AI Skills Hub - Browse 180,000+ Agent Skills

Use when setting up global hooks for Claude Code enforcement. Load when ~/.claude/hooks/ is missing or incomplete, or when explicitly requested. Installs 7 project-agnostic hooks (state transitions, git hygiene, outcome tracking). Run once per machine.

Create OpenCode plugins using @opencode-ai/plugin SDK. Use when user wants to BUILD a plugin in .opencode/plugin/ or ~/.config/opencode/plugin/ - for custom tools, event hooks, LLM parameter control, auth providers, or tool execution interception. DO NOT use when modifying OpenCode source code (packages/plugin, packages/opencode, etc.) or working on OC internals - those are core development, not plugin creation.

Find, install, and configure Model Context Protocol (MCP) servers for OpenCode. Use when user asks about finding MCP servers, installing them, configuring OAuth, or troubleshooting MCP issues.

Expert en création de scripts de test et vérification E2E. ACTIVE AUTOMATIQUEMENT quand: - Une nouvelle fonctionnalité est implémentée - Un bug est corrigé (régression test) - L'utilisateur demande de tester - Avant déploiement en production Crée: scripts de vérification Node.js, tests DB, tests handlers. Garantit: pas de régression, comportement attendu validé.

Expert en prévention d'erreurs et détection de patterns dangereux. ACTIVE AUTOMATIQUEMENT quand Claude: - Écrit du code JavaScript/Node.js - Modifie des handlers Discord.js - Écrit des requêtes SQL - Travaille sur du code multi-serveur (guild_id) Détecte: timeouts Discord, oubli guild_id, routing incomplet, requêtes SQL dangereuses. DOIT être consulté AVANT chaque modification de code.

Expert PostgreSQL pour architecture multi-serveur (guild_id). ACTIVE AUTOMATIQUEMENT quand Claude: - Écrit des requêtes SQL (SELECT, INSERT, UPDATE, DELETE) - Crée ou modifie des tables - Travaille sur des migrations - Manipule des données joueurs/serveurs Garantit: isolation guild_id, requêtes sûres, migrations versionnées. CONSULTE DATABASE-SCHEMA.md avant toute modification.

This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.

Development guidelines and code architecture for HiWonder LanderPi robot project. This skill should be used when creating new features, adding validation tests, writing deployment scripts, or modifying existing code. Ensures consistency with established patterns for CLI tools, remote execution, module design, and ROS2 integration.

Referência dos **endpoints** da API de demos: Blueprint em `/api/demos`, rotas em `backend/routes.py`.

Initial project setup for goal coaching system. Use when user says "set up my project", "configure my coaching project", "initialize my goals", or when starting a fresh coaching project with no existing Project-Goals.md. Guides user through conversational setup (one question at a time), generates Project-Goals.md artifact, and introduces daily/weekly workflow trigger phrases.

Framework for starting new daily chat with gentle context loading from previous day's summary. Use when user says "good morning", starts new chat with minimal prompt, or explicitly requests morning brief. Loads yesterday's summary and generates scannable brief. Optimized for low cognitive load during morning wakeup. Extend with personal metrics and protocols.

Solve GitHub issues end-to-end using a disciplined reproduce-assess-fix-verify loop. Use when asked to "solve issue X", "fix issue X", or given a GitHub issue URL

Automates complete DEV deployment (commit, push, build, deploy, verify). Use when deploying to development environment, pushing to dev branch, or when user mentions deploy, staging, or development server.

Audit claude-skills repository documentation with systematic 9-phase review: standards compliance, official docs verification via Context7/WebFetch, code examples accuracy, cross-file consistency, and version drift detection. Auto-fixes unambiguous issues with severity classification. Use when: investigating skill issues, major package updates detected (e.g., v1.x → v2.x), skill not verified >90 days, before marketplace submission, or troubleshooting outdated API patterns, contradictory examples, broken links, version drift.

Create maintainer-friendly pull requests for open source projects with clean code submissions and professional communication. Prevents 16 common mistakes that cause PR rejection. Use when: contributing to public repositories, submitting PRs to community projects, migrating from contributor to maintainer workflows, or troubleshooting PR rejection, working on main branch errors, failing CI checks, or personal artifacts in commits.

Generate EnergyPlus building simulations from natural language descriptions or building images. Use when user asks to 'create building simulation', 'generate IDF', 'simulate X-story building', provides building floor plans, 3D models, or describes buildings like 'a 3-story office building in Shenzhen'.

