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...
tdd
by ojfbotMANDATORY: Load this skill IMMEDIATELY when user asks to "tdd", "red green refactor", "test first", "write the failing test", "enforce TDD on this change". Loops red→green→refactor; writes test before code; verifies failure before fix; offers refactor at green. Edits files. Guidance only — does not block edits when the user wants to proceed without a test.
gated-slice
by ojfbotDecompose a large agentic-harness effort into Control-Gated Slices (ADR-0086): independently shippable vertical slices, each delivered through ordered Control Gates with explicit Entrance + Success Criteria expressed as TPMs (MOE → MOP → TPM), with any enforcement/automation control required to mature through a Brassboard/shadow (observe-only) stage before going Operational, and promotion past each gate named as a data-gated RIDM decision. Use when the user says "gated-slice", "plan a big effort", "decompose this initiative", "how do I roll out this gate/enforcement", "shadow mode then enforce", "control gates", "slice this up", or when a task is too large for one PR and/or introduces an automated control that takes action. Output is a plan, not code: a slice breakdown + per-slice gates + TPMs + shadow-stage + RIDM promotion points. Distinct from /plan-feature (single-feature spec→test-matrix) and /orchestrate (agent-pipeline execution).
diagram-intake
by ojfbotMANDATORY: Load this skill when user uploads a photo of hand-drawn priorities, says "here are today's goals", "read my diagram", "interpret this photo", "morning priorities", "diagram intake", or provides an image with app/repo labels. Reads a hand-drawn priority diagram, maps goals to canonical repos, cross-references against roadmap and open blockers, outputs structured per-app priorities compatible with /frame-standup Step 7.
doc-refactor
by ojfbotMANDATORY: Load this skill IMMEDIATELY when user asks to "doc-refactor", "update the docs", "fix the README", "documentation is out of date", "normalize docs after refactor". Audits README, docs/, inline comments, and CLAUDE.md; updates stale content; generates Mermaid diagrams; structures docs/ canonically.
pr-review
by ojfbotMANDATORY: Load this skill IMMEDIATELY when user asks to "pr-review", "review this PR", "review PR #NNN", "code review". Structured PR audit combining code quality, security review, and educator perspective. Loads the diff, checks correctness, security, test coverage, and code quality. Use --comment for a standalone GitHub PR comment. Output: APPROVE | REQUEST CHANGES | BLOCKED.
push-all
by ojfbotMANDATORY: Load this skill IMMEDIATELY when user asks to "push-all", "commit my changes", "make a commit", "commit and push". Safe commit workflow with secret scanning and smart message drafting. Scans staged changes for secrets, warns on protected branches, drafts a commit message, and commits. Does not push to remote unless explicitly asked.
recon
by ojfbotMANDATORY: Load this skill IMMEDIATELY when user asks to "recon", "map the codebase", "understand this project", "get oriented", "what does this repo do", or mentions exploring an unfamiliar repo for the first time. Produces a dense technical overview: structure, entry points, stack, architecture patterns, data flows, notable observations. Read-only — no files modified.
resume-audit
by ojfbotMANDATORY: Load this skill IMMEDIATELY when user asks to "audit this resume", "check resume against job", "gap analysis", "match score", "resume audit", "how well does my resume match", "is my resume ready", "pre-submission check", "hiring manager sniff test". Structured audit of resume vs. JD with gap classification, adversarial probing, and tuning knobs. Output: scored matrix, gap analysis, and improvement recommendations.
setup-ci-cd
by ojfbotMANDATORY: Load this skill IMMEDIATELY when user asks to "setup-ci-cd", "add CI", "set up GitHub Actions", "add pre-commit hooks", "harden the pipeline". Auto-detects stack and generates: pre-commit hooks (lint/format/secrets), CI workflow (lint→typecheck→test→build), security workflow (SAST + audit), and coverage gates.
skill-loader
by ojfbotMANDATORY: Load this skill IMMEDIATELY when user asks to "skill-loader", "what skills are available", "load skills for this repo", "which commands do I have", "install skills", "what should I install", "set up skills for X", "remove unused skills". Meta-skill — enumerates the full skill catalog, fuzzy-matches purpose to relevant skills, and outputs install/remove commands. Tier 3.
test-expand
by ojfbotMANDATORY: Load this skill IMMEDIATELY when user asks to "test-expand", "what's not tested", "improve coverage", "write tests for X", "find coverage gaps". Tests only — never modifies implementation code. Use --write to emit actual test file additions in the repo's existing framework and style.
triage
by ojfbotMANDATORY: Load this skill IMMEDIATELY when user asks to "triage", "triage these issues", "label this backlog", "prioritize the issues", "apply triage labels". Severity/effort/domain rubric. Output: label set + ordered backlog. Optional --apply writes labels via gh.
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.