mcpbeat Sign in

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. 79 600 files from 1 763 authors, of which 61 947 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.

61 947
unique skills
out of 79 600 files found on GitHub
17 653
are copies
same content, someone else's repository
1 739
tokens, median
what a typical skill costs you in context
7 890
name collisions
two skills with one name cannot sit side by side

41 041–41 100 of 61 947

page 685 of 1 033
Springboot Verification
by mturac

Verification loop for Spring Boot projects: build, static analysis, tests with coverage, security scans, and diff review before release or PR.

639 tokens zh
Strategic Compact
by mturac

Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.

1k tokens
Swift Actor Persistence
by mturac

Swiftでactorを使用してスレッドセーフなデータ永続化を実装する——メモリキャッシュとファイルバックドストレージを組み合わせ、設計によってデータ競合を排除する。

2k tokens
Swift Concurrency 6 2
by mturac

Swift 6.2のアクセシブルな並行処理——デフォルトはシングルスレッド、@concurrentは明示的なバックグラウンドオフロードに使用し、分離の一貫性はMainActor型に使用する。

2k tokens zh
Swift Protocol Di Testing
by mturac

テスト可能なSwiftコードのためのプロトコルベースの依存性注入——焦点を絞ったプロトコルとSwift Testingを使用してファイルシステム、ネットワーク、外部APIをモックする。

2k tokens
Swiftui Patterns
by mturac

@Observableを使用した状態管理、ビュー合成、ナビゲーション、パフォーマンス最適化、モダンなiOS/macOS UIのベストプラクティスを備えたSwiftUIアーキテクチャパターン。

2k tokens
Tdd Workflow
by mturac

新機能の作成、バグ修正、コードのリファクタリング時にこのスキルを使用します。ユニット、統合、E2Eテストを含む80%以上のカバレッジでテスト駆動開発を強制します。

3k tokens
Team Builder
by mturac

並列チームを構成して派遣するためのインタラクティブなエージェント選択ツール

2k tokens zh
Terminal Ops
by mturac

eccのための証拠優先のリポジトリ実行ワークフロー。ユーザーがコマンドの実行、リポジトリの確認、CIの失敗のデバッグ、正確な実行と検証の証明を伴う狭い修正のプッシュを必要とする場合に使用する。

1k tokens zh
Tinystruct Patterns
by mturac

tinystructフレームワークでアプリケーションモジュールまたはマイクロサービスを開発する際に使用。ルーティング、コンテキスト管理、BuilderによるJSON処理、CLI/HTTPデュアルモードのパターンをカバー。

1k tokens
Token Budget Advisor
by mturac

回答する前に、どれだけの回答深度を消費するかについてユーザーに情報に基づいた選択を提供する。ユーザーが回答の長さ、深さ、またはトークンバジェットを明示的に制御したい場合にこのスキルを使用する。トリガー条件:"token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas"、またはユーザーが回答のサイズや深さの制御を明示的に求めるその他の明確なバリエーション。トリガーしない条件:ユーザーが現在のセッションでレベルを指定済み(そのレベルを維持)、リクエストが明らかに一言の回答、または「token」が認証/セッション/支払いトークンを指している。origin: community

2k tokens zh
UI Demo
by mturac

Playwrightを使用して美しいUIデモ動画を録画する。ユーザーがWebアプリのデモ、ウォークスルー、スクリーン録画、またはチュートリアル動画の作成を求める場合に使用する。可視カーソル、自然なリズム、プロフェッショナルな仕上がりのWebM動画を生成する。

5k tokens
UI To Vue
by mturac

UIスクリーンショットやデザインエクスポートをVue 3コンポーネントに一括変換する際に使用。Vant、Element Plus、Ant Design Vueに対応。

1k tokens zh
Unified Notifications Ops
by mturac

GitHub、Linear、デスクトップアラート、フック、接続された通信インターフェースを網羅する、統合されたeccネイティブワークフローとして通知を運用する。真の問題がアラートルーティング、重複排除、エスカレーション、またはインボックス崩壊である場合に使用する。