创建规范化的小说工程文件夹结构，包含数据库、章节、进度管理等功能的完整写作项目管理体系。当用户需要开始新的小说写作项目时使用，自动生成标准化的目录结构和模板文件。

Map all links from a starting webpage recursively up to 2 hops deep (depth 0, 1, 2 only - depth 3 is descoped), check link accessibility, and generate a sitemap markdown file. Use when the user wants to preview what pages would be extracted, discover site structure, or identify dead links before running extract-webpage-content.

Browser automation via server.ts + cmd.ts. Use for screenshots, web scraping, form filling, navigation. Token-efficient alternative to MCP.

keywords: - webapp-testing - automation - biomedical measurable_outcome: execute task with >95% success rate. ---"

keywords: - gh-fix-ci - automation - biomedical measurable_outcome: execute task with >95% success rate. ---"

Metagenome assembly from long reads using metaFlye and metaSPAdes with binning strategies. Use when reconstructing genomes from microbial communities, recovering metagenome-assembled genomes (MAGs), or resolving strain-level variation in complex samples.

Build iOS projects and diagnose build failures.

> **文档性质**: 领域综述 (Domain Survey) > **适用范围**: 使用 gh-aw 创建和运行 AI Agent 工作流的开发者 > **官方仓库**: <https://github.com/githubnext/gh-aw> > **最后更新**: 2026-01-04

Run Python test suites using uv with offline mode and calculated timeouts. This skill should be used when executing pytest-based tests to avoid network issues, prevent hanging tests, and ensure reliable test execution in uv-managed Python projects.

Generate or edit images using Google Gemini API through the nanobanana tool.

Playwright MCP setup and usage for browser automation, end-to-end UI testing, and retrofitting Playwright suites into existing projects. Use when configuring Claude Code MCP access, authoring Playwright tests, diagnosing UI bugs with automated browser flows, or adding Playwright test workflows/CI to a repo.

Fetches and analyzes Azure DevOps work items, tasks, user stories, bugs, and features using Azure CLI. Use when user mentions ADO, Azure DevOps, work items, task IDs (like #72382), ticket numbers, user stories, bugs, sprint items, acceptance criteria, or needs to query/update DevOps boards.

Add files and frameworks to Xcode projects programmatically

Pre-commit validation ensuring lint and tests pass

Generate iOS app demo videos autonomously using UnaMentis TTS and Shotstack.

This skill should be used when the user asks to "set up CI", "configure GitHub Actions", "create a workflow", "pin actions", "use ratchet", "set up Claude code review", "configure AWS OIDC", "deploy with tickforge", or mentions GitHub Actions, CI/CD pipelines, or workflow security. Provides Uptick's security-first GitHub Actions patterns.

Go and Rust systems programming best practices for performance-critical, concurrent, and safe applications. Covers error handling, ownership/borrowing (Rust), context and goroutines (Go), testing patterns, and production deployment. Use when working with .go, .rs files, Cargo.toml, go.mod, or when asking about Go or Rust development.

Bash scripting best practices for production-grade scripts, CLI tools, and Makefiles. Covers strict mode, error handling, portability, performance patterns, and argument parsing. Use when working with .sh files, Makefiles, shell scripts, or when asking about Bash, shell scripting, CLI design, or command-line tools.

This skill should be used when generating images from text prompts using AI image generation APIs. Supports Google Gemini, OpenAI DALL-E 3, Stability AI, and Replicate. API keys are stored securely in environment variables and excluded from distribution.

Transcribe audio and video files to text using Volcengine Doubao ASR Flash API. Use when converting audio recordings, podcasts, meetings, interviews, or videos to text. Supports local files (audio/video), URLs, and auto video-to-audio conversion via FFmpeg.

Manage inbox email. Uses the inbox script and stores metadata (ids) to open or archive messages later.

Guide for creating and working in Git worktrees with a consistent workflow. Use when a user wants to run a task in a separate worktree, create or clean up worktrees, migrate a repo into a main/worktrees layout, or implement work based on an issue ID using GitHub/GitLab tooling.

Import DevExpert testimonials from Google Sheets (gog) or pasted TSV lists, format text with line breaks, crop profile images to 400x400, copy them to src/assets/testimonials, update src/data/testimonials.json, and optionally update AI Expert IDs in src/pages/cursos/expert/ai.astro. Use when adding new testimonials or processing images.

