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...
dev10x-spec-sync
by Dev10x-GuruInverse Golden Rule path: when code is refactored without behaviour changes, update the canonical spec at docs/specs/<TICKET-ID>.md to match the new code shape. Regenerates Architecture / Implementation Steps / Code References sections, leaves Requirements / Entities / Norms / Safeguards untouched. Bails to Dev10x:spec-update if it detects behavioural drift. TRIGGER when: a structural refactor (rename, file move, signature change) ships and the canonical spec must be re-aligned with the new code shape. DO NOT TRIGGER when: behaviour changes (use Dev10x:spec-update); spec is missing (use Dev10x:ticket-scope); no canonical spec workflow is in use (regular Dev10x:work-on applies).
dev10x-plan-sync
by Dev10x-GuruReconcile persisted plan file with in-session task list. Detects divergences, recreates missing tasks, and updates plan context. TRIGGER when: session resumed after compaction and task list is empty or out of sync with the plan file. DO NOT TRIGGER when: no plan file exists or task list is already in sync with the current session work.
dev10x-afk
by Dev10x-GuruWalk-away mode — harden adaptive + solo-maintainer auto-advance so long-running sessions do not stall on re-strategy or confirmation gates. Writes walk_away: true and doubt_sink: pr-description to .claude/Dev10x/session.yaml; downstream skills consult the flag and route mid-flight doubts to the PR body instead of pausing. TRIGGER when: starting a long-running unattended session (e.g., bundle work, fanout swarm, overnight implementation), or user says "walk away" / "afk" / "headless" / "no more questions". DO NOT TRIGGER when: actively pair-programming, scoping a new ticket (use Dev10x:ticket-scope), or session is already complete.
dev10x-gh-pr-review
by Dev10x-GuruReview a GitHub pull request and post findings with inline comments. Fetches PR diff, reads changed files, checks for interface impact, applies project review guidelines, and posts a review to GitHub. Supports Draft (PENDING) and submitted review modes via Step 8a gate. Supports courtesy-fixup disposition: mechanical, unambiguous findings may be pushed as fixup! commits with reviewer consent (Step 5b/6b). TRIGGER when: reviewing an external PR and posting review comments. DO NOT TRIGGER when: reviewing own branch changes before PR creation (use Dev10x:review), or PR does not exist yet.
dev10x-diag-friction
by Dev10x-GuruDiagnose permission friction. Guide the agent toward pre-approved commands, simplify complex command chains, and (when no safe local rule fits) file an upstream issue to improve the permission friction hooks. Replaces the former Dev10x:skill-reinforcement skill — reinforcement of skill usage is still part of the job, but the broader goal is reducing the friction supervisors see. Reads conversation context to identify the offending command, matches it against a command-to-skill map, audits local + global settings for simpler pre-approved forms, and outputs a firm reinforcement message pointing to the correct skill or pre-approved command. TRIGGER when: user sees agent using CLI instead of a skill, user rejects a command that should have been a skill, supervisor is bothered by repeated permission prompts, or user says "use the skills" / "diag friction" / "skill reinforcement". DO NOT TRIGGER when: agent is already using skills correctly, or the CLI command has no skill equivalent and no friction is observed.
dev10x-skill-audit-queue
by Dev10x-GuruQueue a skill-audit invocation for later by appending a tracker task to the end of the current task list. Use mid-session when you notice friction but do not want to interrupt in-flight work — the audit runs when the supervisor reaches the queued task. Also captures lightweight friction/skill-improvement notes as annotations on the queued task, so the full audit has prior context. TRIGGER when: friction noticed mid-session, but interrupting current work is not desirable; supervisor wants the audit deferred until the active task completes. DO NOT TRIGGER when: supervisor wants the audit to run NOW (use Dev10x:skill-audit directly), or no friction has been observed.
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.