Explore AI Agent Skills & Claude Prompts
Discover open-source agent skills for Claude Code, Codex, ChatGPT, and any tool that uses SKILL.md.
Enter through keywords, occupations, creators, and GitHub sources to see what kinds of skills are emerging across domains.
Use the same catalog through the API
Connect 381,784 public skills to your own search, analytics, or agent workflow with the REST API.
Querying local SQLite index...
decomposition
by fumiya-kumeThis skill should be used when the user asks to "decompose", "break down task", "create detailed todos", "split into todos". Also triggers when the user says in Japanese: "タスク分解", "todo に落として", "細かい todo にして".
dig
by fumiya-kumeThis skill should be used when the user asks to "dig", "challenge assumptions", "stress test plan", "find risks in plan". Also triggers when the user says in Japanese: "前提を疑って", "計画を深掘り", "プランに穴が無いか".
fix-ci
by fumiya-kumeThis skill should be used when the user asks to "fix CI", "fix failed checks", "PR is red", "diagnose CI failure". Also triggers when the user says in Japanese: "CI 直して", "CI が落ちてる", "PR の CI を直して".
deslop
by fumiya-kumeRemove AI-generated code slop from code changes in the current branch
ios-mapkit-implementation
by fumiya-kumeThis skill should be used when the user asks to "add map view", "show user location", "implement MapKit", "add markers to map", "calculate route", "use MKDirections", "search nearby places", "use MKLocalSearch", "implement geocoding", "use CLGeocoder", "add Look Around", "customize map style", "add map annotations", "track user location", "configure location permissions", "地図を表示したい", "MapKitを実装", "マーカーを追加", "経路検索を実装", "ナビゲーション機能", "現在地を取得", "周辺検索", "ジオコーディング", "住所から座標を取得", "座標から住所", "Look Aroundを追加", "地図をカスタマイズ", "位置情報の権限設定", or needs guidance on MapKit for SwiftUI, Core Location integration, MKDirections, MKLocalSearch, CLGeocoder, Look Around preview, map annotations, custom overlays, or location privacy settings for iOS 17+ SwiftUI applications.
ios-voice-input-implementation
by fumiya-kumeThis skill should be used when the user asks to "implement voice input", "add speech recognition", "use SFSpeechRecognizer", "configure microphone permissions", "音声入力を実装したい", "Speech Frameworkの使い方", "マイク権限の設定", "音声認識機能を追加", "ディクテーション機能", or needs guidance on Apple Speech Framework, AVAudioSession configuration, speech recognition authorization, real-time transcription, on-device recognition, or iOS voice input best practices for SwiftUI applications targeting iOS 17+.
m3-expressive
by fumiya-kumeThis skill should be used when the user asks to "implement Material 3 Expressive", "add spring animations", "use MotionScheme", "create expressive button", "add loading indicator", "implement FAB menu", "use shape morphing", "create floating toolbar", "add carousel", "implement ButtonGroup", "use MaterialShapes", "implement vibrant FAB", "add expressive UI", "configure MaterialExpressiveTheme", "use spring physics animation", "Material 3 Expressive を実装", "スプリングアニメーション", "MotionScheme を使用", "表現力豊かなボタン", "ローディングインジケーター", "FABメニュー", "シェイプモーフィング", "フローティングツールバー", "カルーセル", "ButtonGroup を追加", "MaterialShapes を使用", "Vibrant FAB", "MaterialExpressiveTheme を設定", "物理ベースアニメーション", or needs guidance on Material 3 Expressive implementation for Android with Jetpack Compose, including MotionScheme, spring animations, shape morphing, and new expressive components for Android API 24+.
