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...
sw-handoff
by anton-abyzovWrite a portable, secret-scrubbed work handoff doc so you can continue this work in any AI tool. Use when saying "handoff", "running out of tokens", "switch to Codex/OpenCode/Gemini/Cursor", "continue elsewhere", or "continue on another machine".
specweave-multi-repo-sync
by anton-abyzov[DEPRECATED] Use `sw:multi-project --tool github` instead. Organizes specs and splits tasks across multiple GitHub repositories. This skill will be removed in SpecWeave v1.3.0.
sw-multi-project
by anton-abyzovUnified multi-project management skill for GitHub, Azure DevOps, and Jira. Organizes specs and splits tasks across multiple repositories or projects for monorepo, polyrepo, project-per-team, and area-path architectures. Use `--tool github|ado|jira` to select the target integration.
sw-team-build
by anton-abyzov[DEPRECATED] Use sw:team-lead --preset <name> instead.
sw-analytics
by anton-abyzovAnalytics and metrics for SpecWeave usage — token consumption, cache efficiency, agent spawn counts.
close-all
by anton-abyzovBatch-close all complete increments by delegating each one to `sw:done`. Discovers active/ready-for-review increments with zero pending tasks, then iterates and calls `sw:done` per increment. Use when saying "close all", "close stuck increments", or "batch close".
sw-github-issue-standard
by anton-abyzov[DEPRECATED] GitHub issue formatting standard. See docs/internal/specs/github-issue-standard.md
anymodel
by anton-abyzovAnyModel development skill — the universal AI coding proxy. Use this skill whenever working on AnyModel source code (proxy.mjs, cli.mjs, providers/*, site/*, test/*), adding providers or presets, debugging proxy issues, deploying to npm, or modifying the anymodel.dev website. Also activate when the user mentions AnyModel architecture, proxy sanitization, tool schema fixing, Ollama integration, OpenRouter routing, client branding, or the deployment pipeline. Covers the full AnyModel lifecycle: code, test, publish, deploy.
anymodel
by anton-abyzovAnyModel development skill — the universal AI coding proxy. Use this skill whenever working on AnyModel source code (proxy.mjs, cli.mjs, providers/*, site/*, test/*), adding providers or presets, debugging proxy issues, deploying to npm, or modifying the anymodel.dev website. Also activate when the user mentions AnyModel architecture, proxy sanitization, tool schema fixing, Ollama integration, OpenRouter routing, client branding, or the deployment pipeline. Covers the full AnyModel lifecycle: code, test, publish, deploy.
tournament-manager
by anton-abyzovTournament manager for the EasyChamp platform. Use when the user wants to create or operate a sports league, tournament, or bracket — covers generating a league, spinning up a tournament under it, building the bracket, producing a schedule with venues, and entering match results. Activates for 'create a league', 'start a tournament', 'make a bracket', 'schedule matches', 'enter a score', 'record results', 'basketball tournament', 'soccer league', 'single-elim bracket', 'double-elimination', or any EasyChamp-related workflow. Backed by the EasyChamp MCP — requires an EASYCHAMP_API_KEY for live use, or EASYCHAMP_DEMO=1 for offline demos. Do NOT activate for non-sports scheduling (use a generic calendar skill instead) or for tournament-style brackets inside unrelated domains (e.g. 'coding challenge bracket' without EasyChamp — prompt for clarification).
survey-passing
by anton-abyzovFind and complete paid expert surveys from expert network platforms (Arbolus, Guidepoint, GLG, AlphaSights, Techsponential) using the user's real professional background. Automates the mechanical form-filling of expert consultations that pay $50-$100+. Use this skill whenever the user mentions surveys, canopy, expert consultations, Arbolus, Guidepoint, GLG, AlphaSights, 'find surveys', 'check surveys', 'complete survey', 'paid survey', 'expert network', 'canopy reward', or any reference to survey rewards/honorariums. Also activate when the user asks to check Gmail for survey invitations or mentions earning money from expertise sharing.
tax-filing
by anton-abyzovEnd-to-end corporate and personal tax preparation: data gathering from Xero/bank statements/Gmail/Obsidian/Google Drive, P&L generation, IRS compliance analysis, tax calculation, document staging, and payment guidance. Use this skill when the user mentions tax filing, tax preparation, P&L report, Form 1120, Form 1040, corporate tax, personal tax return, Sorsher, accountant meeting, tax deadline, estimated tax payment, IRS payment, extension filing, 1099, W-2, bank statement analysis for taxes, constructive dividends, home office deduction, or any tax-year financial preparation. Also activate when the user wants to analyze business expenses, calculate tax liability, prepare audit documentation, or generate invoices for foreign contractors. This skill handles both C-Corp (Form 1120) and personal MFJ (Form 1040) returns.
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.