AI Skills Hub - Browse 180,000+ Agent Skills

Use when creating new golem-powers skills, editing existing skills, or verifying skills work before deployment

GitHub リポジトリからコードを検索し、関連するコードの実装を取得するスキル。 別リポジトリのコードコンテキストが必要な場合に使用。 以下の場面で使用: - APIエンドポイントの実装を確認したい時 - リクエスト/レスポンスの型定義を探したい時 - 関連するバックエンドコードを検索したい時 - フロントエンドのコンポーネント実装を確認したい時 - テストコードを検索したい時 「バックエンド検索」「フロントエンド検索」「API実装確認」「コード検索」「gh search」などでも呼び出し可能。

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.

生成Draw.io图表XML文件,可直接在diagrams.net中打开和编辑。当用户请求创建流程图、思维导图、架构图、组织架构图、甘特图、时间轴或其他可视化图表时使用。支持所有标准Draw.io形状、样式和连接。

Nuxt Server Routes 後端開發技能。包含 API 響應格式、 錯誤處理（return 非 throw）、Zod 驗證、JWT 認證。 開發 /nuxt-api/* 端點時使用此技能。

蓝湖应用开发技能，用于构建和管理蓝湖相关的应用功能

使用 Chrome CDP 抓取任意 URL 并转换为 Markdown。支持两种模式——页面加载时自动捕获，或等待用户信号（用于需要登录的页面）。当用户想要将网页保存为 Markdown 时使用。

Guidelines for creating and managing Pull Requests in this repo

Turborepo monorepo build system guidance. Triggers on: turbo.json, task pipelines, dependsOn, caching, remote cache, the "turbo" CLI, --filter, --affected, CI optimization, environment variables, internal packages, monorepo structure/best practices, and boundaries.

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

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Builds single-container deployments with PostgreSQL, Nginx, and Supervisor for the Luxia e-commerce platform. Use when: modifying Dockerfile, docker-compose.yml, nginx.conf, supervisord.conf, or deployment scripts.

PostgreSQL database design, queries, and management for INVOOPAY Use when: designing schemas, writing complex queries, optimizing database performance, managing migrations, or debugging database issues

Serve Jekyll site accessible via VPN tunnel

Bootstrap the Home Assistant plugin environment. Use AUTOMATICALLY when invoking any /ha-* command or when needing to run validation scripts. Sets up the plugin path resolver for script execution.

Upload markdown files or folders to Readwise Reader with metadata extraction and error handling

Send messages via Telegram using Telethon library with user (QR login) or bot token authentication. Use when Claude needs to: (1) send notifications or messages to Telegram users/channels, (2) set up a Telegram session for programmatic access, (3) integrate Telegram messaging into workflows. Supports both personal accounts (QR code auth) and bot accounts (token auth).

Interface for MCP (Model Context Protocol) servers via CLI. Use when you need to interact with external tools, APIs, or data sources through MCP servers.

Activate for marketing analytics, KPI tracking, reporting dashboards, attribution analysis, and performance optimization. Use when analyzing campaign data, creating reports, or measuring marketing ROI.

Build 3D web apps with Three.js (WebGL/WebGPU). 556 searchable examples, 60 API classes, 20 use cases. Actions: create 3D scene, load model, add animation, implement physics, build VR/XR. Topics: GLTF loader, PBR materials, particle effects, shadows, post-processing, compute shaders, TSL. Integrations: WebGPU, physics engines, spatial audio.

View plans dashboard with progress tracking and timeline visualization. Use for kanban boards, plan status overview, phase progress, milestone tracking, project visibility.

Search library/framework documentation via llms.txt (context7.com). Use for API docs, GitHub repository analysis, technical documentation lookup, latest library features.

SEO audits, keyword research with ReviewWeb.site API (keyword ideas, difficulty, traffic, backlinks), on-page optimization, technical SEO, programmatic SEO (pSEO), JSON+LD schema, Google Search Console API integration. Activate for search optimization, meta tags, sitemap, Core Web Vitals. Used by seo-specialist, attraction-specialist, content-creator agents.