ONLY trigger this skill when the user EXPLICITLY asks for MCP-based testing: **Required triggers (ALL must mention "MCP" explicitly):** - "test connector with mcp" - "test mcp connector" - "test [provider] with mcp" - "use mcp to test [provider]" - "run mcp connector test" - "mcp test for [provider]" **DO NOT trigger for:** - Generic "test the connector" requests (use stackone run / test_actions instead) - "test [provider]" without explicit MCP mention - Regular validation or testing requests - Any testing that doesn't explicitly mention MCP This skill builds a REAL agent with Claude Agent SDK that sends natural language prompts to evaluate if action descriptions are agent-friendly. It's more intensive than regular testing and should only be used when explicitly requested.

Updates existing skills with version management, creates migration scripts, and provides rollback capabilities. Use when updating skills, managing versions, or creating migration paths between skill versions.

Use the Mixpanel MCP server for analytics. Triggers on mentions of Mixpanel MCP tools, MCP resources, analytics queries via MCP, segmentation, funnels, retention, cohort_comparison, product_health_dashboard, ask_mixpanel, diagnose_metric_drop, guided_analysis, fetch_events, or SQL queries on local DuckDB data.

ArduPilot Rover vehicle development. Use when working with: ground vehicles, boats, balance bots, flight modes (Manual, Auto, Guided, RTL, SmartRTL, etc.), motor control (AP_MotorsUGV), waypoint navigation (AR_WPNav), steering/throttle control, sailboat features, RC input handling, or adding new Rover functionality.

Expert guidance for developing with ArduPilot's submarine/ROV platform.

This skill provides guidance for developing and modifying the ArduPilot AntennaTracker firmware.

ArduPilot sensor libraries (AP_InertialSensor, AP_GPS, AP_Compass, AP_Baro, RangeFinder, AP_Airspeed, AP_OpticalFlow, AP_BattMonitor, AP_Proximity, AP_AHRS, and more). Use when: (1) Reading sensor data in ArduPilot code (2) Adding new sensor drivers or backends (3) Understanding frontend/backend architecture (4) Debugging sensor health, calibration, or data flow (5) Working with peripheral sensors (ESC telemetry, RPM, temperature, etc.)

Expert guidance for developing with ArduPilot's blimp/airship platform.

An agent that codes tasks in BDD-style. Automatically does not commit.

Server-side LinkedIn Conversions API implementation using Stape and Google Tag Manager. Use when setting up LinkedIn CAPI tracking, configuring LinkedIn server-side conversions, implementing LinkedIn conversion tracking, generating LinkedIn access tokens, creating LinkedIn conversion rules, or debugging LinkedIn CAPI events. Triggers on "LinkedIn CAPI", "LinkedIn conversions API", "LinkedIn server-side tracking", "li_fat_id", "LinkedIn conversion rule", "LinkedIn sGTM setup".

Run benchmark and analyze PDF parsing performance

Development skill for CaseMark's Smart Redaction Tool - an intelligent document redaction application with two-pass PII detection combining regex patterns and AI-powered semantic analysis. Built with Next.js 14, pdf.js/pdf-lib, and Case.dev LLMs. Use this skill when: (1) Working on the redaction-tool codebase, (2) Adding or modifying regex patterns, (3) Implementing AI detection features, (4) Building PDF export functionality, or (5) Adding new PII types.

使用 Playwright 与本地 Web 应用交互并进行测试的工具包。支持验证前端功能、调试 UI 行为、捕获浏览器截图以及查看浏览器日志。

XDG Base Directory Specification に基づいた dotfiles の管理を支援するスキル。以下の場合に使用：(1) dotfiles を XDG 準拠のディレクトリ構成に移行したい、(2) 新規に XDG 準拠の設定ファイルを作成したい、(3) アプリケーションの XDG 対応方法を知りたい、(4) ホームディレクトリをクリーンに保ちたい。dotfiles、設定ファイル、XDG、$HOME のクリーンアップに関する質問でトリガー。

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

全面的文档创建、编辑和分析，支持跟踪更改、注释、格式保留和文本提取。当 Claude 需要使用专业文档（.docx 文件）时用于：（1）创建新文档，（2）修改或编辑内容，（3）处理跟踪更改，（4）添加注释，或任何其他文档任务

Analyze staged/unstaged changes using Git only and generate a Conventional Commits draft message (optional emoji); suggest splitting when changes look mixed or large; keep local Git hooks enabled by default (use --no-verify to skip). Use when the user runs $git-commit ... or asks for Git-only Conventional Commit message generation.

