Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 404 files from 1 741 authors, of which 61 763 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Tools, patterns, and utilities for generating professional music with realistic instrument sounds. Write custom compositions using music21 or learn from existing MIDI files.
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
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.
Send Bark (day.app) push notifications after Codex completes a task. Use when one Codex or Claude run is finished, or when you need to notify on task completion with device name, project name, status, and summary.
Send SMTP email notifications after Codex completes a task. Use when one Codex or Claude run is finished, or when you need to notify on task completion with device name, project name, status, and summary via email.
Document ID management for Git repositories. Validates, assigns, and tracks immutable doc_ids across Markdown/YAML files. Use when working with doc_id, document IDs, "@see docid" references, document integrity validation, or shirushi commands.
This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.
Lightweight playbook distilled from AI Architecture to keep dual-engine memory (.ai_context) and manifest dispatcher with minimal overhead; use when bootstrapping or porting the pattern into Claude Skills format.
AIPPT - 基于模板定制化生成 PPT。垫图约束风格 → 提示词替换内容 → AI 生图 → 打包 PPTX。
当用户想要生成图片、画图、绘画、创建图像、AI作画时使用此 Skill。支持文生图和图生图。
执行视频剪辑。根据确认的删除任务执行FFmpeg剪辑，循环直到零口误，生成字幕。触发词：执行剪辑、开始剪、确认剪辑
自媒体写作交互式助手。帮助完成从选题到发布的完整流程。适用于：开始写新文章、检查草稿质量、诊断发布后数据不佳的原因。
Create and define visual art styles for projects. Use when user wants to establish an art direction, create a style guide, define visual language, document aesthetic choices, or create consistent artwork guidelines for games, illustrations, animations, or other visual media.
Create and modify combat system components for SHINOBI WAY game following the dual-system architecture (CombatCalculationSystem + CombatWorkflowSystem). Use when user wants to add new combat mechanics, damage formulas, status effects, mitigation logic, turn phases, or refactor existing combat code. Guides through proper separation of pure calculations vs state management.
Implement Split-Panel Combat UI (Pattern A) for SHINOBI WAY game. Use when user wants to create the horizontal confrontation combat layout, character panels, action dock, phase header, VS divider, or any component from the Pattern A combat UI system. Guides through component creation following the established architecture.
Create exploration content for SHINOBI WAY game with node-based path navigation. Use when user wants to add new regions, locations, room layouts, intel missions, path networks, or exploration mechanics. Guides through the Region→Location→Room hierarchy with intel-gated path choices. (project)
Create new jutsu/skills for SHINOBI WAY game. Use when user wants to add abilities, techniques, jutsu, or combat skills. Guides through all parameters and generates TypeScript code.
> Build full-stack web applications powered by Google Gemini's Nano Banana & Nano Banana Pro image generation APIs. Use when creating Next.js image generators, editors, galleries, or any web app that integrates gemini-2.5-flash-image or gemini-3-pro-image-preview models. Covers React components, server actions, API routes, storage, rate limiting, and production deployment patterns.
> Creates simple Three.js web apps with scene setup, lighting, geometries, materials, or when user wants 3D web content. Supports ES modules, modern Three.js r150+ APIs.
Türkiye Kişisel Verilerin Korunması Kanunu (KVKK / 6698 sayılı Kanun) uyum denetimi. Gizlilik politikası, aydınlatma metni, açık rıza formu oluşturma ve mevcut metinleri KVKK'ya uygunluk açısından analiz etme. Türk şirketleri için GDPR muadili uyum desteği.
Türkçe resmi yazı, dilekçe, itiraz mektubu ve kurumsal yazışma üretimi. Devlet kurumlarına dilekçe, SGK/vergi idaresi yazışması, Noter belgesi, şikâyet mektubu, iş başvurusu için kullan.
Türkçe metin yazımı, düzeltme ve üslup yardımı. Resmi/gayriresmi ton ayarı, sen/siz seçimi, Türkçe dilbilgisi kontrolü ve doğal Türkçe ifadeler için kullan. Türkçe yazarken, Türkçe metin düzeltirken veya Türkçe içerik üretirken aktive et.
Türkçe yazılım projeleri için kod dokümantasyonu, yorum satırları, README ve commit mesajları yazma rehberi. Teknik terimlerin Türkçe karşılıkları ve Türk geliştirici topluluğu standartları.