Generate images via Nano Banana with 129 curated prompts. 3 modes: search (best match), creative (remix), wild (experimental). Actions: generate for banners, portraits, infographics, products. Styles: Ukiyo-e, Bento grid, cyberpunk, cinematic, vintage patent.

Git worktree workflow with tmux integration for parallel Claude Code sessions

Design server-authoritative REST and real-time API contracts for a multiplayer hacking game, focused on commands, events, and deterministic state.

Transform YouTube videos into beautifully formatted ebook articles with transcripts

Search and query labeled entities including exchanges, funds, protocols, and whales. Get entity categories, search for labeled addresses, and retrieve entity information. Use when user asks about exchange wallets, fund tracking, or labeled addresses.

Query DeFi positions, protocol exposure, and liquidity pool positions on EVM chains. Get summary of all DeFi protocols used by a wallet, detailed positions per protocol, and portfolio allocation across DeFi platforms. Use when user asks about DeFi, liquidity pools, yield farming, or protocol exposure.

Manages Etsy shop operations (listings, inventory, receipts/orders, shop data, taxonomy, and webhooks) via Etsy Open API v3 with OAuth 2.0 + PKCE and rate-limit-aware request handling.

Explore and document existing codebases at various depths

View and query the documentation knowledge graph

Create OpenCode plugins using the @opencode-ai/plugin SDK. Use for building custom tools, event hooks, auth providers, or tool execution interception. Use proactively when developing new plugins in .opencode/plugin/ or ~/.config/opencode/plugin/. Examples: - user: "Create a plugin to block dangerous commands" → implement tool execution before hook with blocking logic - user: "Add a custom tool for jira" → design tool schema and implementation using SDK context - user: "Show toast on file edit" → react to file edit events and display status message - user: "Build a custom auth provider" → implement auth flow for new model provider - user: "Intercept git commits" → add hook to validate commit messages before execution

技能管理器。扫描、更新、整理工作区所有Skill，生成清单，检测冲突。

除錯專業知識。自動載入於 DEBUGGER 分析問題、測試失敗、錯誤排查相關任務時。 觸發詞：debug, 除錯, 錯誤, error, bug, 失敗, fail, 問題, issue, 5 Whys, 根因

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.

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.

버그, 테스트 실패, 예상치 못한 동작 발생 시 수정 전 반드시 사용. 4단계 근본 원인 분석 프로세스.

Check and update installed Claude Code skills from multiple sources (Claude plugins and npx skills). Scans for available updates, supports batch or individual updates with intelligent local change merging, and recommends popular skills from skillsmp.com and skills.sh marketplaces. Use when users want to update skills, check for new versions, discover trending skills, or manage their skill collection.

Use when working with WP-CLI (wp) for WordPress operations: safe search-replace, db export/import, plugin/theme/user/content management, cron, cache flushing, multisite, and scripting/automation with wp-cli.yml.

Use when developing WordPress block themes: theme.json (global settings/styles), templates and template parts, patterns, style variations, and Site Editor troubleshooting (style hierarchy, overrides, caching).

Use when developing WordPress plugins: architecture and hooks, activation/deactivation/uninstall, admin UI and Settings API, data storage, cron/tasks, security (nonces/capabilities/sanitization/escaping), and release packaging.

Production-ready QR code system for loyalty programs. Use when generating QR codes for loyalty cards, transactions, coupons, or referrals with encryption (AES-256), expiry times, and anti-fraud protection. Covers QR generation with signatures, scanning via Telegram WebApp showScanQrPopup(), validation with HMAC verification, data format standards, one-time use tokens, and fallback to manual input.

Quality control skill for Static → SvelteKit migration protocol v3.0. Use this skill during migration projects to validate prerequisites before launching agents, detect code duplication, verify TypeScript interfaces, check component best practices, and ensure zero errors. Invoke before each agent launch and after agent completion to prevent duplicate components, missing types, and TypeScript errors. Provides automated validation scripts and comprehensive checklists for all 7 migration stages.

Secure secret storage via Tailscale-only web UI. Never paste secrets in chat again.

Video and audio downloader supporting thousands of websites including YouTube, Bilibili, Vimeo, and more. Use when Claude needs to download videos or audio from URLs for: (1) Downloading single videos, (2) Extracting audio from videos, (3) Downloading playlists, (4) Downloading subtitles, (5) Format selection and quality control. Automatically handles format merging, subtitle embedding, and metadata preservation.

