发现 Skills

Implement the minimal code needed to make failing tests pass in the TDD green phase.

Guide a user through authoring a new document using the GoodDocs template and validation rules.

YAML is sheet music. The LLM is the jazz musician. Comments are the soul.

Create or update Claude Code skills. Use when a user wants to create a new skill, update an existing skill, or needs guidance on skill design.

This skill should be used when the user asks to "swap tokens", "trade ETH for USDC", "exchange tokens on Uniswap", "buy tokens", "sell tokens", "convert ETH to stablecoins", "find memecoins", "discover tokens", "research tokens", "tokens to buy", "find tokens to swap", "what should I buy", or mentions swapping, trading, researching, discovering, buying, or exchanging tokens on any Uniswap-supported chain. Supports both known token swaps and token discovery workflows (discovery uses keyword search and web search — there is no live "trending" feed). Generates deep links to execute swaps in the Uniswap interface.

Always use this skill when integrating Base UI components `@base-ui-components/react` with Material UI `@mui/material`.

Reference for calling the Claude Code agent from other agents.

Use this skill when the user asks to "add LSP server", "configure language server", "set up LSP in plugin", "add code intelligence", "integrate language server protocol", "use pyright-lsp", "use typescript-lsp", "use rust-lsp", "socket transport", "initializationOptions", mentions LSP servers, or discusses extensionToLanguage mappings. Provides guidance for integrating Language Server Protocol (LSP) servers into Claude Code plugins to enable enhanced code intelligence.

Download Hulu movies and TV shows for personal offline viewing. Save your Hulu subscription content for watching without an internet connection.

Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.

Fully automated release note generator for Sky Map. Just provide the last tag.

Media ingestion pipeline — download, transcribe (local GPU), classify, and summarize YouTube videos, Shorts, and TikTok content into organized research notes. Triggers on "research video", "process video", "transcribe", "ingest video", "media pipeline", "watch and summarize", or when a YouTube/TikTok URL is shared with intent to analyze.

ClaudePA session closeout — processes pending updates to Active Searches, updates work category timestamps, manages FLAGS, verifies calendar writes. Standalone from /closeout.

Updates core project docs from session work. Activates on '/document', 'document this', 'update the docs', 'let's document', 'mark this off'. Reads session manifest, updates CHANGELOG/SPEC/STATE/BugTracker, enforces naming conventions, marks completed items done. Mid-session safe — not a closeout ceremony.

Stress-test a plan or design through relentless Socratic questioning, walking down each decision branch until reaching shared understanding. Use when the user wants to stress-test a plan, get grilled, validate assumptions, or mentions 'grill me'.

Triage a bug by deeply exploring the codebase for root cause, then create a GitHub issue with a TDD-based fix plan. Mostly hands-off — minimal user interaction. Use when user reports a bug, wants to investigate an issue, mentions triage, or wants a fix plan.

Generate icons, stickers, and app assets using AI. Use when user wants to create icons, stickers, logos, or visual assets.

Evaluate a system's ability to handle growth — identify bottlenecks, single points of failure, and scaling strategies.

Use when user says "send to Ray," "show in Ray," "debug in Ray," "log to Ray," "display in Ray," or wants to visualize data, debug output, or show diagrams in the Ray desktop application.

Complete Test-Driven Development workflow with red-green-refactor cycle

Translate ideas into user stories, then implement each story as a testable MCP tool with unit tests. Use when: (1) building a new feature from an idea or requirement, (2) creating MCP tools from user stories, (3) writing MCP server tests, (4) replacing flaky E2E tests with unit-tested MCP tools, (5) story-driven development, (6) exposing business logic as MCP tools. Triggers: 'new feature', 'user story', 'MCP from idea', 'test MCP tool', 'create MCP server from requirements', 'story-driven', 'replace E2E with unit tests'.

Master security assessments with vulnerability scanning, penetration testing, security testing, and security audits.

Example skill demonstrating Claude Code capabilities. Activates when user mentions "example", "demo", or "template". Shows how to create effective Skills with proper structure. Use when user wants to see skill examples or understand skill creation.

Advanced .faf (Foundational AI-context Format) specialist. IANA-registered format, MCP server config, championship scoring, bi-directional sync.