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...
write-markdown-docs
by torrustGuide for writing Markdown documentation in this project. Covers GitHub Flavored Markdown pitfalls, especially the critical
write-unit-test
by torrustGuide for writing unit tests following project conventions including behavior-driven naming (it*should*\*), AAA pattern, MockClock for deterministic time testing, and parameterized tests with rstest. Use when adding tests for domain entities, value objects, utilities, or tracker logic. Triggers on "write unit test", "add test", "test coverage", "unit testing", or "add unit tests".
public-trackers-for-testing
by torrustPublic tracker targets for manual testing and debugging of tracker clients. Use when validating announce/scrape behavior against live services, comparing local vs public behavior, or diagnosing network timeouts. Triggers on "public tracker", "test against demo tracker", "debug tracker timeout", or "which tracker should I use".
manual-udp-download-completion-e2e
by torrustManual end-to-end verification of started -> completed peer lifecycle using tracker_client (unified) and tracker stats API. Use when contributors need to simulate a peer completing a download without running containerized qBittorrent E2E. Triggers on "manual e2e", "simulate peer completion", "udp started completed test", or "verify downloads increment manually".
manual-http-download-completion-e2e
by torrustManual end-to-end verification of started -> completed peer lifecycle using the HTTP tracker announce/scrape endpoints with curl (or browser for stats). Use when contributors want a fast, transparent simulation of download completion without containerized clients. Triggers on "manual http e2e", "http announce completed test", "simulate completion with curl", or "verify completed counter http".
review-task
by torrustReview a completed implementation task before push/PR. Validates issue-spec acceptance criteria, scope, tests, docs, and lint readiness on a local branch. Use when asked to verify issue completion without an open PR.
handle-secrets
by torrustGuide for handling sensitive data (secrets) in this Rust project. NEVER use plain String for API tokens, passwords, or other credentials. Use the secrecy crate's Secret<T> wrapper to prevent accidental exposure through Debug output, logs, and error messages. Call .expose_secret() only when the actual value is needed. Use when working with credentials, API keys, tokens, passwords, or any sensitive configuration. Triggers on "secret", "API token", "password", "credential", "sensitive data", "secrecy", or "expose secret".
handle-errors-in-code
by torrustGuide for error handling in this Rust project. Covers the four principles (clarity, context, actionability, explicit enums over anyhow), the thiserror pattern for structured errors, including what/where/when/why context, writing actionable help text, and avoiding vague errors. Also covers the located-error package for errors with source location. Use when writing error types, handling Results, adding error variants, or reviewing error messages. Triggers on "error handling", "error type", "Result", "thiserror", "anyhow", "error enum", "error message", "handle error", "add error variant", or "located-error".
review-pr
by torrustReview an existing pull request for the torrust-tracker project. Covers checklist-based PR quality verification, code style standards, test requirements, documentation, and review feedback. Use only when a PR already exists.
resolve-review-threads
by torrustResolve addressed GitHub pull request review threads for the torrust-tracker project. Use when asked to mark PR suggestions as resolved, resolve review comments, close addressed review threads, or clear Copilot review feedback after fixes are pushed. Triggers on "resolve PR threads", "mark suggestions as resolved", "resolve review comments", or "close addressed review threads".
process-copilot-suggestions
by torrustEnd-to-end workflow for processing and resolving all Copilot code review suggestions on a pull request in torrust-tracker. Use when asked to handle PR review feedback, process all copilot suggestions, audit and resolve review comments, or manage copilot-generated review threads. Triggers on "process copilot suggestions", "handle all PR feedback", "resolve copilot review", "audit PR suggestions", or "close all copilot comments".
fetch-review-threads
by torrustFetch unresolved GitHub pull request review thread IDs for the torrust-tracker project. Use when asked to find open PR review threads, list unresolved review comments, collect thread IDs before resolving suggestions, or inspect Copilot review feedback. Triggers on "fetch review threads", "list unresolved PR comments", "get review thread IDs", or "find open review suggestions".
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.