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...
uno-wasm-pwa
by mtmatteiUno Platform WebAssembly and Progressive Web App development: bootstrapper setup, PWA manifests, debugging, hosting, performance optimization, and deployment. Use when: (1) Targeting WebAssembly with Uno Platform, (2) Adding PWA support with service workers, (3) Debugging Wasm apps, (4) Deploying to Azure Static Web Apps or Nginx, (5) Optimizing Wasm payload size and load time, (6) Configuring AOT compilation for Wasm. Do NOT use for: general project setup (see uno-platform-agent) or .NET version migration (see uno-migration-troubleshoot).
wpf-to-uno-migration
by mtmatteiMigrate WPF desktop applications to cross-platform Uno Platform apps. Phased workflow covering namespace/API mapping, XAML replacements, NavigationView region setup, Material Design theming, settings with IWritableOptions, service abstraction with DI, and platform-specific UI patterns. Use when: (1) Planning or executing a WPF-to-Uno migration, (2) Converting WPF Windows/dialogs to Uno Pages/ContentDialogs, (3) Replacing WPF settings/singletons with Uno Extensions DI, (4) Adapting WPF controls to WinUI/Material equivalents, (5) Debugging blank pages from bad resource keys or NavigationView misconfiguration. Do NOT use for: Silverlight migration (see uno-migration-troubleshoot), UWP migration, new Uno project setup (see uno-platform-agent), or general XAML optimization (see winui-xaml).
uno-platform-agent
by mtmatteiComprehensive Uno Platform development patterns for Single Project architecture, MVVM/MVUX, navigation, styling, platform-specific code, and custom controls. Use when: (1) Creating new Uno Platform projects, (2) Implementing MVVM or MVUX patterns, (3) Setting up navigation or styling, (4) Writing platform-specific code, (5) Building custom controls, (6) Optimizing build configuration with Uno.Sdk. Do NOT use for: XAML-only best practices (see winui-xaml), Toolkit control APIs (see uno-toolkit), or service-layer extensions (see uno-extensions-services).
uno-navigation
by mtmatteiUno Platform Navigation Extensions: region-based navigation, route registration, programmatic and XAML navigation, data passing, qualifiers, NavigationView, TabBar, responsive shells, dialogs, and troubleshooting. Use when: (1) Setting up navigation in an Uno Platform app, (2) Defining routes with ViewMap/DataViewMap/RouteMap, (3) Implementing NavigationView or TabBar navigation, (4) Passing data between pages, (5) Showing dialogs or flyouts via navigation, (6) Debugging blank pages or broken navigation. Do NOT use for: MVUX state management (see mvux), general XAML layout (see winui-xaml), new project scaffolding (see uno-platform-agent).
uno-migration-troubleshoot
by mtmatteiMigration paths and troubleshooting for Uno Platform: upgrading to Single Project, migrating from UWP/WPF/Silverlight, .NET version upgrades, and resolving common build/runtime errors. Use when: (1) Migrating to Uno.Sdk Single Project, (2) Upgrading from .NET 8 to .NET 9, (3) Migrating from WPF or Silverlight, (4) Fixing common build errors (UNOB0011, UNOB0013), (5) Resolving platform-specific runtime issues, (6) Troubleshooting Visual Studio 2022 problems. Do NOT use for: new project setup (see uno-platform-agent) or Wasm-specific optimization (see uno-wasm-pwa).
uno-extensions-services
by mtmatteiUno Platform Extensions for hosting, dependency injection, authentication, HTTP clients, configuration, logging, and storage. Use when: (1) Setting up IHostBuilder and DI container, (2) Adding MSAL or OIDC authentication, (3) Configuring HTTP clients with Kiota or Refit, (4) Loading appsettings.json configuration with IOptions, (5) Setting up logging with ILogger or Serilog, (6) Using IWriteableOptions for runtime config changes. Do NOT use for: project setup or MVVM patterns (see uno-platform-agent) or UI controls (see uno-toolkit).
uno-csharp-markup
by mtmatteiC# Markup for Uno Platform: code-first UI with fluent API, strongly-typed data binding, resources, styles, templates, and Uno Toolkit integration. Use when: (1) Building UI in C# instead of XAML, (2) Using fluent data binding with expression trees, (3) Applying styles and templates in C# Markup, (4) Integrating Uno Toolkit controls in C# Markup, (5) Setting up a C# Markup project from scratch, (6) Converting XAML patterns to C# Markup. Do NOT use for: XAML-based UI (see winui-xaml) or Toolkit control reference (see uno-toolkit).
uno-app-ui-testing
by mtmatteiAutomates UI testing for Uno Platform applications using the Uno App MCP server tools. Use this skill when performing automated UI testing, visual validation, interaction testing, or end-to-end testing of Uno Platform cross-platform applications. Covers app lifecycle management, visual tree inspection, element interaction, screenshot capture, and test assertions.
uno-app-test-assertions
by mtmatteiProvides assertion and validation patterns for UI testing of Uno Platform applications. Use this skill when you need to validate UI state, verify element properties, compare screenshots, or assert on data binding values during automated testing. Complements the uno-app-ui-testing skill with validation-specific guidance.
mvux
by mtmatteiMVUX (Model-View-Update-eXtended) architecture for Uno Platform: immutable records, reactive feeds/states, FeedView, commands, selection, messaging, and pagination. Use when: (1) Creating MVUX models with IFeed/IState/IListFeed/IListState, (2) Displaying async data with FeedView, (3) Implementing two-way binding with states, (4) Working with commands, selection, or messaging, (5) Debugging blank FeedView or missing command generation. Do NOT use for: MVVM patterns (use CommunityToolkit.Mvvm directly), general XAML layout (see winui-xaml), navigation (see uno-navigation).
winui-xaml
by mtmatteiWinUI 3 and XAML best practices for layout, binding, async operations, collections, rendering, memory management, accessibility, and localization. Use when: (1) Working with WinUI 3 or Uno Platform XAML, (2) Optimizing UI performance, (3) Implementing data binding with x:Bind, (4) Managing collections and virtualization, (5) Ensuring accessibility compliance, (6) Handling async operations on UI thread, (7) Preventing memory leaks, (8) Implementing localization. Do NOT use for: C# Markup (see uno-csharp-markup) or Uno Toolkit controls (see uno-toolkit).
dotnet-csharp
by mtmattei.NET C# best practices for building performant, secure, and maintainable applications. Use when: (1) Writing new .NET/C# code, (2) Reviewing code for performance issues, (3) Identifying security vulnerabilities, (4) Refactoring existing applications, (5) Architecting new systems, (6) Debugging production issues. Do NOT use for: XAML-only best practices (see winui-xaml), Uno Platform project setup (see uno-platform-agent), or service-layer extensions (see uno-extensions-services).
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.