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...
zora-config-advisor
by ryakerGuide users through configuring Zora agent setup by interviewing them about their workflow, then generating tailored config.toml and policy.toml files. Use when: (1) setting up Zora for a new workflow, (2) tuning security policy for a specific task, (3) choosing providers, MCP servers, or skills for a use case, (4) reviewing or tightening an existing Zora config. Triggers on "configure Zora", "Zora setup", "policy for", "config for", "zora init help", "what permissions", "which MCP servers".
zora-setup-guide
by ryakerInteractive hands-on setup guide for Zora. Walks the user through every step from zero to first productive task — checking prerequisites, installing, running `zora-agent init`, executing first tasks, and verifying everything works. Use when: (1) someone is setting up Zora for the first time, (2) someone is stuck during installation, (3) someone says 'help me install Zora' or 'get me started'. Triggers on 'setup Zora', 'install Zora', 'get started with Zora', 'Zora setup help', 'walk me through setup'.
kms-auto-capture
by ryakerCapture high-value items from a working session into Richard's Personal KMS at session-end. Triggers on session-end cues — "wrap up", "park this", "let's stop here", "call it", "we're done for today", "goodnight", "sign off", "checkpoint", "save state", "before I forget", or end-of-conversation signals where the user is clearly closing out. Distills the session into atomic claims and stores each via unified_store with metadata.subject. Always searches first to avoid duplicates and routes contradictions through kms_supersede instead of re-storing. Do NOT use for ad-hoc single-item storage (use kms-remember). Do NOT use for batch transcript ingestion (use kms-meeting-synthesis). Do NOT use to dump raw conversation history.
kms-trust-boundaries
by ryakerEnforce corpus trust boundaries when reading, citing, or ingesting any document for Richard's projects — especially Lumen / libcp / L16 reverse-engineering work. Triggers when working with files under ~/Documents/Light_Work/ (UNTRUSTED), ~/Dev/L16_Lumen_ReverseEngineering/ (TRUSTED), or any L16/Lumen/libcp claim. Also triggers on "is this verified", "can I trust this source", "is this canonical", "should I cite this", "ingest this into KMS" when the source is Light_*, or any operation that risks promoting untrusted material into KMS as fact. Refuses to cite from UNTRUSTED paths without "[unverified]" prefix and refuses to ingest into KMS without explicit user override. Codifies the rule stored in KMS memory 54f04f28-259e-4c8c-9f6e-64cefc8fff52. Do NOT use as a generic file-trust skill — this is L16/Lumen-corpus-specific and applies Rich's verify-before-trust standard for that domain.
kms-session-checkpoint
by ryakerSaves structured session knowledge to the Personal KMS (unified_store) — decisions, technical facts, correction patterns, and working procedures discovered during the session. Use whenever the user says "save this session", "checkpoint the session", "save what we learned", "save to KMS before I stop", "dump session insights", "capture what we figured out", "session checkpoint", or "kms checkpoint". Also fires automatically when a PreCompact or periodic Stop hook blocks with a KMS CHECKPOINT reason. Do NOT use for searching or recalling from KMS (that is kms-recall). Do NOT use for storing a single ad-hoc fact — call unified_store directly. Do NOT use for silent per-turn extraction — kms-session-extract.py handles that automatically.
kms-reconcile-pass
by ryakerRun a full-reconciliation pass over a topic cluster in Richard's Personal KMS — identify supersede candidates, contradictions, and near-duplicates, then PROPOSE corrective actions for human approval before dispatching. Triggers on "reconcile KMS", "clean up KMS", "audit KMS for <topic>", "weekly KMS pass", "find contradictions in KMS", "drain KMS dedup debt", "reconcile <topic>", or when Rich asks to clean up an over-written subject area. NEVER silently applies corrections — every supersede/update/delete needs explicit user approval first. Drains the "0 corrections vs N writes" debt the dedup gate spec was written to fix. Do NOT use for single-fact corrections (use kms_supersede directly). Do NOT use for hard-deleting flagged entries past the reversibility window — that is kms_reap, an admin tool.
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.