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...
typegpu
by software-mansion-labsTypeGPU is type-safe WebGPU in TypeScript. Use whenever the user writes, debugs, or designs TypeGPU code: 'use gpu' shader functions, tgpu.fn, buffers, textures, bind groups, compute and render pipelines, vertex layouts, slots, accessors, and any TypeGPU API. Shader logic and CPU-side resources are tightly coupled - handle both sides here even if the user only mentions one (e.g. "how do I write a shader", "how do I create a buffer"). Trigger on any mention of typegpu, tgpu, "use gpu", TypedGPU, or WebGPU code written using TypeGPU's schema API (d.*, tgpu.*, std.*). Do NOT trigger for raw WebGPU (using GPUDevice/GPURenderPipeline directly without tgpu), WGSL-only questions, Three.js, Babylon.js, or WebGL.
gestures
by software-mansion-labsSoftware Mansion's best practices for gestures in React Native apps using React Native Gesture Handler. Use when implementing tap, pan, pinch, rotation, swipe, long press, fling, hover, drag, or any touch interaction. Trigger on: 'gesture handler', 'GestureDetector', 'tap gesture', 'pan gesture', 'pinch gesture', 'rotation gesture', 'long press', 'fling', 'hover gesture', 'swipe', 'pinch to zoom', 'drag', 'touch handling', 'Pressable', 'RectButton', 'Swipeable', 'DrawerLayout', 'VirtualGestureDetector', or any request to handle user touch input in a React Native app.
multithreading
by software-mansion-labsSoftware Mansion's best practices for multithreading in React Native apps using react-native-worklets. Use when running JavaScript on multiple threads, offloading heavy computation from the JS thread, communicating between runtimes, or sharing data across threads. Trigger on: 'worklet', 'worklets', 'react-native-worklets', 'runOnUI', 'runOnJS', 'scheduleOnUI', 'scheduleOnRN', 'scheduleOnRuntime', 'createWorkletRuntime', 'background thread', 'UI thread', 'worker runtime', 'Serializable', 'Synchronizable', 'multithreading', 'parallel execution', 'offload computation', 'background processing', 'Bundle Mode', or any request to move work off the JS thread in a React Native app.
on-device-ai
by software-mansion-labsBuild on-device AI features in React Native and Expo apps with React Native ExecuTorch. Use when adding AI to a mobile app without cloud dependencies — chatbots, image classification, object detection, OCR, semantic or instance segmentation, style transfer, image generation, pose estimation, speech-to-text, text-to-speech, voice activity detection, semantic search with embeddings, tokenization, privacy / PII redaction, or vision-language image understanding. Also use when mentioning offline / on-device / privacy AI, reducing cloud cost or latency, or managing ML models. Covers initExecutorch and every hook (useLLM, useClassification, useObjectDetection, useOCR, useSemanticSegmentation, useInstanceSegmentation, useStyleTransfer, useTextToImage, useImageEmbeddings, usePoseEstimation, useSpeechToText, useTextToSpeech, useVAD, useTextEmbeddings, useTokenizer, usePrivacyFilter, useExecutorchModule), tool calling, structured output, VLMs, Expo and bare resource-fetcher adapters, and error handling.
rich-text
by software-mansion-labsSoftware Mansion's best practices for rich text in React Native using react-native-enriched and react-native-enriched-markdown. Use when building rich text editors, formatted text inputs, Markdown renderers, or any feature requiring inline styling, mentions, links, structured text editing, or Markdown display. Trigger on: 'rich text editor', 'rich text input', 'text editor', 'react-native-enriched', 'react-native-enriched-markdown', 'EnrichedTextInput', 'EnrichedMarkdownText', 'formatted text input', 'WYSIWYG', 'mentions input', 'text formatting toolbar', 'markdown renderer', 'markdown display', 'render markdown', 'display markdown natively', 'LaTeX math', 'GFM tables', or any request to build rich text editing or Markdown rendering in React Native.
svg
by software-mansion-labsSoftware Mansion's best practices for SVG rendering in React Native apps using React Native SVG. Use when rendering vector graphics, icons, charts, illustrations, or any SVG content. Trigger on: 'react-native-svg', 'SVG', 'vector graphics', 'render icon', 'draw shape', 'chart', 'path', 'Svg component', 'SvgUri', 'SvgXml', 'SvgCss', 'FilterImage', 'SVG filter', or any request to display scalable vector content in a React Native app.
react-native-best-practices
by software-mansion-labsSoftware Mansion's best practices for production React Native and Expo apps on the New Architecture. MUST USE before writing, reviewing, or debugging ANY code in a React Native or Expo project. If the working directory contains a package.json with react-native, expo, or expo-router as a dependency, this skill applies. Trigger on: any code task in a React Native/Expo project, 'React Native', 'Expo', 'New Architecture', 'Reanimated', 'Gesture Handler', 'react-native-svg', 'ExecuTorch', 'react-native-audio-api', 'react-native-enriched', 'Worklet', 'Fabric', 'TurboModule', 'WebGPU', 'react-native-wgpu', 'TypeGPU', 'GPU shader', 'WGSL', 'svg', 'animation', 'gesture', 'audio', 'rich text', 'AI model', 'multithreading', 'chart', 'vector', 'image filter', 'shared value', 'useSharedValue', 'runOnJS', 'scheduleOnRN', 'thread', 'worklet', or any question involving UI, graphics, native modules, or React Native threading and animation behavior. Also use when a more specific sub-skill matches.
