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...
git-pr-creation
by marcioaltoeAutomatically creates comprehensive pull requests to the dev branch when user indicates their feature/fix is complete and ready for review. Use when user mentions creating PR, submitting for review, or indicates work is done. Examples - "create a PR", "ready for review", "open a pull request", "submit this to dev", "all tests passing, let's get this reviewed".
barrel-craft
by marcioaltoeExpert in barrel file generation and import organization. Use when user creates index.ts/tsx files, needs clean import paths, wants to organize exports, or mentions barrel files. Examples - "create barrel files", "generate index exports", "organize imports", "I created a new index.ts", "clean up barrel files", "update barrel exports".
quality-engineer
by marcioaltoeExpert in code quality, formatting, linting, and quality gates workflow. Use when user needs to setup quality tools, fix linting errors, configure Biome/Prettier, setup pre-commit hooks, or run quality checks. Examples - "setup code quality", "fix lint errors", "configure Biome", "setup Husky", "run quality checks", "format code", "type check errors".
test-engineer
by marcioaltoeExpert testing and quality engineer for Vitest (running on Bun). Use when user needs test creation, test strategy, code quality setup, E2E testing, or debugging test failures. Examples - "write tests for this function", "create E2E tests with Playwright", "help me test this API route", "setup testing infrastructure", "why is this test failing?", "improve code quality with Biome".
pull-request-skill
by marcioaltoePull Request review manager for CodeRabbit AI. **ALWAYS use when user needs to work with PR reviews, fix CodeRabbit issues, or check review status.** Downloads, organizes, and helps resolve review comments systematically. Examples - "download PR reviews", "fix CodeRabbit issues for PR 123", "check review status", "organize review comments by severity".
gesttione-design-system
by marcioaltoeExpert in Gesttione Design System with deep knowledge of brand colors, metric tokens, typography, and component patterns. **ALWAYS use for Gesttione projects when applying brand colors, creating metric visualizations, or building dashboard components.** Use when user needs Gesttione-specific styling, metric visualizations, dashboard components, or brand-compliant UI. Examples - "create revenue metric card", "use Gesttione brand colors", "design dashboard with metrics", "apply brand identity", "create metric visualization".
ui-designer
by marcioaltoeExpert UI/UX designer for React applications with shadcn/ui and Tailwind CSS. **ALWAYS use when creating UI components, implementing responsive layouts, or designing interfaces.** Use when user needs component creation, design implementation, responsive layouts, accessibility improvements, dark mode support, or design system architecture. Examples - "create a custom card component", "build a responsive navigation", "setup shadcn/ui button", "implement dark mode", "make this accessible", "design a form layout".
web-tests
by marcioaltoeComplete browser automation with Playwright. **ALWAYS use when user needs browser testing, E2E testing, screenshots, form testing, or responsive design validation.** Auto-detects dev servers, saves test scripts to working directory. Examples - "test this page", "take screenshots of responsive design", "test login flow", "check for broken links", "validate form submission".
git-commit
by marcioaltoeAutomatically analyzes code changes and creates git commits with conventional commit messages when the user indicates they want to save/commit their work. Use when user mentions committing, saving work, or wants changes recorded in git history. Examples - "commit these changes", "save this work", "I'm done with this feature, let's commit", "create a commit for the auth updates".
clean-architecture
by marcioaltoeClean Architecture principles for Modular Monolith with bounded contexts and minimal shared kernel. **ALWAYS use when working on backend code, ESPECIALLY when creating files, deciding file locations, or organizing contexts (auth, tax, bi, production).** Use proactively to ensure context isolation and prevent "Core Obesity Syndrome". Examples - "create entity", "add repository", "where should this file go", "modular monolith", "bounded context", "shared kernel", "context isolation", "file location", "layer organization".
code-standards
by marcioaltoeExpert in code design standards including SOLID principles, Clean Code patterns (KISS, YAGNI, DRY, TDA), and pragmatic software design. **ALWAYS use when designing ANY classes/modules, implementing features, fixing bugs, refactoring code, or writing functions.** Use proactively to ensure proper design, separation of concerns, simplicity, and maintainability. Examples - "create class", "design module", "implement feature", "refactor code", "fix bug", "is this too complex", "apply SOLID", "keep it simple", "avoid over-engineering".
error-handling-patterns
by marcioaltoeError handling patterns including exceptions, Result pattern, validation strategies, retry logic, and circuit breakers. **ALWAYS use when implementing error handling in backend code, APIs, use cases, or validation logic.** Use proactively for robust error handling, recovery mechanisms, and failure scenarios. Examples - "handle errors", "Result pattern", "throw exception", "validate input", "error recovery", "retry logic", "circuit breaker", "exception hierarchy".
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.