, streaming UI, API route handlers, client fetching setup, async params pattern. Ensures optimal data loading with proper caching and error handling.

Create personalized triathlon, marathon, and ultra-endurance training plans. Use when athletes ask for training plans, workout schedules, race preparation, or coaching advice. Can sync with Strava to analyze training history, or work from manually provided fitness data. Generates periodized plans with sport-specific workouts, zones, and race-day strategies.

Compose CometChat iOS screens into an app — navigation stack, tab bar, user/group pickers, group details, threads, and iPad. Use when the question is layout and navigation rather than a single component. Triggers: 'tab based chat ios', 'add a groups tab', 'open group details', 'thread screen ios', 'ipad split view cometchat'.

Use this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.

A structured root-cause investigation protocol for complex, ambiguous, or multi-layer technical problems. Activate this skill whenever: a problem has resisted two or more fix attempts; the root cause is unknown or assumed; you are tempted to try a variation of something that already failed; a system has multiple interacting layers (hardware, OS, runtime, middleware, config, network); the user says "ultrathink", "think deeper", "figure out why", "stop guessing", "find the root cause", or "it's still broken after your fix". Also activate proactively when you catch yourself about to write a fix before you have verified the cause — that instinct is the signal the protocol is needed. The protocol enforces three disciplines that distinguish root-cause investigation from trial-and-error: (1) explicit THOUGHT/ACTION/OBSERVATION cycles, (2) a hard gate that blocks implementation until the cause is verified by direct evidence, and (3) structured escalation when in-process diagnostic tools are exhausted.

Expert guidance for building onchain applications with OnchainKit SDK components and utilities

/cs:post-mortem <decision> — Honest retrospective on an executed decision, scored against original assumptions and dissent. Closes the strategic sprint loop. Use when a decision hits its 90-day review checkpoint or its kill criteria trigger — e.g. scoring last quarter's pricing change against its pre-committed success metrics.

Salesloft integration. Manage sales data, records, and workflows. Use when the user wants to interact with Salesloft data.

Use when auditing a codebase to find every JCR query it issues — XPath, SQL2, or AEM QueryBuilder predicates, including ones assembled programmatically through wrapper/helper/DAO code — before an Oak index audit, migration, performance investigation, or when asked "what queries does this app run".

A reference layered architecture for production LangChain 1.0 / LangGraph 1.0 services — LLM factory with version-safe defaults, chain/graph registry, retriever and tool DI, Pydantic-validated config, per-request tenant scoping, middleware ordering, checkpointer selection per environment. Use when starting a new service, refactoring a tangled chain, or onboarding a team to existing code. Trigger with "langchain architecture", "langchain llm factory", "langchain chain registry", "langchain dependency injection", "langchain project structure".