端到端工作流編排器 - 串聯 RESEARCH → PLAN → TASKS → IMPLEMENT → REVIEW → VERIFY

Use when web.run fails to parse a webpage and you need raw Markdown via Crawl4AI.

Claude Skills 架构师 - 创建高质量、可执行的 Skill 定义

Claude Skills 架构师 - 创建高质量、可执行的 Skill 定义

Claude Skills 架构师 - 创建高质量、可执行的 Skill 定义

Claude Skills 架构师 - 创建高质量、可执行的 Skill 定义

Generates prd.json task tracking file from PRD.md requirements document. Use when initializing Ralph loop or when the user asks to convert PRD to JSON format for autonomous execution.

Generate a skill map

Validate plan document structure and frontmatter. Use when checking plans for compliance, ensuring proper formatting, or verifying metadata before commits.

GitHub automation patterns - issues, projects, labels. Includes smart-ops scripts and bulk issue sync.

Comprehensive Alloy MVC Framework guide covering best practices, CLI commands, configuration files, debugging, and code samples. Use when Claude needs to help with Alloy development tasks - creating/configuring Alloy projects, using Alloy CLI commands (new, generate, compile, etc.), configuring alloy.jmk/config.json/widget.json, debugging Alloy compilation or runtime errors, implementing conditional views and data-binding, following Alloy coding best practices and naming conventions, using Backbone.Events for communication instead of Ti.App.fireEvent, or creating custom XML tags for reusable components.

Complete Titanium SDK + Alloy development expertise following PurgeTSS standards. Use when Claude needs to: (1) Design project architecture and folder structures, (2) Implement controllers, views, and services, (3) Choose between Models vs Collections for data strategies, (4) Establish communication patterns (Event Bus, Services), (5) Write clean ES6+ code with proper memory cleanup, (6) Apply PurgeTSS utility classes correctly, (7) Implement testing, error handling, and logging, (8) Optimize performance (ListView, bridge, memory), (9) Apply security patterns for mobile apps, (10) Migrate legacy Titanium apps to modern architecture.

Finalize a work session. Runs final verification, updates history log, and prepares branch for merge. Use when all planned tasks are complete.

BoxLogのリリース作業をガイド。バージョン決定、重複チェック、リリースノート作成、タグ付けまでの全プロセスを支援。

用于遇到 bug/测试失败/异常行为时先做系统化定位再提出修复；当需要排查问题而不是直接“拍脑袋改”时使用。

用于对 PR diff 做多代理独立 code review 并做共识汇总（降低顺序偏差/漏报），适合需要多视角审查或共识化问题筛选的场景

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.

Playwright를 사용하여 로컬 웹 애플리케이션과 상호작용하고 테스트하기 위한 도구 모음. 프론트엔드 기능 검증, UI 동작 디버깅, 브라우저 스크린샷 캡처, 브라우저 로그 확인을 지원합니다.

Extract property data from real estate listing URLs using Firecrawl AI. Use when scraping Zillow, Redfin, Realtor.com, or any property listing site. Returns structured data ready for video generation.

Search past reasoning for relevant decisions and approaches

Create and validate new AI agent skills. This skill provides standards, templates, and validation tools to ensure high-quality, interoperable skills across different AI agents.

YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video

Use for configuring state machine storage types. Triggers on: state machine, babuza storage type, memory state machine, disk state machine, concurrent snapshot

Adds new CNC machining calculation types (pocket, slot, chamfer, etc.) to the manufacturing time estimator.

GitHub Action のリリース手順をガイドする。「リリース」「バージョン更新」「v1 更新」と言われた場合に使用

Terraform IaC patterns for Yandex Cloud. Use when creating, modifying, or refactoring Terraform configurations for YDB, S3, Message Queue, Cloud Functions, API Gateway, or Serverless Containers. Provides resource patterns, naming conventions, and best practices from production projects.

Check Meilisearch index status, tasks, health, and settings. Use for debugging search issues, monitoring indexing tasks, and inspecting index configuration. Read-only admin operations.