Create and modify Argcfiles using the special syntax required. Use this when editing Argcfile.sh, @argc, or any shell script that contains `argc --argc-eval`.
Configures 2-Agent workflow between PM and implementation roles. Use when user mentions 2-Agent, 2エージェント, PM連携設定, Cursor設定, Cursor連携, 2-agent運用. Do NOT load for: 単独運用, ワークフロー実行, ハンドオフ処理.
Implements authentication and payment features using Clerk, Supabase Auth, or Stripe. Use when user mentions ログイン, 認証, auth, authentication, Clerk, Supabase, 決済, payment, Stripe, 課金, サブスクリプション. Do NOT load for: 一般的なUI作成, データベース設計, 非認証機能.
Diagnoses and fixes CI/CD pipeline failures. Use when user mentions 'CI', 'GitHub Actions', 'GitLab CI', 'ビルドエラー', 'テスト失敗', 'パイプライン', 'CIが落ちた', or asks to analyze build/test failures. Do NOT load for: ローカルビルド, 通常の実装作業, レビュー, セットアップ.
Cursorでclaude-memのMCPサーバーにアクセスし、過去のセッション記録を検索・新しい観測を記録。トリガー: 'メモリ検索', 'claude-mem', '過去の判断', '記録して', 'memory search', 'past decisions'. Do NOT load for: 通常のコーディング、一時的なメモ、実装作業。
Sets up deployment, analytics, and health monitoring for projects. Use when user mentions デプロイ, deploy, Vercel, Netlify, 公開, アナリティクス, analytics, GA, Google Analytics, 環境診断, health check. Do NOT load for: 実装作業, ローカル開発, レビュー, セットアップ.
Generates documentation files including NotebookLM YAML and slide content. Use when user mentions ドキュメント, document, YAML, NotebookLM, スライド, slide, プレゼン. Do NOT load for: 実装作業, コード修正, レビュー, デプロイ.
Implements features and writes code based on Plans.md tasks. Use when user mentions 実装, implement, 機能追加, コードを書いて, 機能を作って, feature, coding, 新機能, implementing functions, classes, or features, 新しい関数. Do not use for review or build verification.
Cleans up and organizes project files. Use when user mentions '整理', 'cleanup', 'アーカイブ', 'archive', '肥大化', 'Plans.md', 'session-log', or asks to clean up old tasks, archive completed items, or organize files. Do NOT load for: 実装作業, レビュー, 新機能開発, デプロイ.
Manages memory, SSOT files, and Plans.md operations. Use when user mentions メモリ, memory, SSOT, decisions.md, patterns.md, マージ, merge, Plans.md, 移行, migrate. Do NOT load for: 実装作業, レビュー, 一時的なメモ, セッション中の作業記録.
Optimizes parallel execution of multiple tasks. Use when user mentions 並列で実行, 同時にやって, まとめてやって, run in parallel, do these together. Do NOT load for: 単一タスク, 順次実行が必要な作業, 依存関係のあるタスク.
Manages Plans.md tasks and marker operations. Use when user mentions タスクを追加, Plans.md更新, 完了マーク, タスク状態変更, add task, update plans, mark complete. Do NOT load for: 実装作業, レビュー, Plans.md以外のファイル操作.
Provides development principles, guidelines, and VibeCoder guidance. Use when user mentions 原則, principles, ガイドライン, guidelines, VibeCoder, 安全性, safety, 差分編集, diff-aware. Triggers: 原則, principles, ガイドライン, VibeCoder, 安全性, 差分編集. Do not use for actual implementation - use impl skill instead.
Reviews code for quality, security, performance, and accessibility issues. Use when user mentions レビュー, review, コードレビュー, セキュリティ, パフォーマンス, 品質チェック, セルフレビュー, PR, diff, 変更確認. Do NOT load for: 実装作業, 新機能開発, バグ修正, セットアップ.
Initializes session with environment check and task status overview. Use when user mentions セッション開始, 作業開始, 状況確認, what should I work on, start session. Do NOT load for: 実装作業, レビュー, セッション途中の作業.
Manages cross-session learning and memory persistence. Use when user mentions 前回何をした, 履歴, 過去の作業, セッション記録, continue from before, session history. Do NOT load for: 実装作業, レビュー, 一時的な情報.