macos-mapkit-implementation
by fumiya-kumeThis skill should be used when the user asks to "add map view to macOS app", "show user location on macOS", "implement MapKit for macOS", "add markers to map in macOS app", "calculate route in macOS app", "use MKDirections on macOS", "search nearby places on macOS", "use MKLocalSearch on macOS", "implement geocoding on macOS", "use CLGeocoder on macOS", "add Look Around on macOS", "customize map style on macOS", "configure location permissions for macOS", "set up App Sandbox for location", "use MKMapView with AppKit", "macOSアプリに地図を追加", "macOSで位置情報を表示", "macOSでMapKitを実装", "macOSでマーカーを追加", "macOSで経路検索", "macOSで周辺検索", "macOSでジオコーディング", "macOSでLook Around", "macOSで地図をカスタマイズ", "macOSの位置情報権限設定", "App Sandboxで位置情報", "AppKitでMKMapView", or needs guidance on MapKit for macOS 14+ SwiftUI/AppKit applications, App Sandbox configuration, location entitlements, or macOS-specific location permission handling.
macos-swiftui
by fumiya-kumeThis skill should be used when the user asks to "build macOS app", "create macOS window", "implement NavigationSplitView", "add menu commands", "create Settings window", "implement document-based app", "use WindowGroup", "add toolbar", "implement sidebar", "multi-window app", "macOS アプリを作成", "macOS で実装", "メニューを追加", "設定画面を作成", "マルチウィンドウ", "サイドバーを実装", "ドキュメントベースアプリ", "ツールバーを追加". Provides macOS 14+ (Sonoma) development guidance with SwiftUI, window management, menu integration, and macOS-specific patterns.
nextjs-google-maps
by fumiya-kumeThis skill should be used when the user asks to "add Google Maps", "integrate maps", "show location on map", "implement place search", "add route calculation", "geocode address", "display markers", "create heatmap", "add Street View", "implement drawing tools", "Google Maps を追加", "地図を表示", "位置情報を表示", "場所検索を実装", "ルート計算", "住所から座標を取得", "マーカーを表示", "ヒートマップを作成", "ストリートビュー", "描画ツールを追加", "@react-google-maps/api の使い方", or needs guidance on Google Maps Platform integration with Next.js App Router, including Places API, Directions API, Geocoding API, visualization features, and performance optimization.
swift-docc
by fumiya-kumeThis skill should be used when the user asks to "create DocC documentation", "add documentation comments", "write API docs", "set up DocC catalog", "host documentation on GitHub Pages", "document Swift code", "write /// comments", "create tutorials", "generate documentation", "build documentation", "DocC を作成", "ドキュメントコメントを追加", "API ドキュメントを書く", "DocC カタログを設定", "GitHub Pages でホスト", "Swift コードをドキュメント化", "/// コメントを書く", "チュートリアルを作成", "ドキュメントを生成", or needs guidance on DocC catalogs, documentation comments, symbol documentation, articles, tutorials, or documentation hosting for iOS 17+/macOS 14+ Swift projects.
swift6-strict-concurrency
by fumiya-kumeThis skill should be used when the user asks to "migrate to Swift 6", "enable strict concurrency", "fix Sendable errors", "add @MainActor", "resolve data race warnings", "implement actor isolation", "configure complete concurrency checking", "fix Swift 6 warnings", "make class Sendable", "handle @Sendable closures", "Swift 6 に移行", "Strict Concurrency を有効化", "Sendable エラーを修正", "@MainActor を追加", "データ競合警告を解決", "アクター分離を実装", "完全な並行性チェックを設定", "Swift 6 警告を修正", "クラスを Sendable にする", "@Sendable クロージャを扱う", or needs guidance on Swift 6 strict concurrency migration, Sendable protocol implementation, actor isolation patterns, data race safety, and migration strategies from Swift 5 to Swift 6.
Browse Agent Skills by Occupation
23 major groups · 867 SOC occupations
Browse by Category
Explore agent skills organized by their primary use case
Explore the agent skills ecosystem by occupation and creator
SkillMD is not just a keyword search box. It is an open map that organizes public skills by occupation, creator, and repository, helping you see which workflows, judgment criteria, and domain habits people are writing for AI agents.
Then follow creators and GitHub repositories back to the source: compare the skills a team maintains, whether the repo is active, and how the README frames the work before you open, install, or reuse anything.
Use it three ways: learn an unfamiliar field by occupation, study how creators organize skills, then use source context to decide what is worth opening or reusing.
