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...
hv-qa
by l4ciQA the built product — not the diff. Use on "/hv-qa", "run QA", "test the feature", "validate the build", before ship as a gate, or on first cycle to scaffold a per-repo strategy. Detects testing surfaces per repo (web, API, CLI, mobile, lib), picks runners (Playwright, smoke, contract, lighthouse, ZAP, axe), and produces a scored report with executable pass/fail results plus audit-style usability findings. Strategy is per-repo in .hv/qa/<repo>.md so the skill never hardcodes "browser". Modes — first-run (probe + propose strategy), run (execute strategy, emit verdict), restructure (audit strategy files). Opt-in gate via ship.qa.
hv-refactor
by l4ciRun a full architectural refactor cycle — explores the codebase for friction, categorizes dependencies, designs competing approaches for structural changes, then fixes everything with parallel subagents. Use when you want to find and fix architectural issues.
hv-release
by l4ciCut a release — walk the project's per-project release checklist (`.hv/RELEASE.md`) as a preflight gate, bump version (major/minor/patch), generate categorized release notes from commits since the last tag, prepend a section to CHANGELOG.md, create an annotated git tag, push, publish a release on GitHub or GitLab if origin is set, and offer to close any upstream issues still open for shipped items. Use on "release", "cut a release", "tag a release", "ship X.Y.Z".
hv-review
by l4ciStaff-engineer review of a feature branch before merge or PR — reads commits, diff, referenced item IDs, and matching KNOWLEDGE.md topics; dispatches an Opus reviewer that checks intent match, convention compliance, and quality. Returns PASS / CONCERNS / FAIL. Use on "review this", "check before I ship", "look over the branch", or implicitly from /hv-ship.
hv-ship
by l4ciBundle completed work on a feature branch into a PR (or direct merge) — extracts commits, resolved item IDs with titles, optionally runs /hv-review, and calls hv-pr or hv-merge. Use on "ship it", "open the PR", "finish this branch", when work is done and you want to integrate. Also supports --undo (guided rollback of the last cycle on the base branch, replaces /hv-undo) and --docs (public-docs maintenance, replaces /hv-docs). Use --undo on "roll back the last cycle", "revert that merge". Use --docs on "/hv-docs", "update docs"; auto-invoked post-cycle when docs/ exists.
hv-spike
by l4ciThrowaway feasibility experiment on a dedicated git branch — answers a specific question without polluting main or the backlog. Creates spike/<name> branch and .hv/spikes/<name>.md for question + findings + decision. Branch is never merged; only findings come back. Use when you need to try X before committing to it ("can we use SSE?", "does this library handle our scale?").
hv-update
by l4ciCheck for a newer hv-skills release on GitHub and tell the user how to update — detects install type (plugin, stow, repo clone), compares plugin.json version against the latest release, and prints the exact update command. Read-only; does not run the update itself. Use on "check for updates", "is hv-skills up to date", before long /hv-work sessions.
hv-vision
by l4ciBrainstorm a project's vision and break it into milestones — Socratic discovery, web research, deliberate challenge, then write MILESTONES.md and per-milestone detail files. Handles fresh vision and editing/extending an existing one. Use on "let's plan", "what's the bigger picture", "create a roadmap", "brainstorm milestones".
hv-work
by l4ciOrchestrator-driven parallel implementation — plans tasks, dispatches worker subagents, verifies, commits atomically per task. Supports branch or worktree isolation and direct merge or PR. Use when items already exist in BACKLOG.md and need implementation ("implement [B07]", "build these"); for an item not yet captured use /hv-go.
hv-brainstorm
by l4ciPer-item design exploration before /hv-plan — Socratic discovery, 2-3 approaches with tradeoffs, sectioned design with per-section approval, writes .hv/designs/<ID>.md, hands off to /hv-plan. Use when a Major feature or P0 bug needs design negotiation before implementation planning.
hv-capture
by l4ciCapture bugs, features, and tasks into BACKLOG.md without executing them. Classifies each item, assigns priority/size, mints zero-padded IDs ([B01], [F01], [T01]). Also supports `--remove <ID>[,<ID>...]` to delete captured items and clean up cross-references (dry-run + confirmation gate), and `--from-github` / `--from-gitlab` to pull open upstream issues into the backlog with `GH: #N` / `GL: #N` cross-refs and round-trip closing via `/hv-ship`. Use when the user brain-dumps work, says "capture", "add to backlog", "note this bug", "/hv-capture", "remove [B07]", "delete this entry", "drop this item", "/hv-rm", "import issues", "pull open issues from GitHub", "list issues", "/hv-issues", or describes a problem without asking for an immediate fix. Records only — for an immediate fix use /hv-go; for items already in BACKLOG use /hv-work.
hv-config
by l4ciChange hv-skills configuration interactively — pick which settings to edit from a checklist showing current values, then choose new values from the same options used at init. Also supports positional shortcuts: `/hv-config <key>` jumps to the value picker, `/hv-config <key>=<value>` applies directly. Use on "change config", "switch to worktree mode", "turn on autonomy", "edit settings".
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.