Sets up new projects and generates workflow files like CLAUDE.md, AGENTS.md, Plans.md. Use when user mentions セットアップ, setup, 初期化, initialize, 新規プロジェクト, ワークフローファイル生成. Do NOT load for: 実装作業, レビュー, ビルド検証, デプロイ.
Guides diagnosis and resolution when problems occur. Use when user mentions 動かない, エラーが出た, 壊れた, うまくいかない, broken, doesn't work, error. Do NOT load for: 正常なビルド, 新機能実装, レビュー.
Generates UI components and feedback forms. Use when user mentions コンポーネント, component, UI, ヒーロー, hero, フォーム, form, フィードバック, feedback, 問い合わせ. Do NOT load for: 認証機能, バックエンド実装, データベース操作, ビジネスロジック.
Verifies builds, recovers from errors, and applies review fixes. Use when user mentions ビルド, build, 検証, verify, エラー復旧, error recovery, 指摘を適用, apply fixes, テスト実行, tests fail, lint errors occur, CI breaks, テスト失敗, lintエラー, 型エラー, ビルドエラー, CIが落ちた. Do NOT load for: 実装作業, レビュー, セットアップ, 新機能開発.
Guides VibeCoder (non-technical users) through natural language development (legacy). Use when user mentions どうすればいい, 次は何, 使い方, 困った, help, what should I do. Do NOT load for: 技術者向け作業, 直接的な実装指示, レビュー.
Provides guidance on Cursor ↔ Claude Code 2-agent workflow. Use when user mentions ワークフローについて, Cursorとの連携, 作業の流れ, 2-agent workflow, collaboration. Do NOT load for: 実装作業, ワークフロー設定, ハンドオフ実行.
Manages workflow transitions including handoffs between PM and implementation roles, and auto-fixes review comments. Use when user mentions ハンドオフ, handoff, PMに報告, 実装役に渡して, レビュー指摘を自動修正, auto-fix. Triggers: ハンドオフ, handoff, PMに報告, 実装役に渡して, 完了報告, 自動修正, auto-fix. Do not use for 2-Agent setup - use 2agent skill instead.
Automatically generate and execute Python test scripts from OpenAPI specifications and GraphQL schemas with enhanced features
Use when reviewing code, PRs, or discussing code quality standards. Applies team coding standards and review methodology.
An example skill demonstrating the basic structure. Use when user asks about examples or templates.
Use when generating standup reports, daily updates, or team status summaries. Formats work activity into concise standup format.
Use when making technical decisions, choosing technologies, or documenting architectural choices. Creates ADRs (Architecture Decision Records).
Enforces local testing before any deployment. MUST be used before running vercel, git push, or any deployment command. Prevents deploying untested code.
Project-agnostic guidance for AI assistants using Chronicle. Provides search-first directives, best practices, and workflow patterns across ALL Chronicle-tracked projects. Works with or without MCP server.
Search and retrieve context from past development sessions using Chronicle data. Works with MCP (fast, structured) or CLI commands (portable). Use when user asks about previous work, wants to recall past decisions, needs to understand codebase history, or wants to avoid repeating past approaches.
Manage Chronicle project development using database-tracked milestones, next steps, and roadmap visualization. Works with MCP tools (fast, structured) or CLI commands (portable). Use when planning features, tracking progress, viewing roadmap, or linking sessions to milestones. Eliminates manual DEVELOPMENT_HISTORY.md updates.
Automate cross-system summarization workflow for Chronicle sessions. Export sessions from remote systems (like FreeBSD) and import/summarize on local machine with Gemini API. Use when you have sessions on a system without Gemini API access and need to summarize them on another machine.
Document AI-assisted development sessions to Obsidian vault using Chronicle data. Works with MCP (fastest) or CLI commands (portable). Use when completing a coding session, creating development logs, or maintaining a knowledge base of past work. Automatically creates structured notes with metadata, summaries, and wikilinks.
Complete workflow for tracking development work with Chronicle - session recording, git tracking, AI summarization, and Obsidian documentation. Works with CLI commands (portable) or MCP tools (faster). Use when starting a new development session, setting up project tracking, or when user wants comprehensive session management.
Autonomous penetration testing coordinator using ReAct methodology. Automatically activates when user provides a target IP or asks to start penetration testing. Orchestrates reconnaissance, exploitation, and privilege escalation until both user and root flags are captured. (project)
Claude Skills — questions
Answers built from the skills we actually parsed.