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...
smithery-homepage
by smithery-aiBuild and edit the Smithery homepage app -- a TanStack Start + shadcn/ui web app at ~/.smithery/homepage that connects to MCP servers through the Smithery Connect API. Use this skill whenever the user wants to create, modify, or add features to the Smithery homepage, build pages that display data from MCP tools (Linear issues, Gmail, Notion, etc.), or asks about editing anything in ~/.smithery/homepage. Also triggers for requests like 'add a page to the homepage', 'show my Linear issues on the homepage', 'update the homepage UI', or any task involving the ~/.smithery/homepage project.
smithery-ai-cli
by smithery-aiFind, connect, and use MCP tools and skills via the Smithery CLI. Use when the user searches for new tools or skills, wants to discover integrations, connect to an MCP, install a skill, or wants to interact with an external service (email, Slack, Discord, GitHub, Jira, Notion, databases, cloud APIs, monitoring, etc.).
setup-agentpw
by smithery-aiSet up agent.pw credential management in agent applications. Use when adding credential storage, OAuth flows, API key management, or auth header resolution to an agent platform. Triggers on "set up agent.pw", "add agent.pw", "integrate agent.pw", "credential management", "store credentials", "OAuth for agents", "connect external APIs", or when building agent apps that need to call authenticated external APIs on behalf of users.
mcp-cli
by smithery-aiHow to use the mcp-to-cli command-line tool to connect to remote MCP servers and interact with their tools, resources, and prompts. Use this skill whenever the user wants to connect to an MCP server from the terminal, call MCP tools via CLI, manage MCP connections, list or invoke tools/resources/prompts on a remote server, or debug MCP server interactions. Also use this when the user mentions "mcp-to-cli", asks about CLI-based MCP workflows, or wants to script MCP tool calls.
effect-doctor
by smithery-aiDiagnose and improve Effect-TS code against canonical patterns. Use whenever the user is writing, reviewing, refactoring, or debugging code that imports from `effect`, `@effect/*`, or a project built on Effect (like effectctx). Covers Layer composition, Service/Context.Tag, error channels with Data.TaggedError, Scope and resource management, Stream/Queue/PubSub, Schema decoding at boundaries, fiber management, tracing with withSpan, and the anti-patterns that experienced Effect users keep flagging (missing `yield*`, unbounded concurrency, providing Layers twice, accessor R-leakage, etc.). Trigger on phrases like "review my Effect code", "is this idiomatic Effect", "audit the Layer composition", "why is this fiber not interrupting", "what's the right error type here", "convert this Promise code to Effect", or any task that involves writing non-trivial Effect-TS code where idiom matters.
agentjsx
by smithery-aiAuthoring and diagnosing code in the agentjsx codebase (npm package `@flamecast/agentjsx`, locally at `/Users/arjun/Documents/github/effectctx`). The library lets you define an agent as a JSX tree — capability components install tools, block components emit prompt content, shaper components transform via `renderChildren`. Use whenever the user is writing new components (capability, content, or shaper), adding a new extension, debugging the render walk or tool reconciler, asking how a piece of agentjsx works internally, or referencing JSX patterns like `useRenderContext`, `runEffect`, `emitTool`, `emitFragment`, `renderChildren`. Also trigger on filenames in `src/jsx/`, `src/core/`, `src/platforms/`, `src/extensions/`, or any task touching `@flamecast/agentjsx` imports. Use proactively when you see `createAgentRuntime`, `<Workspace>`, `<Compact>`, `<McpServer>`, `<Skills>`, `<Todo>`, or any other agentjsx component in code — that's the strong signal you should consult this skill before authoring more.
unicorn-or-bust
by smithery-aiStart the Unicorn or Bust game. Use this skill when a user wants to play the Unicorn or Bust game - a choose your own adventure game where you play as a startup founder navigating challenges to build a unicorn. The game is powered by the unicorn-or-bust MCP server with dynamic challenges, resource management (runway, morale, product, investor hype), and stat progression.
mcp-oauth
by smithery-aiAuthenticate with any OAuth 2.1 MCP server. Handles discovery, PKCE, dynamic client registration, local callback server, token exchange, and authenticated requests. Use when connecting to OAuth-protected MCP servers, testing MCP tools, or debugging auth flows. Accepts an MCP server URL as argument.
mcp-oauth-debug
by smithery-aiMCP OAuth compliance simulator — walks the exact path a real client would (unauthenticated probe → 401 challenge → discovery → registration → authorization → token exchange → MCP calls) and reports spec compliance at each step. Use when investigating auth failures, testing server compliance, or onboarding new OAuth MCP servers. Triggers on "debug oauth", "test oauth flow", "oauth compliance", "oauth-debug", "why is auth failing".
ask-codex
by smithery-aiGet an independent opinion from OpenAI Codex CLI (GPT 5.4 model) on a design decision, code review, or debugging hypothesis. Use when you want a second opinion from a different model, need to challenge your own approach, or want to validate a fix before committing. Triggers: "ask codex", "get codex opinion", "what does codex think", "second opinion", or when /ask-council invokes it.
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.