2k tokens zh
Verification Loop
by mturac
714 tokens
Video Editing
by mturac

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

2k tokens
Videodb
by mturac

ビデオとオーディオの表示、理解、アクション。表示:ローカルファイル、URL、RTSP/ライブストリーム、またはリアルタイムのデスクトップ録画からコンテンツを取得し、リアルタイムコンテキストと再生可能なストリームリンクを返す。理解:フレームを抽出し、ビジュアル/セマンティック/時間的インデックスを構築し、タイムスタンプと自動クリップでモーメントを検索する。アクション:トランスコードと正規化(コーデック、フレームレート、解像度、アスペクト比)、タイムライン編集(字幕、テキスト/画像オーバーレイ、ブランディング、オーディオオーバーレイ、吹き替え、翻訳)、メディアアセットの生成(画像、オーディオ、ビデオ)、ライブストリームまたはデスクトップキャプチャされたイベントのリアルタイムアラートを実行する。

36k tokens
Visa Doc Translate
by mturac

ビザ申請書類(画像)を英語に翻訳し、原文と翻訳を含むバイリンガルPDFを作成する

2k tokens zh
Vite Patterns
by mturac

Vite build tool patterns including config, plugins, HMR, env variables, proxy setup, SSR, library mode, dependency pre-bundling, and build optimization. Activate when working with vite.config.ts, Vite plugins, or Vite-based projects.

6k tokens zh
Windows Desktop E2e
by mturac

E2E testing for Windows native desktop apps (WPF, WinForms, Win32/MFC, Qt) using pywinauto and Windows UI Automation.

8k tokens
Workspace Surface Audit
by mturac

アクティブなリポジトリ、MCPサーバー、プラグイン、コネクター、環境サーフェス、ツールのセットアップを監査し、最も価値の高いeccネイティブスキル、フック、エージェント、オペレーターワークフローを推奨する。ユーザーがOpenAI Codexのセットアップを支援してほしい場合や、環境で実際に何が使えるかを理解したい場合に使用する。

2k tokens zh
X API
by mturac

X/Twitter API integration for posting tweets, threads, reading timelines, search, and analytics. Covers OAuth auth patterns, rate limits, and platform-native content posting. Use when the user wants to interact with X programmatically.

2k tokens
Backend Patterns
by mturac

Node.js, Express, Next.js API 라우트를 위한 백엔드 아키텍처 패턴, API 설계, 데이터베이스 최적화 및 서버 사이드 모범 사례.

4k tokens
Clickhouse Io
by mturac

ClickHouse database patterns, query optimization, analytics, and data engineering best practices for high-performance analytical workloads.

3k tokens
Coding Standards
by mturac

TypeScript, JavaScript, React, Node.js 개발을 위한 범용 코딩 표준, 모범 사례 및 패턴.

3k tokens
Continuous Learning V2
by mturac

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.

43k tokens scripts
Continuous Learning
by mturac

[DEPRECATED - use continuous-learning-v2] Legacy v1 stop-hook skill extractor. v2 is a strict superset with instinct-based, project-scoped, hook-reliable learning. Do not invoke v1; route continuous learning, session learning, and pattern extraction requests to continuous-learning-v2.

2k tokens scripts
Eval Harness
by mturac

평가 주도 개발(EDD) 원칙을 구현하는 OpenAI Codex 세션용 공식 평가 프레임워크

2k tokens
Frontend Patterns
by mturac

React, Next.js, 상태 관리, 성능 최적화 및 UI 모범 사례를 위한 프론트엔드 개발 패턴.

4k tokens
Golang Patterns
by mturac

견고하고 효율적이며 유지보수 가능한 Go 애플리케이션 구축을 위한 관용적 Go 패턴, 모범 사례 및 규칙.