rnrepo
by software-mansion-labsBest practices for integrating and using RNRepo — Software Mansion's infrastructure for pre-built React Native library artifacts that reduces native build times by up to 2×. Use when setting up, configuring, or troubleshooting RNRepo in a React Native or Expo project. Trigger on: 'RNRepo', 'rnrepo', 'slow builds', 'build times', 'prebuilt artifacts', 'prebuilt libraries', '@rnrepo/expo-config-plugin', '@rnrepo/build-tools', 'prebuilds-plugin', 'rnrepo.config.json', 'DISABLE_RNREPO', 'packages.rnrepo.org', 'Maven prebuild', 'CocoaPods prebuild', 'xcframework prebuild', 'prebuild AAR', 'build from source', 'native compilation slow', 'Gradle plugin slow', 'pod install slow', 'CI build times'.
expo-horizon
by software-mansion-labsSoftware Mansion's guide for migrating Expo SDK apps to Meta Quest using expo-horizon packages. Use when adding Meta Quest or Meta Horizon OS support to an existing Expo or React Native project. Trigger on: Meta Quest, Horizon OS, Quest 2, Quest 3, Quest 3S, VR app, expo-horizon-core, expo-horizon-location, expo-horizon-notifications, build flavors for Quest, panel sizing, VR headtracking, Horizon App ID, quest build variant, isHorizonDevice, isHorizonBuild, migrate expo-location to Quest, migrate expo-notifications to Quest, Meta Horizon Store publishing, or any task involving running an Expo app on Meta Quest hardware.
radon-mcp
by software-mansion-labsBest practices for using Radon IDE's MCP tools when developing, debugging, and inspecting React Native and Expo apps. Use when interacting with a running app through Radon IDE - viewing screenshots, reading logs, inspecting the component tree, debugging network requests, reloading the app, or querying React Native documentation and library info. Trigger on: 'debug React Native', 'fix UI', 'network issues', 'build issues', 'Radon IDE', 'view screenshot', 'app logs', 'component tree', 'network inspector', 'reload app', 'React Native docs', 'library description', 'emulator', 'development viewport', 'view_screenshot', 'view_application_logs', 'view_component_tree', 'reload_application', 'view_network_logs', 'view_network_request_details', 'query_documentation', 'get_library_description', and every request involving live app inspection, debugging or development in a Radon IDE session.
animations
by software-mansion-labsProduction animation patterns for React Native using Reanimated 4, Skia, WebGPU, and TypeGPU. Covers CSS transitions, CSS animations, shared value animations, canvas animations with react-native-skia, GPU shader animations, layout animations, scroll-driven animations, interpolation, particle systems, procedural noise, SDF rendering, performance tuning, and accessibility. Trigger on: Reanimated, useSharedValue, useAnimatedStyle, withSpring, withTiming, withDecay, withRepeat, withSequence, CSS transition, CSS animation, layout animation, FadeIn, SlideIn, ZoomIn, LinearTransition, keyframe, interpolate, scrollTo, useFrameCallback, react-native-skia, Skia Canvas, Atlas, usePathInterpolation, usePathValue, useClock, useTexture, SKSL, interpolateColors, Picture API, canvas animation, sprite animation, WebGPU, react-native-wgpu, TypeGPU, GPU shader, WGSL, particle system, Perlin noise, SDF, Three.js, react-three-fiber, animation performance, or any request to animate UI in React Native.
audio
by software-mansion-labsSoftware Mansion's best practices for audio in React Native using react-native-audio-api. Covers audio playback (buffer sources, oscillators, streaming), recording (file, callback, graph), audio effects (gain, filters, delay, convolver, panner, waveshaper), real-time analysis and visualization, audio worklets (custom synthesis, UIRuntime/AudioRuntime), system integration (sessions, interruptions, permissions), and testing. Trigger on: react-native-audio-api, AudioContext, AudioRecorder, AudioBuffer, AudioBufferSourceNode, AudioBufferQueueSourceNode, OscillatorNode, StreamerNode, GainNode, BiquadFilterNode, DelayNode, ConvolverNode, StereoPannerNode, WaveShaperNode, AnalyserNode, AudioParam, AudioManager, PlaybackNotificationManager, RecordingNotificationManager, WorkletNode, WorkletSourceNode, WorkletProcessingNode, audio playback, record audio, microphone, waveform, audio visualization, audio streaming, audio worklet, or any React Native feature that captures, processes, or emits sound.
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.