AI Skills Hub - Browse 180,000+ Agent Skills

This skill should be used when the user asks to create a contact in Outlook from freeform text data (e.g., business cards, email signatures, addresses). It handles parsing contact information and creating properly structured Outlook contacts that sync to mobile devices.

This skill should be used when moving a single email message to the Archive folder in Microsoft 365 Mail. It provides a clean interface to move one specific email using its messageId without polluting the context window. Use this skill when processing bulk archive operations, moving spam emails, or any workflow requiring reliable one-email-at-a-time moves to Archive.

CRITICAL: PostgreSQL MCP Server SQL limitations and correct patterns. This skill MUST be consulted before writing any SQL for the CRM database. Documents what works and what DOES NOT work with mcp__postgresql__ tools.

Debug and synchronize communication between the robocar main controller (Heltec WiFi LoRa 32) and camera module (ESP32-CAM)

Transcribe audio files from meetings into text documents using Whisper. Use when the user types /transcribe, has a new audio recording, or when RA detects new audio files in meetings/audio/. Supports speaker diarization with pyannote.

Rapid task capture without breaking flow. Use when the user types /task or wants to quickly add a todo item to tasks.md. Supports priority flags (!high, !low). Use this instead of /note for action items.

Use when tests have race conditions, timing dependencies, or inconsistent pass/fail behavior - replaces arbitrary timeouts with condition polling to wait for actual state changes, eliminating flaky tests from timing guesses

Use when writing tests - test structure, mocking patterns, pre-commit checks

Remote control tmux sessions for interactive CLIs by sending keystrokes and scraping output.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior

Context-efficient browser automation using Playwright scripts and subagent isolation. Use when you need to interact with web pages, extract data from websites, verify page elements, or automate browser tasks while avoiding context window pollution from verbose HTML/accessibility trees. Provides both direct script execution and a specialized subagent pattern for complex investigations that generate large intermediate responses.

The digital librarian for Claude Code projects. Enforces structured document lifecycle management - organizing, indexing, and archiving project documentation automatically. Use when creating, organizing, or managing project documentation. Ensures documents are created in the proper `docs/` directory structure with required metadata, handles temporary documents in system temp directories, maintains an auto-generated index, and performs automatic archiving of old/complete documents. Use for any task involving document creation, organization, or maintenance.

Browser automation toolkit using Playwright. Supports interacting with web applications, form filling, capturing screenshots, viewing browser logs, and running automated tests. Use when automating browser tasks, testing web UI, or scraping web pages.

Upsert a single PR comment that serves as an AI session ledger (human steering, deltas, tests) across Codex + Claude Code. Not a PR description.

Create a structured plan directory with Ralph Wiggum Loop integration for backend Django projects (PLAN.md, task files, and RALPH-PROMPT.md).

Configure AWS IAM users, roles, policies, and identity federation

Build automated CI/CD pipelines with CodePipeline and CodeBuild

MANDATORY skill creation framework for ALL skill creation requests. USE WHEN user wants to create, validate, update, or canonicalize a skill, OR user mentions skill creation, skill development, new skill, build skill, OR user references skill compliance, skill structure, or skill architecture.

Configure S3 buckets with security, lifecycle, and replication policies

Design and implement production-grade VPC architectures

Clear description of what skill does and when to use it. Should match activation triggers.

LLM이 잘 설계된 도구를 통해 외부 서비스와 상호작용할 수 있게 해주는 고품질 MCP (Model Context Protocol) 서버를 만들기 위한 가이드입니다. Python (FastMCP) 또는 Node/TypeScript (MCP SDK)를 사용하여 외부 API나 서비스를 통합하는 MCP 서버를 구축할 때 사용하세요.

Use when the user wants to create, edit, list, or manage Claude Code rules in .claude/rules/. Provides guided elicitation to configure path-specific rules with proper YAML frontmatter and glob patterns. Can list all available rules from user-level and project directories.

다단계 분석, 수정 능력 및 가설 검증이 필요한 복잡한 작업을 위해 구조화되고 성찰적인 문제 해결 방식을 적용합니다. 복잡한 문제 분해, 적응형 계획 수립, 경로 수정이 필요한 분석, 범위가 불분명한 문제, 다단계 해결책 및 가설 기반 작업 시 사용합니다.

[Utility] ⛔ MANDATORY skill for ANY Brain canvas operations. AI MUST invoke this skill BEFORE creating/modifying ANY files in Docs/Brain/. Failure to follow = broken canvas.

