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...
product-evaluation
by roshansinghUse when evaluating product value, running low/medium/goldset validation, interpreting canonical validation reports, deciding the next highest-value KG/product gap, or before proposing the next validation-driven feature in this repository.
coverage-report
by roshansinghUse when the user asks to run, summarize, compare, or interpret SuperContext KG coverage metrics for a repo or fleet snapshot. Produces a deterministic `coverage-run.json` + `coverage-run.md` from the existing CLI and surfaces the smallest set of actionable findings (blocking contract flags, weakest cells, narrow next-PR recommendation). NOT for code-coverage tools like pytest-cov.
coverage-report
by roshansinghUse when the user asks to run, summarize, compare, or standardize SuperContext KG coverage metrics for one repo or a fleet. Builds or uses a snapshot, runs coverage metrics, generates coverage-run.json and coverage-run.md via the repo CLI, and summarizes the highest-value KG coverage gaps without hand-editing numbers.
pre-pr-semantic-review
by roshansinghRun before pushing PR updates in this repository, especially after changing extractors, normalization, query/evaluation logic, metrics, loaders, relink/snapshot code, endpoint/path reconciliation, config/YAML contracts, manifest producers/consumers, output-contract/packet-shape/budget code, or GitHub review fixes. Focuses on Copilot-style semantic bugs (Python/AST binding semantics, fail-closed behavior, source-order resolution, multiplicity, validation, path/filter semantics, metric scope correctness, trust-boundary drift) AND change-completeness failures (a new rule applied to only some sites, an inconsistent serialization/measurement unit, partial enum coverage, built-but-unwired code, docs drifting from changed behavior), plus regression tests.
supercontext-mcp
by roshansinghUse when planning, implementing, reviewing code, or analyzing SuperContext A/B trace reports with a SuperContext MCP server available. For broad planning, architecture, dependency, or impact questions, call planning_context before broad repo exploration when the task mentions a service, repo, symbol, package, endpoint, event channel, domain, file path, or changed files/ranges. Use exact primitive tools for exact caller, callee, service brief, or event producer/consumer questions. Use the trace-evaluation guidance for ab-report.md, ab-report.json, deltas.jsonl, or LangSmith run analysis.
supercontext-mcp
by roshansinghUse when planning, implementing, reviewing code, or analyzing SuperContext A/B trace reports with a SuperContext MCP server available. For broad planning, architecture, dependency, or impact questions, call planning_context before broad repo exploration when the task mentions a service, repo, symbol, package, endpoint, event channel, domain, file path, or changed files/ranges. Use exact primitive tools for exact caller, callee, service brief, or event producer/consumer questions. Use the trace-evaluation guidance for ab-report.md, ab-report.json, deltas.jsonl, or LangSmith run analysis.
safe-git-pr-workflow
by roshansinghUse for Git/PR work in this repository, especially staging, committing, pushing, creating PRs, resolving review comments, or recovering from git index/ref lock errors caused by sandboxed .git writes.
implement-debate
by roshansinghUse when the user asks Codex to implement a specific converged agent debate, apply a debate plan, or finish a debate end-to-end across one or more PRs in this repository. Orchestrates debate readiness checks, scoped implementation, semantic self-review, Claude pre-PR review, Copilot review loops, merge-to-main, and follow-up PR sequencing.
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.