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...
ayjnt-workflows
by northclockPair an agent with a durable Cloudflare Workflow. Use when the user asks to "add a workflow", "run a long-running job", "extend AgentWorkflow", "make order processing durable", "retry with backoff", or "survive worker restarts". Creates `agents/<route>/workflow.ts` next to `agent.ts`; the framework wires the workflow binding, the typed RPC stub, and the GeneratedEnv field. Uses the `withWorkflow<typeof MyWorkflow>()(Agent)` mixin so the agent gets a typed `this.workflow(params)` shortcut with no magic binding strings. NO migrations — workflows are ephemeral execution containers; state lives in the paired Agent's DO.
ayjnt-middleware
by northclockAdd middleware to gate, log, or wrap responses for an ayjnt agent or a subtree of agents. Use when the user asks to "add middleware", "add auth", "rate limit", "log every request", "gate the admin subtree", or "wrap responses". Drops `middleware.ts` at the right folder level (root for everything, a sub-folder for a subtree, a `(group)/` for a non-URL-scoped grouping), uses the Hono-style `Context` + `next()` pattern, and confirms the chain order matches what the user expects.
ayjnt-overview
by northclockPrimer on the ayjnt framework — file conventions, what the codegen produces, the CLI surface, and where to find each feature. Use this when the user asks general "how does ayjnt work" / "what is ayjnt" / "how do I get started" questions, when they need to understand the layout of a freshly cloned ayjnt project, or as a default fallback when no more specific ayjnt skill matches. Detects ayjnt projects by the presence of an `agents/` directory or the `ayjnt` dependency in `package.json`.
ayjnt-rpc
by northclockCall agent methods — from another agent (typed DO RPC via `getAgent<T>`) or from a browser UI / catalog consumers (Cloudflare's `@callable()` decorator + `agent.stub.method()`). Use when the user says "call <agentB> from <agentA>", "inter-agent RPC", "call from the UI", "call from the browser", "agent.stub.method", "agent.call", "@callable decorator", or "advertise this method in the catalog". The framework treats the `@callable()` decorator as the single source of truth for both browser-callability and catalog inclusion. A legacy `/** @callable */` JSDoc tag exists as a fallback for the rare catalog-only case.
ayjnt-troubleshoot
by northclockDiagnose and fix common ayjnt failures. Use when the user reports a specific symptom — "useAgent doesn't work", "compatibility date error", "lockfile divergence", "404 on /<route>", "wrangler refuses to deploy", "basePath gotcha", "agent state is undefined", "renamed an agent and lost storage", or "inter-agent RPC returns [object Object]". Maps each symptom to its root cause and the one-line fix. Most failures map to gotchas with known resolutions; don't speculate when the symptom matches one of these.
ayjnt-voice
by northclockBuild a voice agent — streaming speech-to-text + text-to-speech over WebSocket via @cloudflare/voice. Use when the user asks to "make the agent talk", "add voice", "build a voice assistant", "use Workers AI for voice", or "add STT/TTS". Wraps the agent class in `withVoice(Agent)`, plugs in Workers AI STT + TTS providers, and generates a typed `useVoiceAgent` hook that respects ayjnt's URL shape (not the upstream PartySocket prefix).
ayjnt-email
by northclockMake an agent receive and reply to email. Use when the user asks to "make the agent handle email", "receive email", "reply to email", "add onEmail handler", "email-driven agent", or "support@ inbox to agent". Define `async onEmail(message)` on the agent and ayjnt wires Cloudflare Email Routing, generates the worker's `email()` handler, and adds a `send_email` binding so `replyToEmail` works.
ayjnt-mcp
by northclockBuild an MCP (Model Context Protocol) agent — an agent that exposes tools, prompts, or resources for LLM clients like Claude Desktop, Codex, or the @modelcontextprotocol/sdk TypeScript client. Use when the user asks to "build an MCP server", "expose tools to an LLM", "extend McpAgent", "register MCP tools", or "connect Claude Desktop to my agent". Generates `agents/<route>/agent.ts` that extends `McpAgent`, instantiates `McpServer`, and registers tools/resources/prompts via the SDK's helpers. Skips the normal `/<route>/<instance>` URL dispatch — McpAgent.serve() owns the transport.
ayjnt-new-agent
by northclockAdd a new agent to an ayjnt project. Use when the user asks to "create an agent", "add an agent at /<route>", "scaffold a new agent", or similar. Drops `agents/<route>/agent.ts` with the correct base class, env, and state shape, makes sure the URL maps the way the user expects, and decides whether to also add `app.tsx`, `docs.md`, middleware, or RPC methods based on what the user said. Triggers in any project with an `agents/` folder and an `ayjnt` dependency.
ayjnt-add-ui
by northclockAdd a co-located React UI to an existing ayjnt agent. Use when the user asks to "add a UI", "add app.tsx", "co-locate a React component", or "render a page for the <agent> agent". Drops `agents/<route>/app.tsx` next to the existing `agent.ts`, uses the typed `useAgent()` hook ayjnt generates per agent, makes sure `react` + `react-dom` + their types are in `package.json`, and confirms the project's `tsconfig.json` extends the framework path aliases.
ayjnt-browser
by northclockAdd Browser Rendering tools to an agent with one import. Use when the user asks to "let the agent browse the web", "add browser tools", "search the web", "use Cloudflare Browser Rendering", or "give the LLM access to a browser". One import of `browserTools` from `ayjnt/browser` triggers the framework to wire BROWSER, LOADER, AI, and `nodejs_compat` into wrangler.jsonc — and the helper returns an AI-SDK ToolSet you can pass straight to `generateText`.
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.