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...
42-init
by chapter42Bootstrap een klantproject voor 42-SEO-Skills. Vraagt naar profiel (content/ecom/technical/full), activeert alleen relevante skills via disabledSkills in .claude/settings.local.json, zet auth (.env) op, maakt de gedeelde Python venv in ~/.claude/venvs/42-seo/, en prikt 42-reports/<klant>/ neer. Use when user says "init SEO project", "42-init", "setup SEO", "nieuw klantproject", "initialiseer SEO".
42-geo-prospect
by chapter42CRM-lite for managing GEO agency prospects and clients. Track leads through the full sales pipeline: Lead → Qualified → Proposal Sent → Won → Lost. Store audit history, notes, deal values, and generate pipeline summaries. Use when user says "prospect", "lead", "client", "pipeline", "crm", "nuovo prospect", "aggiungi cliente", or when managing the business side of GEO services.
42-geo-sales
by chapter42GEO sales pipeline management and proposal generation. CRM-lite prospect tracking with JSON storage, automatic proposal generation from audit data with pricing tiers and ROI projections. Use when user says "prospect", "proposal", "offerte", "pipeline", "sales", "client management".
42-images
by chapter42Image optimization analysis for SEO and performance. Checks alt text, file sizes, formats, responsive images, lazy loading, and CLS prevention. Supports batch analysis from Screaming Frog CSV exports, CDN optimization, and AI image SEO. Use when user says "image optimization", "alt text", "image SEO", "image size", or "image audit".
42-internal-links
by chapter42Competitive internal link analysis for e-commerce category pages. Crawls competitor pages with Playwright (or Firecrawl as fallback), maps every internal link into named blocks (breadcrumb, facet-filters, A-Z index, FAQ, product cards, etc.), checks crawlability (real <a> vs JS-only), audits canonical tags and Google rankings, then generates prioritized improvement stories in SCQA format. Use when user says "internal link analysis", "interne link analyse", "link vergelijking", "categorie pagina analyse", "competitor link audit", "concurrent analyse links", "linkblokken vergelijken", or wants to compare how competitors structure internal links on category pages. Also use when analyzing hub vs lister page architectures.
42-keyword-discovery
by chapter42Keyword discovery en ideation vanuit seed keywords. Haalt suggestions, related keywords, zoekvolume en difficulty op via DataForSEO. Classificeert intent, berekent opportunity scores, en identificeert quick wins + GEO-kansen. Werkt ook zonder API in mock-modus voor LLM-gestuurde expansie. Use when user says "keyword discovery", "keyword ideeën", "zoekwoord suggesties", "keyword ideas", "find keywords", "welke zoekwoorden", "waar moet ik over schrijven", "keyword research", "seed keywords uitbreiden", "zoekwoord onderzoek".
42-keyword-mapper
by chapter42Map keywords naar pagina's op basis van Screaming Frog embeddings + GSC data. Vindt content gaps (keywords zonder pagina), cannibalisatie (meerdere pagina's op zelfde keyword), en quick wins (hoge impressies, lage CTR). Use when user says "keyword mapping", "keyword pagina match", "content gap", "zoekwoord toewijzing", "welke pagina rankt voor", "GSC analyse", "keyword gap analysis".
42-meta-optimizer
by chapter42AI-powered bulk meta description analysis: score quality on 4 criteria (0-40), rewrite to length constraints (desktop ≤160 chars, mobile ≤130 chars), and generate featured snippet "At a glance" summaries. Accepts single URLs, CSVs with URLs, or Screaming Frog Internal:HTML exports. No Python scripts — this is fully AI-based analysis and rewriting. Use when user says "meta description", "meta optimizer", "meta rewrite", "snippet", "featured snippet", "meta grade", "meta score", "meta quality", "SERP snippet", "description optimization", "meta bulk", "rewrite descriptions".
42-paa-scraper
by chapter42Recursively scrape People Also Ask questions up to 5 levels deep plus Related Searches tree. Builds a question tree for FAQ content and featured snippet strategy. Use when user says paa scraper, people also ask, paa tree, question research, faq mining, paa extraction, related searches, question tree, paa depth, 42-paa.
42-page-analysis
by chapter42Deep single-page SEO analysis covering on-page elements, content quality, technical meta tags, schema, images, and performance. Supports optional Screaming Frog data input and Chrome DevTools MCP for CWV/Lighthouse. Use when user says "analyze this page", "check page SEO", or provides a single URL for review.
42-page-health
by chapter42Samengestelde per-URL gezondheidscore (0-100) die meerdere SEO-risicosignalen combineert: thin content, orphan pages, missing on-page elementen, indexability problemen, en optioneel traffic decay. Bulk URL triage na Google core updates. Use when user says "page health", "URL risk", "HCU audit", "core update impact", "slechtste pagina's", "pagina gezondheid", "URL triage", "risico score".
42-passage-analyzer
by chapter42Passage-level content analyse voor AI/RAG readiness. Segmenteert pagina-content in passages (heading-boundary splitting), scoort elke passage op AI-extractability, en identificeert welke passages optimaal zijn voor citatie en welke herwerkt moeten. Optioneel AI-powered gap analyse per passage. Use when user says "passage analyse", "passage scoring", "chunk analyse", "RAG readiness", "AI extractability", "passage segmentatie", "content chunking".
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.