YouTube video URL

Rollback brain/ files to a previous backup state. Use when session went wrong or need to recover from bad state. Optionally includes git reset.

Update project dependencies using taze, a modern CLI tool that keeps deps fresh. Supports monorepos, version range updates, and automatic installation. Use when updating dependencies, upgrading packages, or keeping packages up-to-date.

Runbook de diagnostic pour AutomationService (fenêtres horaires, hysteresis, off-repeat, timezone) et état state_store.

Efficiently navigate codebase documentation during Research phase. Use instead of Grep/Glob for finding architectural decisions, feature specs, and technical docs. Maps topics to doc locations for fast context retrieval. If codebase lacks documentation structure, provides patterns to establish one.

Set up AgentPulse in a React or Electron project. Use when the user wants to add AgentPulse, make their app MCP-controllable, or integrate with Claude Code/Claude Desktop. This is a ONE-TIME setup skill. For help writing useExpose hooks, use the "agentpulse" skill instead.

Use when the user asks about: game development, making games, cute framework, CF, cf_make_app, cf_app_update, game loop, sprite rendering, draw sprite, animation, collision detection, intersect, overlap, keyboard input, mouse input, gamepad, draw shapes, draw text, render, Aseprite, audio, sound effects, project setup, new game, create project, CMake, cmake setup, start game project, C++ game, C game

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.

YouTube 视频智能剪辑工具。下载视频和字幕，AI 分析生成精细章节（几分钟级别）， 用户选择片段后自动剪辑、翻译字幕为中英双语、烧录字幕到视频，并生成总结文案。 使用场景：当用户需要剪辑 YouTube 视频、生成短视频片段、制作双语字幕版本时。 关键词：视频剪辑、YouTube、字幕翻译、双语字幕、视频下载、clip video

Implement exactly one Beads task in a dedicated git worktree/branch with plan→code→self-review and write full updates back to the task. Use when implementing a Beads task, coding in a worktree, or executing a single task implementation.

Guide building LLM applications with pattern selection, tool design, context engineering, and safety guardrails. Use when building agents, designing agent tools, adding RAG, creating LLM-powered features, or asking how to structure an AI application.

Security hardening for Clawdbot Gateway. Use when running security audits, interpreting audit findings, configuring DM/group policies, setting up sandboxing, managing elevated tools, extracting secrets to .env, or responding to security incidents. Also triggers on questions about prompt injection defense, access control, network exposure, or the three-layer security model (sandbox, tool policy, elevated).

Quick ad-hoc browser testing with Playwright. Use when user says "test this page", "check if X works", "take a screenshot", "test the login", or any quick browser automation task. Executes custom Playwright code on-the-fly with visible browser.

Manages session lifecycle including context restoration, checkpoint creation, and learning capture

Audit Kubernetes RBAC, enforce policies, and manage secrets. Use for security reviews, permission audits, policy enforcement with Kyverno/Gatekeeper, and secret management.

Manage GitOps workflows with Flux and ArgoCD. Use for sync status, reconciliation, app management, source management, and GitOps troubleshooting.

Debug Kubernetes pods, nodes, and workloads. Use when pods are failing, containers crash, nodes are unhealthy, or users mention debugging, troubleshooting, or diagnosing Kubernetes issues.

Use when context threshold is exceeded and supervisor signals checkpoint needed, or when .tina/checkpoint-needed exists

Testing workflow and tmux safety rules for tmuxx development

Transcribe audio files with speaker diarization using MLX-Whisper + pyannote-audio. Generates speaker-attributed transcripts and meeting analysis.

Calculate and verify file checksums. Supports MD5, SHA1, SHA256, SHA512.

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.

Structured, repeatable debugging methodology with automated analysis and metrics tracking

AI image generation with OpenAI and Google APIs. Supports text-to-image, reference images, aspect ratios, and parallel generation (recommended 4 concurrent subagents). Use when user asks to generate, create, or draw images.

Create new hooks for Claude Code. Use when adding safety, automation, or notification hooks.

Create new skills using test-driven documentation. Use when adding, improving, or extracting skills.

Thorough GitHub pull request review from a PR URL, including diff analysis against the target base branch, code quality, potential bugs, critical errors, and consistency with the existing codebase.