Full SDK integration test that runs actual queries through the Claude SDK sandbox. Use after making changes to SDK client code, session management, skill loading, network proxy, voice/TTS, or image generation. Runs real prompts through the SDK to verify the complete path works.

Maintain skills wiki health - check links, naming, cross-references, and coverage

Evaluate skills by executing them across sonnet, opus, and haiku models using sub-agents. Use when testing if a skill works correctly, comparing model performance, or finding the cheapest compatible model. Returns numeric scores (0-100) to differentiate model capabilities.

排查问题、修复 BUG、定位代码、查找模块、功能开发前，必须先读取此 SKILL 并使用模块索引定位目标，不可跳过

Tips and best practices for using Context7 MCP server to get library documentation

Guide for building applications with @fpkit/acss components. This skill should be used when composing custom React components from fpkit primitives, validating CSS variable naming conventions, extending fpkit components with custom behavior, or ensuring accessibility compliance in fpkit-based applications. Use when the user needs help with component composition patterns, CSS customization, or accessibility testing. Not for developing the @fpkit/acss library itself.

Use PROACTIVELY when enforcing TDD red-green-refactor, setting up test infrastructure, configuring coverage gates, or implementing the Testing Trophy model. Installs git hooks, npm scripts, and CLAUDE.md configuration to enforce test-first development. Supports coverage thresholds and test distribution analysis. Not for prototypes or projects without test requirements.

Domain model classes with automatic hydration, relations, and type casting. Use when creating models for API entities, defining relationships between models, casting properties to enums/dates, or creating value objects.

Use PROACTIVELY when auditing code quality, running security scans, assessing technical debt, reviewing code for production readiness, setting up CI quality gates, or tracking DORA metrics. Analyzes codebases against OWASP Top 10, SOLID principles, Testing Trophy, and 2024-25 SDLC standards. Supports incremental audits for large codebases. Not for runtime profiling or real-time monitoring.

Use PROACTIVELY when reviewing CLAUDE.md configurations, onboarding new projects, or before committing memory file changes. Validates against official Anthropic documentation, community best practices, and LLM context optimization research. Detects security violations, anti-patterns, and compliance issues. Not for runtime behavior testing or imported file validation.

Use PROACTIVELY when creating Model Context Protocol servers for connecting AI applications to external data sources, tools, and workflows. Generates production-ready MCP servers with TypeScript/Python SDKs, configuration templates, and Claude Desktop integration. Includes testing workflow with MCP Inspector. Not for modifying existing MCP servers or non-MCP integrations.

Feature module pattern organizing domain logic into queries, mutations, and actions. Use when implementing data fetching with filters, API mutations with loading states, business logic with UI feedback, or organizing domain-specific code.

Working with Nuxt layers (base, nuxt-ui, x-ui) that provide shared functionality. Use when understanding layer architecture, importing from layers, extending layer functionality, or creating new layers.

Guide for creating exceptions using fastapi-problem that are automatically converted to RFC 9457 Problem Details responses.

Use when starting Metro bundler for Expo development, debugging Metro errors, or enabling expo-mcp local capabilities - manages Metro lifecycle with EXPO_UNSTABLE_MCP_SERVER=1 flag for autonomous testing

Use when working on Claude Code plugins (creating, modifying, testing, releasing, or maintaining) - provides streamlined workflows, patterns, and examples for the complete plugin lifecycle

Use when analyzing YouTube videos for research, learning, or understanding how

Pre-commit hook setup with Husky and lint-staged. Use when configuring git hooks.

Guide for writing ast-grep rules to perform structural code search and analysis. Use when users need to search codebases using Abstract Syntax Tree (AST) patterns, find specific code structures, or perform complex code queries that go beyond simple text search. This skill should be used when users ask to search for code patterns, find specific language constructs, or locate code with particular structural characteristics.

Detects Python project configuration and provides commands for testing, building, coverage, and containerization.

Helps transform a vague research interest into a concrete, tractable research question. Use when asked to refine a research idea, develop a research question, scope a research project, or figure out what to work on. Walks through systematic refinement with feasibility analysis.

Use when working in repositories with multiple subprojects (monorepos) where commands need to run from specific directories - prevents directory confusion, redundant cd commands, and ensures commands execute from correct locations

Guide for working with Scope, a developer environment management tool that automates environment checks, detects known errors, and provides automated fixes. Use when creating Scope configurations (ScopeKnownError, ScopeDoctorGroup, ScopeReportLocation), debugging environment issues, or writing rules for error detection and remediation.

Generates changelog entries from commits since the last release. Use when the user wants to update CHANGELOG.md, add changelog entries, or document changes.