4k tokens
Golang Testing
by mturac

테이블 주도 테스트, 서브테스트, 벤치마크, 퍼징, 테스트 커버리지를 포함한 Go 테스팅 패턴. 관용적 Go 관행과 함께 TDD 방법론을 따릅니다.

4k tokens
Iterative Retrieval
by mturac

Pattern for progressively refining context retrieval to solve the subagent context problem

2k tokens
Postgres Patterns
by mturac

쿼리 최적화, 스키마 설계, 인덱싱, 보안을 위한 PostgreSQL 데이터베이스 패턴. Supabase 모범 사례 기반.

986 tokens
Security Review
by mturac

인증 추가, 사용자 입력 처리, 시크릿 관리, API 엔드포인트 생성, 결제/민감한 기능 구현 시 이 스킬을 사용하세요. 포괄적인 보안 체크리스트와 패턴을 제공합니다.

6k tokens
Strategic Compact
by mturac

임의의 자동 컴팩션 대신 논리적 간격에서 수동 컨텍스트 압축을 제안하여 작업 단계를 통해 컨텍스트를 보존합니다.

1k tokens
Tdd Workflow
by mturac

새 기능 작성, 버그 수정 또는 코드 리팩터링 시 이 스킬을 사용하세요. 단위, 통합, E2E 테스트를 포함한 80% 이상의 커버리지로 테스트 주도 개발을 시행합니다.

3k tokens
Verification Loop
by mturac

OpenAI Codex 세션을 위한 포괄적인 검증 시스템.

682 tokens
API Design
by mturac

REST API tasarım kalıpları; kaynak isimlendirme, durum kodları, sayfalama, filtreleme, hata yanıtları, versiyonlama ve üretim API'leri için hız sınırlama içerir.

4k tokens
Backend Patterns
by mturac

Node.js, Express ve Next.js API routes için backend mimari kalıpları, API tasarımı, veritabanı optimizasyonu ve sunucu tarafı en iyi uygulamalar.

4k tokens
Coding Standards
by mturac

TypeScript, JavaScript, React ve Node.js geliştirme için evrensel kodlama standartları, en iyi uygulamalar ve kalıplar.

3k tokens
Continuous Learning V2
by mturac

Hook'lar aracılığıyla oturumları gözlemleyen, güven skorlaması ile atomik instinct'ler oluşturan ve bunları skill/command/agent'lara evriltiren instinct tabanlı öğrenme sistemi. v2.1 çapraz proje kontaminasyonunu önlemek için proje kapsamlı instinct'ler ekler.

3k tokens
Continuous Learning
by mturac

OpenAI Codex oturumlarından yeniden kullanılabilir kalıpları otomatik olarak çıkarın ve gelecekte kullanmak üzere öğrenilmiş skill'ler olarak kaydedin.

1k tokens
Database Migrations
by mturac

Şema değişiklikleri, veri migration'ları, rollback'ler ve PostgreSQL, MySQL ve yaygın ORM'ler (Prisma, Drizzle, Django, TypeORM, golang-migrate) arasında sıfır kesinti deployment'ları için veritabanı migration en iyi uygulamaları.

2k tokens
Deployment Patterns
by mturac

Deployment iş akışları, CI/CD pipeline kalıpları, Docker konteynerizasyonu, sağlık kontrolleri, rollback stratejileri ve web uygulamaları için üretim hazırlığı kontrol listeleri.

3k tokens
Django Patterns
by mturac

Django architecture patterns, REST API design with DRF, ORM best practices, caching, signals, middleware, and production-grade Django apps.

5k tokens
Docker Patterns
by mturac

Yerel geliştirme, konteyner güvenliği, ağ, volume stratejileri ve multi-servis orkestrasyon için Docker ve Docker Compose kalıpları.

2k tokens
E2e Testing
by mturac

Playwright E2E test kalıpları, Page Object Model, yapılandırma, CI/CD entegrasyonu, artifact yönetimi ve kararsız test stratejileri.

