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...
example-data-processor
by fkeshehProcess CSV data files by cleaning, transforming, and analyzing them. Use this when users need to work with CSV files, clean data, or perform basic data analysis tasks.
docs
by fkeshehManage C4-model documentation hierarchies with SHA-tracked source-file references and bottom-up staleness propagation. Use this skill whenever the user wants to audit doc/code drift, find stale documentation, sync docs after a refactor, scaffold a docs tree with init, check doc coverage, find orphan source files (code that no doc references), add a new code-level doc, regenerate aggregator overviews from leaves, or wire a pre-commit/CI doc-staleness gate. TRIGGER on phrases like "are docs stale", "doc coverage", "docs drifted", "init docs", "C4 docs", "fmk docs", "doc audit", "which docs need updating", "regenerate the container overview", "find uncovered files", "fmk-docs check", "fmk-docs orphans", or any mention of `docs/.fmk-docs.yml`. SKIP for prose-only docs with no source-file linkage, generated API reference docs (typedoc/sphinx), or single-file READMEs that don't follow C4 hierarchy.
plan
by fkeshehCreate detailed implementation plans backed by research AND a mandatory clarification dialog. Before writing any plan content, every open question, undefined term, ambiguity, missing constraint, or scope edge must be resolved with a citation — an explicit user answer (recorded verbatim) or codebase/external evidence (file:line or doc URL). Plans built on assumptions or "reasonable defaults" are forbidden. The skill iterates a Q&A loop with the user until the open-question table has zero OPEN rows; in parallel, sub-agents research code- and external-answerable items. Produces a phased plan at docs/plans/ with SHA-tracked references and embeds the resolved questions table in the plan body as a permanent audit trail. TRIGGER on "create a plan", "plan the implementation", "write an implementation plan", "/plan", "plan this feature", "how should we implement". SKIP for trivial single-file edits, plans the user explicitly opts out of clarification on, or when the user provides a fully-specified plan and only asks f
analyze-pr-comments
by fkeshehAnalyze and address all review comments on a pull request. Fetches unresolved comments via GitHub GraphQL API, reads code context for each, evaluates validity, makes necessary changes or drafts polite responses. Also handles replying to PR threads with auto-linkable commit hashes. TRIGGER on "analyze PR comments", "address PR review", "resolve PR feedback", "check PR comments", "reply to PR review".
research
by fkeshehResearch codebase comprehensively and emit SHA-tracked, line-referenced research docs at docs/research/. Decomposes the user's question, spawns parallel sub-agents to investigate, synthesizes findings with concrete file:line references, computes git hash-object SHA for every referenced source file, and writes a YAML-frontmatter doc. If a doc with the same topic/slug already exists, UPDATES that doc instead of duplicating (refreshes SHAs, appends a Follow-up Research section). Companion to the `docs` plugin (C4 docs). TRIGGER on phrases like "research X", "investigate Y", "deep dive into Z", "how does X work in this codebase", "audit X", "explore the codebase for X", "/research". SKIP if the user only wants a quick answer with no doc artifact, or for non-codebase questions.
green
by fkeshehTDD GREEN phase for ONE slice. With a failing test already in place (from /red), writes the MINIMAL implementation — the vertical walking skeleton (route → data → server/stub → render → mutation) — to make the slice's E2E pass, mirroring the repo's patterns and staying inside the editable scope. Does inner unit red→green cycles for pure logic. Commits the working feature. Second step of /red → /green → /refactor. Trigger: /green (optionally /green slice-X).
presubmit
by fkeshehFinal pre-submission gate + grading panel. First runs ALL the repo's real checks (typecheck, lint, format, unit, build, and the full E2E suite incl. regression) with no masking. Then spins one subagent per EVALUATED ASPECT — the FULL set the brief names (functional completeness, frontend fluency, monorepo awareness, convention consistency/pattern fidelity, code quality, server-communication & state/data-flow, testing, commit hygiene & history, scope & regression discipline, AI-leveraged understanding) — to grade with file:line evidence. Produces a scorecard + prioritized fixes + a go/no-go. Run before declaring a task done. Trigger: /presubmit.
red
by fkeshehTDD RED phase for ONE slice. Writes the failing acceptance test (the slice's happy-path E2E) for docs/slices/slice-X.md, meeting the assessment's test criteria (meaningful, mirrors repo conventions, strict assertions), and confirms it fails for the RIGHT reason before any code is written. Commits the failing test. First step of the controllable /red → /green → /refactor loop. Use to start a slice test-first. Trigger: /red (optionally /red slice-X).
refactor
by fkeshehTDD REFACTOR phase for ONE slice. With tests GREEN, improves the slice's code WITHOUT changing behavior so it adheres to the assessment rules: strict TypeScript (no any), lint-clean, mirrors the repo's conventions and the traced feature, reuses shared packages, no new deps, stays in scope. Keeps tests green after each step, then runs the full gate incl. the regression E2E suite. Commits the cleanup (skipped if nothing changed). Final step of /red → /green → /refactor. Trigger: /refactor (optionally /refactor slice-X).
to-c4
by fkeshehGenerate a C4-model architecture map of a codebase as Structurizr DSL (docs/c4/workspace.dsl) — Context / Container / Component levels — so the system is graspable at a glance. Reuses docs/wiki (workspaces → containers, server-communication → relationships) if present; bundles a Docker helper (c4.sh) to validate the DSL, view it live in the Structurizr UI, and export Mermaid to embed in the wiki or a PR. Stack-agnostic. Trigger: /to-c4.
to-slices
by fkeshehBreak an assessment task into ordered VERTICAL slices (walking skeletons), each independently testable end-to-end, written to docs/slices/slice-1.md, slice-2.md, … The user sets the rough slice count by task complexity. Each slice touches every architectural layer (route → data → server call/stub → render → mutation) and ships with its own happy-path E2E. Reads the codebase map from docs/wiki/ (run /to-wiki first) to mirror real patterns and respect scope. Plan-first: proposes the slice breakdown for sign-off BEFORE writing the slice docs. Trigger: /to-slices.
to-wiki
by fkeshehMap an unfamiliar codebase into a fast, navigable local wiki (docs/wiki/) using parallel subagents. Built for the start of a live coding assessment on an UNKNOWN monorepo: discovers the stack, workspaces, conventions, server-communication style, testing setup, scope boundaries, and traces one reference feature end-to-end — so you can read the repo fluently and mirror its patterns. Pages carry YAML frontmatter with a per-source SHA1 freshness signal (detect + refresh stale pages after the code changes). Use at the very start, or whenever you are dropped into a strange repo and need a map before writing code. Trigger: /to-wiki.
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.