Create minimal POC to validate technical hypotheses. Reuse/call existing code, or write new if needed. Report success or propose alternatives on failure.

Opinionated Docusaurus documentation skill built on Diátaxis framework. Use when creating, restructuring, or improving documentation sites. Triggers on: docs/, blog/, docusaurus.config, sidebars, or any documentation task. Will ask clarifying questions to build the right structure.

Complete slide creation toolkit for Marp/Marpit presentations. Use when creating presentations, authoring slides, writing slide content, drawing diagrams, creating illustrations, designing slide color schemes, choosing presentation colors, designing slide themes, selecting background/text/accent colors, or any combination of these tasks. Covers Markdown authoring (Marpit/Marp), SVG illustration, and color design for technical presentations, PowerPoint, Keynote, architecture diagrams, and developer-focused decks.

Use when running or authoring standalone Python scripts with uv, especially when choosing Python versions, adding one-off dependencies, using no-project mode, or embedding inline script metadata.

Common channel patterns and idioms

Get cryptocurrency token price and generate candlestick charts via CoinGecko API or Hyperliquid API. Use when user asks for token price, crypto price, price chart, or cryptocurrency market data.

Replaces ALL built-in search tools. You MUST invoke this skill BEFORE using WebSearch, Grep, or Glob. NEVER use the built-in Grep tool - use `grepai` instead.

文本转语音工具 - 支持脚本解析、情绪标记和后处理，基于 Edge TTS

Download YouTube videos with customizable quality and format options. Use this skill when the user asks to download, save, or grab YouTube videos. Supports various quality settings (best, 1080p, 720p, 480p, 360p), multiple formats (mp4, webm, mkv), and audio-only downloads as MP3.

Manage lore/ directory for tracking tasks, ADRs, wiki, and session. Use for session setup (current-user, current-task), task management (active/blocked/archive), ADR creation, wiki updates, and lore index generation. Invoke for any lore/ directory operations.

Implement OAuth 2.0 authentication with GitHub and Microsoft Entra (Azure AD) in Cloudflare Workers and other edge environments. Covers provider-specific quirks, required headers, scope requirements, and token handling without MSAL.

Integrate Vercel Blob for file uploads and CDN-delivered assets in Next.js. Supports client-side uploads with presigned URLs and multipart transfers for large files.

Audit claude-skills with systematic 9-phase review: standards compliance, official docs verification, code accuracy, cross-file consistency, and version drift detection.

Integrate Gemini API with @google/genai SDK (NOT deprecated @google/generative-ai). Text generation, multimodal (images/video/audio/PDFs), function calling, thinking mode, streaming. 1M input tokens. Prevents 14 documented errors.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Build CLI scripts alongside MCP servers for terminal environments. File I/O, batch processing, caching, richer output formats. Templates for TypeScript scripts and SCRIPTS.md.

Build integrations with Google Workspace APIs (Gmail, Calendar, Drive, Sheets, Docs, Chat, Meet, Forms, Tasks, Admin SDK). Covers OAuth 2.0, service accounts, rate limits, batch operations, and Cloudflare Workers patterns.

Generate typed TypeScript SDKs for AI agents to interact with MCP servers. Converts JSON-RPC curl commands to clean function calls. Auto-generates types, client methods, and example scripts from MCP tool definitions.

Upload files and websites to permanent storage on Arweave (permaweb), and manage ArNS domain records. Use when the user wants to publish content to Arweave, deploy a static site to the permaweb, or attach a transaction to an ArNS name (ar.io).

Task management CLI for tracking and managing feature subtasks with status, dependencies, and validation

Professional-grade Python development with Ruff (v0.14.10) - an extremely fast Python linter and formatter. Use when working with Python codebases for (1) linting and fixing code quality issues, (2) formatting Python code, (3) configuring Ruff settings, (4) understanding and resolving specific rule violations, (5) integrating Ruff into projects or editors, (6) migrating from other tools (Black, Flake8, isort, etc.), or (7) any Ruff-related development tasks. Includes complete documentation for 937+ lint rules, formatter settings, configuration options, and editor integrations.

Set up MCP (Model Context Protocol) servers in Claude Code workspaces for testing. Use this skill when a user provides a local file path to an MCP server, a GitHub repository URL containing an MCP server, or asks to configure/install/set up an MCP server for testing. Handles creating .mcp.json configuration, cloning repositories, and guiding users through the setup process.