2k tokens
Eval Harness
by mturac

Eval-driven development (EDD) ilkelerini uygulayan OpenAI Codex oturumları için formal değerlendirme çerçevesi

2k tokens
Frontend Patterns
by mturac

React, Next.js, state yönetimi, performans optimizasyonu ve UI en iyi uygulamaları için frontend geliştirme kalıpları.

4k tokens
Golang Patterns
by mturac

İdiomatic Go desenler, en iyi uygulamalar ve sağlam, verimli ve bakımı kolay Go uygulamaları oluşturmak için konvansiyonlar.

4k tokens
Golang Testing
by mturac

Table-driven testler, subtestler, benchmark'lar, fuzzing ve test coverage içeren Go test desenleri. TDD metodolojisi ile idiomatic Go uygulamalarını takip eder.

4k tokens
Jpa Patterns
by mturac

JPA/Hibernate patterns for entity design, relationships, query optimization, transactions, auditing, indexing, pagination, and pooling in Spring Boot.

1k tokens
Kotlin Patterns
by mturac

Idiomatic Kotlin patterns, best practices, and conventions for building robust, efficient, and maintainable Kotlin applications with coroutines, null safety, and DSL builders.

5k tokens
Kotlin Testing
by mturac

Kotlin testing patterns with Kotest, MockK, coroutine testing, property-based testing, and Kover coverage. Follows TDD methodology with idiomatic Kotlin practices.

5k tokens
Laravel Patterns
by mturac

Laravel architecture patterns, routing/controllers, Eloquent ORM, service layers, queues, events, caching, and API resources for production apps.

3k tokens
Laravel Security
by mturac

Laravel security best practices for authn/authz, validation, CSRF, mass assignment, file uploads, secrets, rate limiting, and secure deployment.

2k tokens
Laravel Tdd
by mturac

Test-driven development for Laravel with PHPUnit and Pest, factories, database testing, fakes, and coverage targets.

2k tokens
Laravel Verification
by mturac

Verification loop for Laravel projects: env checks, linting, static analysis, tests with coverage, security scans, and deployment readiness.

1k tokens
Nextjs Turbopack
by mturac

Next.js 16+ and Turbopack — incremental bundling, FS caching, dev speed, and when to use Turbopack vs webpack.

675 tokens
Postgres Patterns
by mturac

Sorgu optimizasyonu, şema tasarımı, indeksleme ve güvenlik için PostgreSQL veritabanı kalıpları. Supabase en iyi uygulamalarına dayanır.

1k tokens

Claude Skills — questions

Answers built from the skills we actually parsed.

What is a Claude Skill?
A folder with a SKILL.md file: instructions that teach an agent to do one thing well, optionally with scripts and reference files alongside. The format is open and called Agent Skills — Claude Code, Codex and other agents read the same files. It is not a program you run; it is knowledge the agent loads when the task calls for it.
How is a skill different from an MCP server?
A server gives the agent new abilities — it connects to something and exposes tools. A skill gives the agent knowledge: how to use what it already has. They combine, and often literally: 11 352 of the skills here declare which MCP servers they need to work.
Why are there fewer skills here than in other catalogues?
Because we deduplicate by content. Of 79 600 files found on GitHub, 61 947 are unique — the rest is the same skill copied into someone else's repository, word for word. Catalogues that count files rather than skills show every copy as a separate entry.
What does the token count mean?
A skill is loaded into the model's context when it is used, so its size is a running cost on every request that touches it. We measure the whole folder, not just SKILL.md: one official skill is 377 tokens, another drags 83 files of fonts behind it.
How do I install a skill?
Copy the skill folder into ~/.claude/skills for personal use, or into .claude/skills inside a project. The agent picks it up by the name in the SKILL.md header — which is worth checking: 7 890 skills here share a name with another skill, and two of them cannot sit side by side.