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...
design-ux
by e-xodeDesign and UX methodology for the Vue SSR Starter Kit: design-first thinking, visual hierarchy (size > color > weight > position), Material Design 3 alignment via Vuetify 4, 8px spacing rhythm ($spacing-unit multiples), color semantics (primary for CTAs, success/error for feedback, neutral for chrome), micro-interactions (meaningful, restrained, accessible), responsive UX (mobile-first, breakpoint semantics), and WCAG 2.1 AA accessibility. Trigger on: UI quality, design direction, visual hierarchy, accessibility audit, responsive decisions, animation design, color review, UX patterns, user feedback design. This is methodology — the design agent is the executor. Don't use for: SCSS implementation (→ design-scss), Vuetify component API (→ vuetify-components), app architecture (→ vue-ssr-architecture), auth flow (→ vue-ssr-auth), deciding when to delegate design work (→ vue-ssr-design).
seo
by e-xodeSEO reference for the Vue SSR Starter Kit (e-xode/vue-ssr): how the kit's server-side SEO is wired and the per-page checklist. Covers meta injection in src/entry-server.js (title/description/keywords/robots/theme-color/author built from route meta i18n keys via t()), JSON-LD structured data (Organization site-wide, WebSite + SearchAction on the home route, BreadcrumbList on deep pages, suppressed on noindex routes), Open Graph + Twitter Cards, bilingual hreflang alternates (en/fr + x-default to /en), and the dynamic robots.txt + sitemap.xml served by server.js (public paths only, 1h cache). Trigger on any SEO work: meta tags, canonical, structured data, sitemap, robots, hreflang, Core Web Vitals, or per-page SEO checklists. Don't use for: routing internals (→ vue-ssr-architecture), translation copy of meta keys (→ translate), off-site/LinkedIn marketing content (→ marketing-content/content-strategy), visual/perf styling (→ design-scss).
translate
by e-xodei18n and translation reference for the Vue SSR Starter Kit (e-xode/vue-ssr): 2-locale system (EN/FR) with vue-i18n 11 in Composition API mode, nested JSON locale files at src/translate/{en,fr}.json, key naming conventions (section.subsection.camelCase), interpolation syntax ({param}), locale-aware routing via useLocalePath composable, and parity enforcement between locales. Trigger on any i18n work: adding/editing translations, creating new locale keys, fixing missing translations, checking locale parity, using t() in templates, locale routing, or internationalization questions. Don't use for: app architecture (→ vue-ssr-architecture), auth flow (→ vue-ssr-auth), post-task validation (→ vue-ssr-hooks), component styling (→ design-scss).
brand-art-direction
by e-xodeMaterial Design 3 / Vuetify 4 art-direction charter for the Vue SSR Starter Kit (e-xode/vue-ssr): the opinionated, screenshot-verifiable brand-identity layer above design-scss and design-ux. Defines the clean-minimal direction (single indigo brand accent, neutral-gray chrome, bordered flat MD3 surfaces, 8px rhythm, restraint over decoration) as DECIDABLE screenshot-checkable systems: quiet surface rhythm, canonical hover/elevation per component archetype with sibling consistency, palette roles, decorative restraint, and an evidence-based pre-delivery checklist graded by the visual-qa agent. Trigger on ANY visual/finition or polish work on rendered views: card hovers, surface backgrounds, elevation, accent usage, hero/CTA styling. Load BEFORE design-scss/design-ux when styling views. Don't use for: SCSS token/mixin mechanics (→ design-scss), UX methodology (→ design-ux), Vuetify component API (→ vuetify-components), design routing (→ vue-ssr-design), marketing copy (→ content-strategy).
vue-ssr-deployment
by e-xodeDeployment and CI/CD reference for the Vue SSR Starter Kit: Docker multi-stage build, docker-compose split into a base (app, remote DB) plus a docker-compose.local.yml override (local mongo) switched via the COMPOSE_FILE variable in .env, GitHub Actions workflows (npm-publish on tags, npm-test on PR, docker-build to GHCR), production configuration (Helmet CSP, COOKIE_SECRET, graceful shutdown SIGTERM/SIGINT), Dependabot weekly npm updates. Trigger on any deployment, Docker, docker-compose local-vs-remote DB switch, CI/CD, production config, or infrastructure question. Don't use for: app architecture (→ vue-ssr-architecture), auth flow (→ vue-ssr-auth), post-task validation (→ vue-ssr-hooks).
vuetify-overview
by e-xodeVuetify 4 (Material Design 3) entry point and global configuration for the Vue SSR Starter Kit: component selection decision tree (which v-component for which UI need), project-wide defaults in src/plugins/vuetify.js (rounded, variants, density per component), the semantic color palette (primary/secondary/accent/success/warning/error), SSR-safe instantiation (createApplicationVuetify(ssr) flag), and responsive breakpoints via the useDisplay composable. Trigger on: choosing which Vuetify component to use, project default props, color tokens by name, SSR Vuetify setup, useDisplay/breakpoint behavior, or a general 'which Vuetify component' question. Don't use for: specific component APIs — forms (→ vuetify-forms), data tables (→ vuetify-data), cards/dialogs/alerts (→ vuetify-components), app-bar/drawer/tabs (→ vuetify-layout), theming/dark mode (→ vuetify-theming), icons (→ vuetify-icons), SCSS tokens (→ design-scss).
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.