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...
vercel-ai-sdk
by durable-streamsVercel AI SDK integration with Durable Streams. createDurableChatTransport() for useChat(), toDurableStreamResponse() for server-side streaming, resumable chat sessions with reconnectToStream(), read proxy pattern for auth. Load when building chat apps with Vercel AI SDK (@ai-sdk/react) and durable streams.
yjs-getting-started
by durable-streamsFirst-time setup for @durable-streams/y-durable-streams. Install peer deps, start dev servers (DurableStreamTestServer + YjsServer), create a collaborative Y.Doc, connect with YjsProvider, verify sync, add awareness for presence. Load when setting up Yjs collaborative editing for the first time.
yjs-server
by durable-streamsDeploy Yjs collaborative editing. YjsServer setup with compaction threshold, Caddy reverse proxy with flush_interval -1 for SSE, 3-layer architecture (Browser → Caddy → YjsServer → DS Server), Electric Cloud managed alternative with @electric-sql/cli provisioning. Load when deploying y-durable-streams to production or configuring server infrastructure.
yjs-sync
by durable-streamsYjsProvider deep-dive for @durable-streams/y-durable-streams. Provider options, connection lifecycle (connect, disconnect, destroy), synced/status/error events, connection state machine, dynamic auth headers, liveMode (sse vs long-poll), error recovery behavior. Load when configuring provider behavior beyond basic setup.
yjs-editors
by durable-streamsIntegrate Yjs collaborative editing with TipTap v3 and CodeMirror 6 over durable streams. Canonical React pattern: doc+awareness in useState, provider in useEffect with connect:false (listeners before connect). TipTap: Collaboration + CollaborationCaret extensions, -caret not -cursor package. CodeMirror: yCollab binding. Covers awareness wiring, multi-document navigation with key={docId}, SSR ssr:false requirement. Critical anti-patterns that crash agents documented.
writing-data
by durable-streamsWriting data to durable streams. DurableStream.create() with contentType, DurableStream.append() for simple writes, IdempotentProducer for high-throughput exactly-once delivery with autoClaim, fire-and-forget append(), flush(), close(), StaleEpochError handling, JSON mode vs byte stream mode, stream closure. Load when writing, producing, or appending data to a durable stream.
tanstack-ai
by durable-streamsTanStack AI integration with Durable Streams. durableStreamConnection() for useChat(), toDurableChatSessionResponse() for server-side streaming, SSR hydration with materializeSnapshotFromDurableStream(), multi-client sync with live: true, chunk sanitization, read proxy pattern. Load when building chat apps with TanStack AI (@tanstack/ai-react) and durable streams.
go-to-production
by durable-streamsProduction readiness checklist for durable streams. Switch from dev server to Caddy binary, configure CDN caching with offset-based URLs, Cache-Control and ETag headers, Stream-Cursor for cache collision prevention, TTL and Stream-Expires-At for stream lifecycle, HTTPS requirement, request collapsing for fan-out, CORS configuration. Load before deploying durable streams to production.
server-deployment
by durable-streamsRunning durable stream servers. DurableStreamTestServer for development (Node.js, @durable-streams/server, not for production), Caddy plugin for production with Caddyfile configuration, data_dir for file-backed persistence, max_file_handles tuning, long_poll_timeout, server binary downloads for macOS Linux Windows, @durable-streams/cli tool setup, conformance test runner.
forking
by durable-streamsCreating and using forked streams. Fork a source stream at a specific offset using Stream-Forked-From and Stream-Fork-Offset headers via DurableStream.create(). Reads transparently stitch inherited and fork data. Covers fork creation, fresh handle pattern, TTL/expiry inheritance, content-type inheritance, and deletion lifecycle. Load when forking, branching, or creating a stream variant from an existing stream.
getting-started
by durable-streamsFirst-time setup for Durable Streams. Install @durable-streams/client, create a stream with DurableStream.create(), read with stream(), subscribe to live updates, resume from saved offsets. Covers offset semantics ("-1", "now", opaque tokens), LiveMode (false, true, "long-poll", "sse"), and StreamResponse consumption (.json(), .text(), .subscribeJson()).
reading-streams
by durable-streamsAll stream reading patterns for @durable-streams/client. stream() function, DurableStream.stream(), LiveMode (false, true, "long-poll", "sse"), StreamResponse state machine, .json(), .text(), .jsonStream(), .textStream(), .subscribeJson(), .subscribeBytes(), .subscribeText(), SSE resilience with auto-fallback to long-poll, visibility-based pause, binary SSE base64 auto-decode, dynamic headers for auth token refresh, backoff config, StreamErrorHandler onError for error recovery.
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.