Safely identify and clean up merged or stale Git branches with a dry-run-first workflow; supports custom --base refs, protected branch patterns via git config, and optional remote branch deletion. Use when the user runs $git-clean-branches ... or asks to prune merged/stale branches (treat $git-cleanBranches as a legacy alias mention).

Manage Git worktrees under ../.atmu/{project-name}/ with add/list/remove/prune/migrate; infer the main repo path even when run inside a worktree and use absolute paths to avoid nested directories; default to branching from main/master; copy gitignored .env/.env.* (excluding .env.example) into new worktrees; migrate uncommitted changes via stash. Use when the user runs $git-worktree ... or asks about Git worktrees / parallel branches / isolated workspaces / migrating uncommitted changes.

Generate iOS app icons for Ential apps. Creates 180x180 PNG icons with solid orange background and white Lucide icons using PIL. No alpha channel to prevent iOS rendering issues.

Generate publication-quality PDF annual reports with professional layouts, images, icons, and branding.

MacのChromeにインストールされているTampermonkey userscriptの一覧を取得し、スクリプト名、有効/無効状態、バージョン、作者などのメタデータを表示する。ユーザーが「Tampermonkeyのスクリプトを確認して」「userscriptの一覧を見せて」などのリクエストをした際に使用する。

Plans dashboard server with progress tracking and timeline visualization.

Background HTTP server rendering markdown files with calm, book-like reading experience.

Generate well-formatted, conventional commit messages by analyzing git diff and staged changes. Use when the user asks to create commit messages, analyze changes for commits, generate changelog entries, or needs help writing descriptive git commit logs. Supports both conventional commit format and customizable templates.

Start, stop, or check status of the Claudia Gateway service for messaging integrations.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

AutoRAG는 RAG(Retrieval-Augmented Generation) 파이프라인을 자동으로 최적화하는 AutoML 도구입니다. 문서 파싱, 청킹, QA 데이터 생성, RAG 파이프라인 최적화, 배포를 지원합니다. 사용자가 RAG 시스템을 구축하거나 최적화할 때 이 스킬을 활용하세요.

Run automated tests for the to-do application. Supports backend (pytest), frontend (Jest/Vitest), and E2E tests (Playwright). Integrates with TDD workflow and .specify/ framework.

Set up development environment for a specific phase of the to-do application. Installs dependencies, creates configuration files, and initializes databases. Perfect for onboarding or switching between phases.

Start the Next.js frontend application for the to-do app. Supports both Phase 2 (Full-Stack) and Phase 3 (Chatbot) frontends with hot reload for development.

Verify development environment setup for the to-do application. Checks prerequisites, dependencies, configuration files, database connectivity, and service health. Use after setup-phase to ensure everything is ready.

Start the FastAPI backend server for the to-do application. Supports both Phase 2 (Next.js) and Phase 3 (Chatbot) backends. Automatically detects the phase and starts the appropriate server.

データ分析・可視化・レポート作成。pandas、SQL、BigQuery、スプレッドシート操作、統計分析、グラフ作成。「データ分析」「SQL」「BigQuery」「pandas」「集計」「可視化」「レポート」に関する質問で使用。

Fetch Bugsnag error event data directly from the Bugsnag API. Use when you need to analyze production errors, crashes, or exceptions tracked in Bugsnag.

This skill should be used when the user asks to "test memex-cli", "test code-with-codex", "test ux-design-gemini", "test /multcode", "run component tests", "validate workflow components", "run integration tests", or "verify plugin functionality". Provides comprehensive testing framework for coding-workflow plugin components.

This skill should be used when you need to know what members, methods, or extensions are available on Kotlin types. It queries autocomplete metadata generated by the kotlin-autocomplete-gradle-plugin.

Use before completing any task that modified code in `src/` or fixtures in `tests/conftest.py` - ensures registries are valid and up-to-date before marking work complete.

Use when creating or modifying functions in `src/` - ensures all code has proper Google-style docstrings and reminds to regenerate the service registry.

Design command-line interface parameters and UX: arguments, flags, subcommands, help text, output formats, error messages, exit codes, prompts, config/env precedence, and safe/dry-run behavior. Use when you’re designing a CLI spec (before implementation) or refactoring an existing CLI’s surface area for consistency, composability, and discoverability.

