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...
butflow
by assistant-uiUse when the user asks for butflow mode, wants GitButler-driven implementation flow, or asks to implement a change through PR creation, CI monitoring, review-thread resolution, and merge in the assistant-ui monorepo.
trusted-publishing
by assistant-uiConfigure npm trusted publishing (OIDC) and lock down publishing access for a newly added publishable package in the assistant-ui monorepo. Use whenever a new public package is created under packages/* (a new package.json with `"private": false` / a new name on npm), when a release fails a package with an npm trusted-publishing / OIDC authorization error, or when the user asks to set up OIDC / trusted publishing / disallow tokens for a package.
update-deps
by assistant-uiUpdate dependencies across the assistant-ui monorepo (npm via pnpm + taze, Expo SDK-pinned packages, Python packages via uv, and GitHub Actions). Use when the user asks to bump, upgrade, or update dependencies (root, packages, examples, templates, python/*, .github/workflows/*), refresh the pnpm lockfile or uv.lock files, repin GitHub Actions, or run the dependency-update workflow before a release.
assistant-ui
by assistant-uiAdd, configure, and integrate assistant-ui components in React apps. Use when developers ask to add a chat thread, set up a runtime, integrate with AI SDK, configure tools, or build AI chat interfaces with assistant-ui.
tap
by assistant-uiUse this skill whenever you write or review code that uses `@assistant-ui/tap` or `@assistant-ui/store` in the assistant-ui monorepo: resources, React hooks inside resource bodies, `useResource`/`useResources`/`useTapRoot`, `useClientResource`/`useClientLookup`/`useClientList`, `useAui`/`useAuiState`/`useAuiEvent`, `ScopeRegistry`, `Derived` child scopes, `attachTransformScopes`, `useAssistantClientRef`/`useAssistantEmit`, or any new package exposing a store scope. Read first to avoid the recurring mistakes catalogued below.
tool-ui
by assistant-uiFind, install, configure, and integrate Tool UI components in React apps using shadcn registry entries, compatibility checks, scaffolded runtime wiring, toolkit setup with assistant-ui, and troubleshooting workflows. Use when developers ask to add one or more Tool UI components, choose components for a use case, verify compatibility, wire a toolkit in a codebase, or integrate Tool UI payloads into assistant-ui or an existing chat/runtime stack.
runtime
by assistant-uiGuide to the assistant-ui runtime system, single-thread state, and the imperative runtime API in @assistant-ui/react. Use when creating a runtime (useLocalRuntime with a ChatModelAdapter, useExternalStoreRuntime for Redux/Zustand, useRemoteThreadListRuntime), wiring AssistantRuntimeProvider, or reading/mutating thread, message, and composer state and events. Covers the unified hooks useAui, useAuiState, useAuiEvent (composer.send, thread.runStart, thread.runEnd), legacy hooks (useAssistantRuntime, useThreadRuntime, useMessageRuntime, useComposerRuntime, useThread, useThreadMessages), the AssistantRuntime/ThreadRuntime/MessageRuntime/ComposerRuntime hierarchy, thread operations (append, cancelRun, message().edit/reload), capabilities, and types (ThreadMessage, MessagePart, MessageStatus, ChatModelRunResult). Use for provider "Cannot read property of undefined" errors or state not updating. For multi-thread list UI and switching between conversations use thread-list instead.
setup
by assistant-uiInstalls and configures assistant-ui in a project via the CLI, and picks the right runtime for a backend. Use for first-time install, scaffold, or config: `npx assistant-ui@latest create my-app` (templates default, minimal, cloud, cloud-clerk, langgraph, mcp), `npx assistant-ui@latest init [--yes] [--overwrite]` in an existing Next.js app, or `npx assistant-ui@latest add` registry components (markdown-text, thread-list). Also use to choose a runtime hook for a backend: useChatRuntime (AI SDK), useLangGraphRuntime, useAgUiRuntime, useA2ARuntime, useLocalRuntime (custom streaming API), or useExternalStoreRuntime (Redux/Zustand). Covers Vite/TanStack Start setup, shadcn styling, the playground --preset flag, and avoiding the deprecated @assistant-ui/styles and @assistant-ui/react-ui packages. For upgrading an existing install or post-upgrade breakage use update; for building UI from raw parts use primitives.