Use PROACTIVELY when reviewing CLAUDE.md configurations, onboarding new projects, or before committing memory file changes. Validates against official Anthropic documentation, community best practices, and LLM context optimization research. Detects security violations, anti-patterns, and compliance issues. Not for runtime behavior testing or imported file validation.

Use PROACTIVELY when creating Model Context Protocol servers for connecting AI applications to external data sources, tools, and workflows. Generates production-ready MCP servers with TypeScript/Python SDKs, configuration templates, and Claude Desktop integration. Includes testing workflow with MCP Inspector. Not for modifying existing MCP servers or non-MCP integrations.

Use PROACTIVELY when auditing code quality, running security scans, assessing technical debt, reviewing code for production readiness, setting up CI quality gates, or tracking DORA metrics. Analyzes codebases against OWASP Top 10, SOLID principles, Testing Trophy, and 2024-25 SDLC standards. Supports incremental audits for large codebases. Not for runtime profiling or real-time monitoring.

Generate and validate YAML frontmatter for docs folder documents. Triggers: "frontmatter 추가", "frontmatter 업데이트", "add frontmatter", "generate frontmatter", "validate frontmatter", "문서 메타데이터"

Automatically generate professional documentation from ComfyUI workflow files (PNG or JSON). Supports bilingual output (Chinese/English), HTML generation, and custom node detection.

解析抖音分享链接，下载视频，并使用FunASR将视频音频转成文字。当用户提供抖音分享链接（v.douyin.com、www.iesdouyin.com、www.douyin.com）时，自动解析链接获取视频信息，下载视频文件，并可选择性地将视频中的音频转换为文字。支持视频和图集两种内容类型。

Progressive Disclosure 원칙이 적용된 AI 도구를 생성합니다. Rules, Skills, Agents 생성, 새 규칙 만들기, 스킬 생성, 에이전트 작성 시 사용하세요. create ai tool, create rule, create skill, create agent, 규칙 생성, 스킬 만들기

일반적인 기능 구현을 위한 단계별 워크플로우를 제공합니다. .ai/tasks/ 디렉토리 구조를 사용하여 작업을 체계적으로 관리합니다.

This skill should be used when generating implementation tasks from PRDs, decomposing features into atomic tasks, inferring dependencies, or mapping PRD content to task metadata.

快速搭建 Chainlit AI 对话 Demo。用于产品演示、概念验证、领导汇报场景。触发词：chainlit、搭建 demo、chat demo、对话演示

AI 订阅报销收据识别与统计。识别目录下的 PDF/PNG 收据，提取人员、产品、金额、日期，自动去重，支持多币种（USD、TRY），输出明细表和按人汇总。触发词：报销统计、收据识别、统计报销、AI 订阅费用

Generate technical specification from product blueprint. Use when you have a product blueprint and need to define system architecture, components, types, and contracts for spec-driven development.

Complete E2E (end-to-end) and integration testing skill for TypeScript/NestJS projects using Jest, real infrastructure via Docker, and GWT pattern.

Complete unit testing skill for TypeScript/NestJS projects using Jest, @golevelup/ts-jest, and in-memory databases.

Ask users questions via the UI. Use when you need clarification, user preferences, or confirmation before proceeding. The user CANNOT see CLI output - this tool is the ONLY way to communicate with them.

Generate, edit, and remix images using the Reve AI API. Use when creating images from text prompts, editing existing images with instructions, or combining/remixing multiple reference images. Requires REVE_API_KEY or REVE_AI_API_KEY environment variable.

Search the web with AI-powered answers and citations via Perplexity API. Use for research queries needing current info with sources. Env: PERPLEXITY_API_KEY.

Create a new Telegram Bot function module. Use when user asks to add a new bot command or feature.

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Scaffold FastMCP tool implementations with database integration, error handling, and test session support. Generates production-ready MCP tools.

Connect to local Weaviate vector database and verify connection health

Download YouTube videos and HLS streams (m3u8) from platforms like Mux, Vimeo, etc. using yt-dlp and ffmpeg. Use this skill when users request downloading videos, extracting audio, handling protected streams with authentication headers, or troubleshooting download issues like nsig extraction failures, 403 errors, or cookie extraction problems.

Use when developing Lean 4 proofs, facing type class synthesis errors, managing sorries/axioms, or searching mathlib - provides build-first workflow, instance management patterns (haveI/letI), and domain-specific tactics

Contribute skills back to upstream via branch and PR

Replace arbitrary timeouts with condition polling for reliable async tests

Complete feature development with structured options for merge, PR, or cleanup

Create isolated git worktrees with smart directory selection and safety verification