Interact with Supabase projects via the Supabase CLI. Manage databases, run SQL queries, handle migrations, deploy Edge Functions, manage storage, and work with branching. Use when the user mentions Supabase, needs database operations, wants to deploy serverless functions, or work with Postgres databases hosted on Supabase.

当需要高速下载大文件、使用断点续传或配置下载代理时,或者资源下载失败，调用 aria2c 工具。

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Implement input validation patterns for F# API boundaries. Use when validating user input, API requests, or form data. Ensures early validation with clear error messages using Result types. Creates code in src/Server/Validation.fs.

Implement F# backend using Giraffe + Fable.Remoting with proper separation: Validation → Domain (pure logic) → Persistence (I/O) → API. Use when implementing server-side logic, API endpoints, or business rules. Ensures validation at boundaries, pure domain functions, and proper error handling with Result types. Creates code in src/Server/ files: Validation.fs, Domain.fs, Persistence.fs, Api.fs.

Development skill for CaseMark's discovery-desktop application - a legal e-discovery platform for document upload, OCR processing, and semantic search. Built with Next.js 16, React 19, Drizzle ORM, and Case.dev APIs. Use this skill when: (1) Working on or extending the discovery-desktop codebase, (2) Integrating with Case.dev APIs for OCR, semantic search, or vault management, (3) Modifying the database schema or queries, (4) Building e-discovery workflow features, or (5) Deploying/configuring the application.

Implement RemoteData pattern for explicit async state handling in Elmish frontend. Use when adding API calls, form submissions, or any async operation. Ensures all loading/error states are handled explicitly, preventing impossible UI states.

Create or update Infogroove infographic templates and sample data files, then render SVG outputs. Use when a user asks to generate/modify infogroove `def.json` + `data.json`, create new infographic directories, or render SVGs from Infogroove templates.

Review an in-repo specification pack and produce a prioritized backlog of architectural spike questions (design/research/prototyping) for a Python service on Google Cloud (Cloud Functions gen2 / Cloud Run) and LLM integrations. Use when you must identify gaps/risks before implementation. Output must be written to questions/arch_spikes.md (overwrite) and the chat response must only confirm the file path and spike counts.

Generate structured task completion reports in two synchronized formats - a concise chat summary and a detailed documentation file. Use this skill when completing tasks that require formal documentation, audit trails, or reproducible records of work performed. Particularly useful for specification-driven development, API implementation, or any workflow requiring both user-facing summaries and comprehensive technical documentation.

Manage n8n workflows and automations via API. Use when working with n8n workflows, executions, or automation tasks - listing workflows, activating/deactivating, checking execution status, manually triggering workflows, or debugging automation issues.

Use when given a GitHub issue number and base branch to implement end-to-end

Generate, deploy, and manage AI research reports on prism.qnury.es. Reports are deployed as static sites with both human-readable (HTML) and AI-readable (Markdown) formats. Use when conducting research that needs to be published, when reading existing reports, or when managing the report archive.

Toolkit for interacting with and testing SahayakAI web applications using Playwright. Supports verifying educational flows (Quizzes, Micro-lessons), debugging UI behavior, and capturing browser state.

Generate slide images and final PDF/PPTX from v2 styled prompts (prompts/styled/*.md), storing intermediates in artifacts/<deck>/work/. Use when the user asks to render/generate/export slides from a Styled PROMPT into images/PDF/PPTX.

Read and manage email via IMAP (ProtonMail Bridge, Gmail, etc.). Check for new/unread messages, fetch content, search mailboxes, and mark as read/unread. Works with any IMAP server including ProtonMail Bridge.

Run Docker-based Agent Society Protocol integration test. Creates N agent containers with real network communication, establishes social graph relationships via HTTP API, deploys AGENT ERC20 token on local Anvil, and verifies event exchange between containers. Use when testing multi-agent communication with real Docker networking, container orchestration, or production-like agent deployment. Triggers on "docker agent test", "containerized agent test", "docker integration test", "/docker-agent-society-test", or "run docker agent test".

Query and audit Google Ads accounts via API. Use for conversion tracking analysis, campaign performance, ROAS optimization, and SEM audits. Enforces verification methodology: NEVER draw conclusions from configuration alone—always cross-reference against actual metrics behavior.

Expert guidance for creating, writing, and refining Claude Code Skills. Use when working with SKILL.md files, authoring new skills, improving existing skills, or understanding skill structure and best practices.

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Generate animated GIF/WebM videos of graph visualizations from natural language descriptions