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...
responsive-layouts
by marcushellbergGuide Claude on building responsive Vaadin 25 layouts that adapt to different screen sizes. This skill should be used when the user asks to "make a layout responsive", "support mobile", "adapt to screen size", "use breakpoints", "use media queries", "use container queries", "responsive design", "mobile first", or needs help making a Vaadin Flow view work well on both desktop and mobile devices.
reusable-components
by marcushellbergGuide Claude on structuring Vaadin 25 Flow views into focused, reusable components. This skill should be used when the user asks to "structure a view", "organize view code", "break down a complex view", "extract a component", "split a view into components", "simplify a large view", "create a reusable component", "use Composite", "compose components", or when a view is growing beyond ~200 lines, has multiple logical sections, or contains repeated UI patterns.
security
by marcushellbergGuide Claude on securing Vaadin 25 applications with Spring Security. This skill should be used when the user asks to "add security", "add login", "create a login view", "create a login form", "use Spring Security", "secure a view", "add authentication", "add authorization", "use @RolesAllowed", "use @PermitAll", "use @AnonymousAllowed", "use @DenyAll", "use VaadinSecurityConfigurer", "add OAuth2", "use OAuth2 login", "use Google login", "use Keycloak", "use GitHub login", "add logout", "add a logout button", "use AuthenticationContext", "protect a view", "role-based access", "configure SecurityFilterChain", or needs help with view access control, login forms, OAuth2 providers, or logout handling in Vaadin Flow.
testbench-testing
by marcushellbergGuide Claude on writing end-to-end browser tests with Vaadin TestBench in Vaadin 25. This skill should be used when the user asks to "write an end-to-end test", "write a browser test", "use TestBench", "create a page object", "test in a real browser", "integration test a Vaadin app", "visual regression test", "cross-browser test", or needs help with TestBench Element API, ElementQuery, page objects, or TestBenchTestCase.
theming
by marcushellbergGuide Claude on Vaadin 25 theming with both Aura and Lumo themes. This skill should be used when the user asks to "choose a theme", "set up Aura", "set up Lumo", "customize the theme", "change colors", "enable dark mode", "customize design tokens", "use theme variants", "use utility classes", "change the color scheme", or needs help with theme-specific CSS custom properties, component theme variants, or building a custom theme in Vaadin 25.
third-party-components
by marcushellbergGuide Claude on integrating third-party Web Components and React components from npm into Vaadin 25 Flow applications. This skill should be used when the user asks to "integrate a web component", "wrap a web component", "third-party component", "@Tag", "@NpmPackage", "@JsModule", "@DomEvent", "@EventData", "@Synchronize", "integrate a React component", "wrap a React component", "ReactAdapterComponent", "ReactAdapterElement", "npm component", "PropertyDescriptor", "callJsFunction", "synchronize properties", or "listen to DOM events".
ui-unit-testing
by marcushellbergGuide Claude on writing fast, browser-free UI unit tests for Vaadin 25 Flow views. This skill should be used when the user asks to "write a UI test", "unit test a view", "test without a browser", "use UIUnitTest", "test a Vaadin component", "browser-free testing", "browser-less testing", or needs help with the TestBench UI unit testing framework, component testers, navigation in tests, or mocking Spring beans in Vaadin UI tests.
vaadin-layouts
by marcushellbergGuide Claude on using Vaadin 25 HorizontalLayout and VerticalLayout correctly. This skill should be used when the user asks to "create a layout", "arrange components", "align items", "fix layout sizing", "use HorizontalLayout", "use VerticalLayout", or needs help with spacing, padding, margins, flex-grow, flex-shrink, or alignment in Vaadin Flow views. Also trigger when debugging layout issues like components shrinking unexpectedly or overflowing their container, or when choosing between layout components (HorizontalLayout vs VerticalLayout vs FlexLayout vs AppLayout).
views-and-navigation
by marcushellbergGuide Claude on creating Vaadin 25 views with @Route, setting up router layouts (AppLayout, @Layout), navigation between views, and passing data via URL parameters. This skill should be used when the user asks to "create a view", "add a route", "use @Route", "set up navigation", "use AppLayout", "build a navigation menu", "use SideNav", "pass data between views", "use route parameters", "use query parameters", "create a master-detail view", "use @Layout", "use RouterLayout", "use @ParentLayout", "use @RoutePrefix", "use @Menu", "use RouterLink", or "navigate programmatically". Also trigger when the user needs help choosing between route parameters and query parameters, building a MainLayout with a drawer and navigation menu, or structuring nested router layouts.
signals
by marcushellbergGuide Claude on using Vaadin Signals for reactive state management in Vaadin 25 Flow. This skill should be used when the user asks to "use signals", "manage state reactively", "share state between users", "use reactive state", "use ValueSignal", "use NumberSignal", "use ListSignal", "use computed signals", "use ComponentEffect", "bind signals to components", or needs help with reactive UI updates, signal transactions, signal factories, or thread-safe state management in Vaadin Flow.
client-side-views
by marcushellbergGuide Claude on building client-side (React/Hilla) views in Vaadin 25. This skill should be used when the user asks to "build a client-side view", "create a React view", "use Hilla", "use @BrowserCallable", "file-based routing", "call Java from React", "create an offline view", "client-side rendering", "use ViewConfig", "create a Hilla endpoint", "use reactive endpoints", "subscribe to server push from React", "use signals in React", or needs help with React-based Vaadin views, file-based routing conventions, or type-safe backend communication.
data-providers
by marcushellbergGuide Claude on using Vaadin 25 data providers efficiently for Grid, ComboBox, and other listing components. This skill should be used when the user asks to "load data into a grid", "use a data provider", "lazy load data", "paginate grid data", "filter a grid", "sort a grid", "use setItems", "use CallbackDataProvider", "bind a Spring service to a grid", "use setItemsPageable", or needs help with in-memory vs lazy data binding, filtering, sorting, or custom data providers in Vaadin Flow.
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.