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...
seo-aeo-expert-perspectives
by jacob-dietleThis skill should be used when making SEO, AEO (Answer Engine Optimization), or search visibility decisions. Apply expert perspectives (Eli Schwartz, Mike King, Lily Ray, Rand Fishkin, Cyrus Shepard) to diagnose what actually matters for search performance — programmatic page generation, structured data, title tags, E-E-A-T signals, and AI Overview optimization. Use when building pages for search visibility, adding structured data, evaluating whether programmatic pages have search value, or optimizing for AI-generated answers.
quickstart
by jacob-dietleThis skill should be used when a user wants to build their first Context OS or kick off initial setup of a knowledge graph system. Guides through a 10-minute flow — assess content, create the two-layer directory structure, generate CLAUDE.md, ingest first content, and verify compounding works. Adapts to blank-slate vs existing-content starting points. Use when user says "set up a context OS", "get started with context OS", "build a knowledge graph from scratch", or "quickstart".
ingest
by jacob-dietleThis skill should be used when processing raw content (transcripts, documents, notes, current conversation) into structured knowledge nodes for a Context OS. Extracts atomic concepts, creates nodes with complete frontmatter and [[wiki-links]], and routes each node to the correct knowledge_base/ domain. Use when user says "ingest this", "process into knowledge base", "turn this into nodes", or provides raw content to structure. Uses tags consistent with existing graph nodes; new concepts start as status emergent.
eval-loop
by jacob-dietleThis skill should be used when a specific quality problem (UX, data, architecture, feature) needs systematic diagnosis and iterative fixing toward a defined target. Traces symptoms to root causes, sets measurable targets with automated backpressure (unit tests, Playwright, LLM-as-judge, or rubric scoring), and iterates until targets pass. Use when user reports a quality gap ("this is a 3/10"), when shipping a feature that needs a quality bar ("what would 10/10 look like?"), or when a class of problems keeps recurring. Core pattern — symptom → generalize → root causes → targets → fix → verify → loop. Step 0 routes predictive/scoring problems OUT to eval-driven-scoring.
epistemic-context-grounding
by jacob-dietleGround implementation decisions in domain knowledge before designing solutions. Prevents over-engineering by checking what documentation exists, making assumptions explicit, and verifying them against canonical sources. Core principle - know what you don't know before designing.
decision-accountability
by jacob-dietleThis skill should be used when making architectural decisions, writing specs, or reviewing decisions that contain "future work", "v2", "simpler for now", "out of scope", or complexity claims. Verifies assumptions are grounded and catches corner-cutting disguised as pragmatism. Applies to code, specs, data models, auth flows, and context structures.
content-strategy-and-assembly
by jacob-dietleThis skill should be used when producing content (newsletter posts, blog posts, LinkedIn posts) from existing corpus material. Discovers relevant context from the knowledge graph, selects the right content framework, assembles a draft against a spec, then runs an eval loop of anti-slop checks until the output clears quality gates. Built from real content production pipelines with 142 automated anti-slop tests and the eval-loop methodology.
code-service-defrag
by jacob-dietleThis skill should be used to periodically defragment a multi-app/multi-service codebase — both CODE (duplicate deploy targets, colliding bindings, stale forks) and CONTEXT (parallel spec conventions, orphan docs, scattered context packages) — on any platform (Cloudflare, Railway, Vercel, Fly, Render, Docker Compose). Converts the vague "things are getting messy" feeling into specific, located, severity-ranked findings. Detect-only — does NOT auto-consolidate. Apply on a monthly cadence, before any risky deploy, after a migration, or whenever canonical-source ambiguity is suspected. Core principle — agentic coding fragments state faster than humans consolidate it, so drift accumulates silently until a deploy fires from the wrong place or an agent onboards from the wrong context.
coordinated-agent-teams
by jacob-dietleThis skill should be used when decomposing a spec into a multi-agent implementation plan with dependency ordering, parallelism decisions, contract testing, and verification strategy. Applies evidence from 5 verified multi-agent builds (sequential handoff, parallel fanout, mixed waves, corpus-wide single-agent, phased query engine) to prevent the common failure modes — integration surprises, context loss, silent failures, and over-specification overhead. Use when the implementation involves 3+ agents, has parallelization opportunities, or requires handoffs across context windows.
context-os-cli
by jacob-dietleThis skill should be used when users ask about their work context, what they're working on, recent activity, file relationships, or knowledge graph structure. Uses context-os CLI (including graph health/search/stats commands) combined with grep/glob for context restoration. Every claim MUST cite a receipt ID for user verification.
context-os-basics
by jacob-dietleFoundation patterns for building context operating systems
context-gap-analysis
by jacob-dietleEnumerate required context, check what exists, and find the simplest path forward before any task. Prevents hallucinations by forcing the agent to verify assumptions before acting.
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.