streaming
by assistant-uiStreaming backends and wire protocols for assistant-ui via the assistant-stream package. Use when building a custom (non-AI-SDK) streaming endpoint with createAssistantStreamResponse or createAssistantStreamController, emitting parts through appendText/appendReasoning/appendSource/appendFile/addToolCallPart and setResponse; choosing between the AI SDK Data Stream format (toUIMessageStreamResponse) and the native Assistant Transport format; encoding or decoding streams with DataStreamEncoder/DataStreamDecoder, AssistantTransportEncoder/AssistantTransportDecoder, PlainTextEncoder, or UIMessageStreamDecoder; or wiring streamed chunks into useLocalRuntime or useChatRuntime. Use specifically for debugging stream wire issues: text-delta, part-start, result events, text/event-stream content-type, SSE format, tool calls not rendering, or partial text not showing. For general non-stream debugging route to the relevant focused skill, not the parent overview.
thread-list
by assistant-uiImplements multi-thread (conversation history) management in assistant-ui apps: rendering the prebuilt `ThreadList` next to `Thread`, or building a custom sidebar with `ThreadListPrimitive` and `ThreadListItemPrimitive` (Root, New, Items, Trigger, Title, Archive, Unarchive, Delete). Covers thread CRUD through the `useAui()`/`useAuiState()` API: `switchToThread`, `switchToNewThread`, and per item `rename`, `archive`, `unarchive`, `delete`, `generateTitle`, `initialize`, plus reading `s.threads.threadIds`/`archivedThreadIds`/`mainThreadId`. Includes cloud-backed persistence via `useChatRuntime` + `AssistantCloud` and a local `useRemoteThreadListRuntime` + `InMemoryThreadListAdapter` path. Use when a user wants a thread list/sidebar, switching, searching, sorting, drag-and-drop, or renaming/archiving/deleting conversations. For single-thread state, messages, or composer use runtime; for cloud auth/persistence setup use cloud.
tools
by assistant-uiRegisters LLM tools and renders custom tool-call UI in assistant-ui (@assistant-ui/react). Use when adding frontend-only tools with makeAssistantTool / useAssistantTool (browser actions like clipboard, navigation, localStorage, async-generator streaming, AbortSignal), rendering backend AI SDK tool() calls with makeAssistantToolUI / useAssistantToolUI (status.type running/complete/incomplete/requires-action, args, result, artifact via ToolCallMessagePartProps), building generative UI from tool results, or implementing human-in-the-loop and approval flows (addResult, resume with context.human(), respondToApproval for server-side needsApproval gates). Covers registering tool components inside AssistantRuntimeProvider and the case-sensitive toolName matching that connects a tool to its UI. Reach for this when tool UI is not rendering, a tool is not being called, or a result is not showing.
update
by assistant-uiUpgrades an existing assistant-ui project to current releases and executes the resulting migrations. Use when the user wants to update, upgrade, bump, or migrate @assistant-ui/react, @assistant-ui/react-ai-sdk, ai, or @ai-sdk/react, hits peer-dependency conflicts or post-upgrade type errors, or must apply renamed APIs after a version jump. Detects installed versus latest versions via npm ls / npm view, then routes through breaking-change references for each jump (AI SDK v4/v5 to v6; assistant-ui 0.8.x to 0.14.x): useAssistantApi to useAui, runtime.threadList to runtime.threads, ThreadPrimitive.ViewportSlack removal, the primitives components prop to children render functions, toDataStreamResponse to toUIMessageStreamResponse, maxSteps to stopWhen: stepCountIs(n). Runs npx assistant-ui@latest upgrade, pnpm/npm add @latest, and npx tsc --noEmit to verify. For a first-time install or fresh scaffold (not an upgrade) use setup instead.
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.