01 Map a field
Browse 23 occupation groups and 867 SOC roles to learn what skills exist in adjacent domains and how they break down real work.
02 Follow creators
Use creator and repository pages to inspect maintained skill collections, recent updates, and source context before trusting a result.
03 Search with sources
Search 1.7M+ collected skills, then use occupation tags, creators, and GitHub source context to decide what is worth opening.
Start with the occupation map, then follow creators and repositories back to real code. SkillMD helps explain why a skill is worth opening, not only what it is named.
Standardizing Agent Capabilities with SKILL.md and Model Context Protocol (MCP)
In the rapidly evolving landscape of artificial intelligence, LLM agents (Large Language Model agents) have transitioned from simple text predictors to autonomous problem solvers. To orchestrate complex, multi-step agentic workflows, developers require a standardized format to specify agent capabilities, prompt instructions, system rules, and database bindings. This is where SKILL.md and the Model Context Protocol (MCP) have emerged as standard developer paradigms. SkillMD serves as the central directory for indexing, exploring, and sharing these critical agent configurations.
Our open-source registry currently tracks over 1.7 million collected SKILL.md configurations and system prompts. By compiling agent configurations from active developers on GitHub, we bridge the gap between prompt engineering research and production execution. Whether you are building agents with Anthropic's Claude Code, OpenAI's GPT-4, Google's Gemini, or local models using Ollama and LlamaIndex, standardized skill definitions ensure your agents behave predictably across different runtime environments.
What is the Model Context Protocol (MCP)?
The Model Context Protocol (MCP) is an open-source standard designed to connect LLMs to data sources, developer tools, and external environments. MCP establishes a bidirectional communication channel between client applications (like Cursor, Claude Desktop, or custom agent systems) and servers hosting data or capabilities. Standardizing instructions via SKILL.md enables LLMs to query databases, read local files, execute terminal commands, and integrate third-party APIs. SkillMD allows you to find ready-to-run MCP servers and prompt instructions for various occupations and technical tasks.
The Structure of a Professional SKILL.md File
A valid SKILL.md configuration is designed to be easily read by humans and parsed by LLMs. It contains precise system instructions, trigger conditions, required parameters, and execution examples. Below is the typical architectural blueprint of a professional agent skill:
- Metadata & Core Scope: Declares the name of the skill, author details, target models, and a description of the capability.
- Triggers & Intent Detection: Details semantic triggers that help the agent decide when to invoke this skill.
- System Prompts: Explicit system-level instructions that direct the agent's behavior, personality, safety guardrails, and formatting preferences.
- Capabilities & Tools: Lists the files, databases, or APIs the agent must access to complete the tasks.
- Few-Shot Examples: Demonstrates real inputs and outputs, helping the model generalize behavior through in-context learning.
Optimizing Agent Workflows for Modern LLMs
Writing effective agent skills requires deep knowledge of prompt engineering. With the release of advanced reasoning models like Claude 3.5 Sonnet, ChatGPT o1, and DeepSeek-V3, prompt templates must focus on structured thinking. Developers are encouraged to use XML tags (e.g., <thought>, <context>, and <rules>) to isolate execution boundaries. Standardized prompts prevent agents from suffering from context drift, ensuring that long-running tasks remain aligned with the initial system parameters.
Exploring by SOC Occupations and Creator Profiles
What makes SkillMD unique is its taxonomy. Instead of simple text search, we parse and organize files according to the Standard Occupational Classification (SOC) system. This means you can discover skills written for Computer and Mathematical roles, Business and Financial operations, Legal, Design, and and Educational Instruction fields. By tracking creator profiles, developers can study how different teams organize their custom instructions, compare version updates, and fork public configs for specialized enterprise use cases.
SkillMD operates as a high-performance index running on a fast Go backend and a highly responsive Astro SSR frontend. All search queries execute in milliseconds, featuring smart debouncing to prevent multiple API requests while keeping user data secure. Join our community of developers to standardize your AI agent instructions and optimize your LLM prompting workflows today.
Frequently Asked Questions
A practical guide to agent skills: what they are, how to inspect them, and how SkillMD helps you explore the ecosystem.