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...
fonts
by teamniteoConfigure web fonts via Astro's Fonts API (top-level `fonts` in Astro 6+, `experimental.fonts` in 5.x). Use whenever custom fonts come up — user mentions Google Fonts, Fontsource, local fonts, typography changes, font loading or performance, or asks to "add fonts", "change typography", "use custom fonts", "improve font loading", "optimize fonts". The Fonts API replaces `@import` and `@font-face` in CSS.
brand-designer
by teamniteoGenerate custom brand color palettes using color theory (complementary, triadic, analogous) — built around a 60/30/10 dominant/accent/highlight ratio with TheColorAPI for hue rotation. Use when user provides hex codes, requests "customize colors", "generate color palette", "create color palette", "pick brand colors", "design a palette", "what colors should I use", or asks to extract colors from a logo. A bare logo upload alone does NOT trigger this skill — wait for an explicit color-extraction or palette request.
pagespeed-audit
by teamniteoLive performance audit for deployed pages using Google PageSpeed Insights API. Runs Lighthouse against public URLs and scores them across Performance, Accessibility, Best Practices, and SEO, plus Core Web Vitals (LCP, INP, CLS, FCP, TTFB) and the top opportunities to improve each. Report-only — no fixes applied. Use when user requests "run pagespeed", "test core web vitals", "audit performance", "check Lighthouse score", "run a performance audit", or "test how fast the site is".
plausible-analytics
by teamniteoAdds Plausible Analytics to Astro sites with a Cloudflare Workers proxy for privacy and ad-blocker bypass. Requires a project deploying to Cloudflare Workers (uses `worker/index.js` route registration). Use when user requests "add Plausible", "add analytics", "add tracking", "page views", "visitor tracking", or privacy-friendly analytics. Skip if the project deploys to Vercel/Netlify/static-only — paste Plausible's standard `<script>` tag into Layout directly, no skill needed.
prelaunch-checklist
by teamniteoPre-launch validation for Hakuto sites — verifies wrangler config, form wiring, legal pages, placeholder content scrub; confirms `seo-audit` and `code-review` have been run; reminds the user of manual Cloudflare dashboard steps. Report-only — no fixes applied. Use when user requests "run prelaunch checklist", "is the site ready to ship?", "ready to go live", "pre-launch check", "launch check", or "final check before deploy".
professional-copywriter
by teamniteoProfessional SaaS and website copywriting focused on benefit-driven messaging and conversion optimization. Use when content is missing, incomplete, or user explicitly requests copy generation/improvement. Critical constraint: preserve user-provided copy verbatim unless they request edits.
scaffold-sync
by teamniteoPull selective scaffold updates from the installed Hakuto plugin into an existing Hakuto site. Compares the site's last-synced scaffold version against the current `${CLAUDE_PLUGIN_ROOT}/scaffold` tree, shows a per-file diff, and applies only files the user approves. Never overwrites silently. Persists state in `.hakuto-sync.json` at the site root. Use when the user requests "sync scaffold", "check for scaffold updates", "pull scaffold changes", "update scaffold", "what's new in the scaffold", or "is my scaffold current?".
section-blog
by teamniteoAdds multi-page blog system to existing websites with listing page, post templates, author archives, and category pages. Supports flexible content layouts beyond single-column text. Use when user requests "add blog", "add articles section", "add news", or mentions blog functionality. Skip for headless CMS integrations (Contentful, Sanity, Strapi), single one-off articles embedded in existing pages, or sites already using a different content collection setup.
section-docs
by teamniteoAdds technical documentation section with sidebar navigation to existing websites. Creates /docs home page with search, nested category pages, and minimal content-focused design. Use when user requests "add documentation", "add docs", "add API docs", "add developer docs", "add a help center", or "add a knowledge base". Skip for single one-off help articles that fit inside an existing page, headless doc platforms (Mintlify, GitBook, ReadMe, Docusaurus) where the docs live in a separate codebase, or sites that just need a FAQ section rather than a structured multi-page reference.
section-form
by teamniteoAdds forms to Astro pages using React with Zod validation, submitting to a Cloudflare Workers handler. Use when user requests "add form", "contact form", "newsletter signup", "inquiry form", "booking form", "feedback form", "registration form", "waitlist", or any form functionality requiring client-side validation and server submission. Skip for pure mailto: links, static HTML forms posting to third-party services (Formspree, Netlify Forms), or display-only fake forms used as visual mockups.
seo-audit
by teamniteoStatic SEO audit for Astro `_dist/` HTML — meta tags, headings, canonicals, schema, sitemap, robots.txt, alt text, mixed content, internal links, image sizes, favicons. Can scope to a single page, group of pages, or whole site. Report-only — no fixes applied. Use when user requests "run SEO test", "SEO audit", "check meta tags", "validate canonicals", "audit indexability", or "check site for SEO issues".
website-builder
by teamniteoCore orchestrator for generating production-ready Astro websites through conversational design. Use when user requests "build a SaaS site", "make me a landing page", "create a website", "I need a portfolio site", "create a company website", "build a marketing site", or wants to add or modify pages ("add a features page", "build the pricing page", "create about page", "add contact"). Handles site architecture and design systems, and coordinates with `professional-copywriter`, `brand-designer`, `fonts`, `section-form`, `section-blog`, `section-docs`, `plausible-analytics`, and the audit skills.
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.