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...
usage-view
by ww-w-aiKnow exactly what you spent. Interactive HTML dashboard with cost breakdown, token usage, and 5-hour window timeline across all sessions
report-limit
by ww-w-aiMax plan hit the wall? 💀 Report your 5h window data — we're mapping the rate limit formula Anthropic won't publish
setup-statusline
by ww-w-aiLive token counter in your CLI. Shows real-time input/output/cache token counts in the Claude Code status bar
setup-git-lite
by ww-w-aiDisable Claude Code built-in git instructions and inject a curated 280-tok minimum via SessionStart hook. Saves ~2,200 tok/session + ~1,700 tok/call.
continue
by ww-w-aiCheaper and faster than /compact. Restores previous session context by reading transcripts directly — no LLM calls, no token cost
devmd-gap-analysis
by ww-w-aiCompare DevMD files against actual source code. Measures coverage, accuracy, and consistency with deterministic counting and evidence-backed findings.
devmd-guide
by ww-w-aiInteractive guide for writing DevMD files from scratch. Walks through files one by one in dependency order, asking the right questions to fill each template.
devmd-scan
by ww-w-aiAnalyze an existing codebase and generate DevMD spec files. Supports single-file or full-project mode. Language-aware discovery with self-verification.
cowork-commit
by ww-w-aiTrigger whenever the user asks to commit AND wants the commit message enriched with AI collaboration history. Creates a lightweight commit message (key decision highlights + link) and a full directive-log file with conversation transcript + recap. The key signal is the combination of (1) making a commit with (2) capturing how AI contributed. Trigger on phrases like commit with AI recap, attach collaboration history to commit, record AI work in commit, cowork-commit. DO NOT trigger for plain commits without AI documentation, standalone time-period recaps (use cowork-insights instead), PR reviews, or general git operations.
cowork-doc-init
by ww-w-aiOne-time bootstrap of an existing project's docs/ and source into the cowork-doc-sync taxonomy structure. After a detailed gap analysis, relocate docs to match the standard. Phase 1 = relocation only (no new creation, includes moving content between docs), Phase 2 = analyze source to create new docs (only after user approval). For ongoing maintenance use /cowork-doc-sync. Triggers: cowork-doc-init, /cowork-doc-init, init doc structure, relocate docs, organize existing docs, doc init, doc bootstrap
cowork-doc-sync
by ww-w-aiOngoing doc-sync skill that aligns a project's docs/ with the current code/decision state. Call once at the very end, after implementation/refactoring is complete. Enforces a numbered taxonomy (00-reference~99-misc) + status model (LIVING/ACTIVE/FROZEN) + migration rules. To fit an existing project into this structure for the first time, use /cowork-doc-init. Triggers: cowork-doc-sync, /cowork-doc-sync, sync docs, align docs, organize docs, doc sync, doc alignment
cowork-insights
by ww-w-aiInvoke for "/cowork-insights" command or when the user asks to summarize, review, or report on past Claude Code sessions. Analyzes sessions to show key prompts (verbatim), structured assessments (goal/outcome/friction), tool usage patterns, and actionable insights. Produces HTML report + shareable Markdown for Jira/Notion/Slack. Three report formats — full (deep narrative), standard (core insights), minimal (quick team share). Supports --from/--to with absolute (2026-03-01) or relative (7d, 2w, 1m) dates. Trigger on phrases like weekly status update, sprint recap, what did I do with Claude, AI usage patterns, session history, minimal recap, what I worked on today, share with team, cowork-insights. DO NOT invoke for active tasks (debugging, refactoring, code review, project setup) or for commit-time recaps (use cowork-commit instead).
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.