发现 AI Agent Skills

Manage WezTerm mux servers for AI agent swarms on high-RAM servers (512GB+). Use when wezterm mux unresponsive, agent sessions need rescue, tuning scrollback, or configuring persistent remote sessions.

Provides MaxCompute SQL intelligent generation capabilities for AI agents, covering text2sql conversion principles, dialect syntax differences (DQL/DDL/DML), common query pattern templates (Top N, PIVOT, window functions, etc.), and ODPS error code diagnostics. Use when generating, debugging, or migrating MaxCompute / ODPS SQL.

Use when growing Xiaohongshu following, engaging with audience, building community, responding to comments and DMs, or increasing follower retention and loyalty

Alpaca integration. Manage Organizations, Users, Filters. Use when the user wants to interact with Alpaca data.

Expert knowledge for Azure Portal development including troubleshooting, security, and configuration. Use when managing portal RBAC sharing, Intune/Entra mobile access, dashboard JSON, portal policies, or HAR diagnostics, and other Azure Portal related development tasks. Not for Azure Cloud Shell (use azure-cloud-shell), Azure Resource Manager (use azure-resource-manager), Azure Monitor (use azure-monitor), Azure Security (use azure-security).

Verify that existing work is ready to merge, release, or hand off using an explicit evidence contract. Use when a request asks to verify, validate, prove, check readiness, run the relevant tests, or distinguish a claimed result from an observed one. Do not use to write missing tests or fix failures.

Find Amazon products for affiliate marketing with ASINs, prices, and ratings. Use when user searches for Amazon products, affiliate recommendations, or needs product ASINs for content.

Download videos, audio, subtitles, and clean paragraph-style transcripts from YouTube and any other yt-dlp supported site. Use when asked to “download this video”, “save this clip”, “rip audio”, “get subtitles”, “get transcript”, or to troubleshoot yt-dlp/ffmpeg and formats/playlists.

Builds network traffic baselines from NetFlow/IPFIX CSV or JSON exports using Python pandas, computing hourly/daily volume distributions, per-host and protocol/port statistics, and top-talker profiles, then flags outliers via z-score and IQR anomaly detection. Use when a SOC analyst needs to establish normal traffic patterns and surface deviations such as data exfiltration spikes, beaconing, or unusual port usage from historical flow data.

Evaluates GraphRAG systems across knowledge graph completeness, retrieval relevance, answer correctness, reasoning depth, and hallucination prevention. Provides structured evaluation frameworks, metric selection guidance, and testing protocols. Use when evaluating GraphRAG quality, benchmarking multi-step reasoning, measuring hallucination reduction, or when user mentions evaluate GraphRAG, quality metrics, answer correctness, test my GraphRAG, or measure RAG performance.

Sets up, manages, queries, and configures Cloud Firestore databases (Standard/Enterprise edition), including data modeling, security rules, indexes, and SDK integrations (Web, Python, iOS, Android, Flutter). Use when creating/listing Firestore databases, defining data models/indexes, writing SDK queries, or integrating Firestore SDKs. Don't use for Firebase Hosting, Data Connect, Auth, Storage/GCS, Crashlytics, Functions, or BigQuery.

Looks up current LiveKit facts (API signatures, CLI flags, config options, model and provider support, SDK changelogs, pricing) from the docs instead of answering from memory. Use whenever a question touches LiveKit specifics: "does LiveKit support X", "what changed in agents 1.8", "what are the arguments to Y", "how much does LiveKit cost", "find an example of Z in the LiveKit repos", or before writing any LiveKit code. Other LiveKit skills load this one first. Covers the LiveKit Docs MCP server and the `lk docs` CLI.

Implement Encore.ts services and lay out an application using `encore.service.ts`, service directories, systems, and `~encore/clients`. For service boundaries and architecture decisions, use `encore-architecture`.

WeChat Mini Program development framework. Use for building WeChat mini apps, WXML templates, WXSS styles, WXS scripting, component development, and WeChat API integration.

The reusable on-brand template-SYSTEM skill -- build a brand kit + a small set of reusable templates so a non-designer can produce consistent on-brand graphics fast across formats. Use when someone wants templates, a brand kit, a consistent visual system, or help choosing/using a design tool (Canva/Adobe Express/Figma). For social, consistency + speed beat bespoke. Uses the BRAND framework. Reads brand-profile first. The agent designs the SYSTEM (brand-kit tokens, template set, hierarchy rules, workflow); a design tool or the image tools produce the actual graphics; the finished asset enters the WoopSocial flow (WoopSocial publishes -- it does NOT design or generate). Honest about the ~70-80% on-brand ceiling and AI copyright limits. Distinct from brand-profile (the identity source), thumbnail-design + pinterest-pin-design (single asset types), carousel-writer (copy vs visual frame), and image-prompt + the image tools (generation vs layout).

PRD writing and product definition expert. Use when writing PRDs, user stories, acceptance criteria, or prioritizing features. Covers RICE/MoSCoW frameworks, agile requirements, and specification best practices.

Creates complete AEM components with dialog, HTL template, Sling Model, unit tests, and clientlibs. Supports extending Core Components and project components. When a Figma design URL is provided, fetches the design via Figma MCP (get_design_context) and translates it into pixel-perfect HTL, CSS, and JS. Follows Adobe Experience League best practices for AEM Cloud Service and 6.5. Use this skill whenever the user mentions creating, building, generating, or scaffolding an AEM component, or mentions component types like teaser, card, hero, banner, accordion, tabs, carousel, list, navigation, breadcrumb, or any custom AEM component. Also trigger when the user wants to extend a Core Component, create a component dialog, add a Sling Model, or convert a Figma design into an AEM component.

You must use this when investigating complex claims across diverse sources or fact-checking contradictory information.