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...
setup-github-labels
by wkentaroApplies one small canonical GitHub label set to the current repo, so every repo you run it in speaks the same label vocabulary: an issue `type:` axis (bug/feature/task, mirroring GitHub Issue Types), the five whose-turn triage roles (needs-triage/needs-info/ready-for-agent/ready-for-human/wontfix), and a PR-verdict axis (recommend-merge/recommend-close/recommend-triage). This skill owns the GitHub label objects (name, color, description); `setup-matt-pocock-skills` owns the triage roles' agent wiring. Use when setting up labels on a repo, or after editing this skill's canonical tables. Invoke explicitly; it is not auto-triggered.
make-branch
by wkentaroMove changes from main or a placeholder branch to a well-named feature branch, preserving commits and working tree state. Use before opening a PR when work started on main or an auto-generated branch name.
make-pr
by wkentaroPush the current branch and create or update a GitHub pull request with a good title, description, labels, and assignee. Use after the branch name is already conventional.
to-html
by wkentaroRender an explanation, analysis, plan, findings doc, or draft as a single self-contained HTML file (generous whitespace, sparse prose, diagram-first, one accent color) the user can open, screenshot, share, or copy from. Use when the user wants any standalone HTML document regardless of domain, e.g. says "explain this as html", "turn this into html", "visualize with html", or "make an html doc/report so I can review/discuss/copy". Content-agnostic; carries a fixed visual aesthetic.
exemplar-review
by wkentaroReview a diff against the best exemplars for its domain — checking both whether it reinvents a community-standard tool or idiom (prior-art), and whether it clears the quality bar a recognized exemplar would hold (excellence-bar, e.g. Apple-grade UI, Stripe-grade docs). Use when the user wants a taste, quality, or idiom pass, asks "is this <X>-grade?", "what would <person> think?", "are we reinventing the wheel?", "is there a standard way?", or runs /exemplar-review. Complements correctness/simplify/maintainability reviewers with the perspective they structurally lack.
review-fix
by wkentaroRun /code-review, /simplify, /brooks-review, /review, and /exemplar-review on a change via parallel subagents, address the meaningful findings, fold the fixes into clean commits, and force-push with lease. Use when the user wants to review-and-fix a change before merge — on uncommitted work, the current feature branch, or a GitHub PR / GitLab MR. Triggers include "review-fix", "review and fix this PR/MR", "polish this branch", or "run the reviews, address the suggestions, then force-push".
kaizen-codebase
by wkentaroRun one autonomous codebase-improvement pass on the current repo. Find the single highest-leverage, low-risk improvement (architecture, tech debt, dead code, test gaps, simplification) and either ship it as a draft PR or, when the change needs human judgment, file a ready-for-human issue. Does exactly one thing then stops, so it composes with /loop for recurring improvement (e.g. `/loop /kaizen-codebase` or `/loop 1d /kaizen-codebase`). Use when the user wants to continuously or periodically improve a repository, asks to "improve the codebase", set up a recurring code-quality agent, or run one improvement iteration.
recommit
by wkentaroReshape a branch's commits-that-aren't-in-main into a clean, logical, independently-valid sequence without changing the final tree — splitting grab-bag commits, folding fixups, ordering refactor-before-feature, dropping dead-infra commits — then stop (no push). Use when preparing a PR/MR branch for review or merge, cleaning up messy iterative history (review-fix amendments, fixups, interleaved refactors, WIP commits), or when the user says "clean up the git history", "tidy the commits", "recommit", or "make the history present nicely on the PR".
v
by wkentaroSignals that this message was dictated by voice, so technical terms may be mis-transcribed. Use when the user prefixes a dictated message with /v.
git-hunk
by wkentaroSplit uncommitted changes into focused, logical commits using git-hunk. Use when asked to "split changes", "split commits", "organize commits", "commit by hunk", or "separate changes into commits".
core
by wkentaroCore git-hunk usage guide. Read this before splitting changes into commits. Covers the list/show/stage workflow, stable content-based hunk IDs, grouping hunks into focused commits, ordering commits so each is independently valid, splitting a single hunk across commits by line, surgically dropping debug lines, re-splitting an already-committed branch, and fixing staging mistakes. Use when the user asks to split changes, split commits, organize commits, commit by hunk, separate a refactor from a feature, clean up a messy diff before committing, or untangle a working tree full of unrelated changes.
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.