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...
yarp
by Tyler-R-KendrickUSE FOR: Building high-performance reverse proxies, API gateways, and load balancers using YARP (Yet Another Reverse Proxy) from Microsoft. Use when you need customizable request routing, load balancing, header transforms, session affinity, health checks, and dynamic configuration for proxying traffic to backend services. DO NOT USE FOR: Simple API gateway features like request aggregation and built-in rate limiting (use Ocelot), service mesh capabilities like mTLS and circuit breaking (use Istio or Linkerd), or CDN-style edge caching (use a CDN like Cloudflare or Azure Front Door).
reactiveui
by Tyler-R-KendrickUSE FOR: Building MVVM applications using Reactive Extensions with ReactiveObject, WhenAnyValue, ReactiveCommand, view model activation, and data binding for WPF, MAUI, Avalonia, and Blazor. DO NOT USE FOR: Simple applications without reactive data flows, server-side APIs without UI, or projects that prefer CommunityToolkit.Mvvm for a simpler MVVM approach.
reactive-extensions
by Tyler-R-KendrickUSE FOR: Composing event streams, UI events, timers, and asynchronous data sources using IObservable<T> with LINQ operators for filtering, throttling, combining, and error handling. DO NOT USE FOR: Simple async/await workflows, pull-based data streaming (use IAsyncEnumerable), or producer/consumer queues (use System.Threading.Channels).
onnx
by Tyler-R-KendrickUse when running pre-trained ONNX models for inference in .NET with ONNX Runtime. Covers session management, tensor inputs/outputs, execution providers (CPU/GPU/DirectML), model optimization, and integration with ASP.NET Core. USE FOR: running pre-trained ONNX models in .NET, image classification inference, NLP model inference, cross-framework model deployment (PyTorch/TensorFlow to .NET), GPU-accelerated inference with CUDA or DirectML DO NOT USE FOR: training ML models from scratch (use mlnet or Python), calling cloud-hosted LLMs (use microsoft-extensions-ai or azure-ai-inference), building agent workflows (use agent-framework), custom ML pipelines with feature engineering (use mlnet)
ncrontab
by Tyler-R-KendrickGuidance for NCrontab cron expression parser and scheduler for .NET. USE FOR: parsing cron expressions, calculating next/previous occurrences, validating cron syntax, scheduling background tasks with cron patterns, generating occurrence lists for display. DO NOT USE FOR: full job scheduling frameworks (use Quartz.NET or Hangfire), distributed task scheduling, Windows Task Scheduler integration, real-time event processing.
lucene-net
by Tyler-R-KendrickUSE FOR: Full-text search indexing and querying, faceted search, autocomplete and suggestion systems, document search with relevance ranking, and applications requiring embedded search without an external server. DO NOT USE FOR: Relational data querying (use EF Core or Dapper), real-time analytics on structured data, or scenarios requiring a managed search service (use Elasticsearch or Azure AI Search).
microsoft-foundry
by Tyler-R-KendrickUse this skill to work with Microsoft Foundry (Azure AI Foundry): deploy AI models from catalog, build RAG applications with knowledge indexes, create and evaluate AI agents. USE FOR: Microsoft Foundry, AI Foundry, deploy model, model catalog, RAG, knowledge index, create agent, evaluate agent, agent monitoring. DO NOT USE FOR: Azure Functions (use azure-functions), App Service (use azure-create-app).
curryfy
by Tyler-R-KendrickUse when applying function currying and partial application patterns in C# to create specialized, reusable function compositions. USE FOR: function currying, partial application, function composition, creating specialized functions from general ones, builder-like functional APIs DO NOT USE FOR: full functional programming library (use language-ext), parser combinators (use pidgin or fparsec), optional value handling (use optional)
orchard-cms
by Tyler-R-KendrickUSE FOR: Building modular content-managed web applications with Orchard Core. Use when you need a multi-tenant CMS with content types, custom modules, workflows, themes, and a decoupled or headless content API on ASP.NET Core. DO NOT USE FOR: Static sites without dynamic content management (use a static site generator), single-page applications that consume third-party headless CMS APIs (use Contentful or Strapi clients), or applications that do not need content authoring workflows (use ASP.NET Core directly).
micro-frontends
by Tyler-R-KendrickMicro-frontend architecture — composition approaches, Module Federation, single-spa, web components, shared state, and inter-app communication. Covers the patterns and tradeoffs for splitting a frontend across independent teams. USE FOR: micro-frontend architecture, Module Federation, single-spa, runtime composition, independent frontend deployment, cross-team frontend development DO NOT USE FOR: single-team SPA development (use spa), server-side rendering (use ssr), backend service decomposition (use dev/architecture/microservices)
stripe
by Tyler-R-KendrickUSE FOR: Integrating Stripe payment processing into .NET applications using the Stripe.NET SDK. Use when implementing checkout flows, subscriptions, payment intents, customer management, webhook handling, and Connect platform payments. DO NOT USE FOR: PayPal, Square, or Braintree payments (use their respective SDKs), cryptocurrency payments (use Coinbase Commerce or similar), or payment processing without Stripe as the provider.
stateless
by Tyler-R-KendrickGuidance for Stateless state machine library for .NET. USE FOR: modeling state transitions with guards and actions, workflow engines, order processing pipelines, device lifecycle management, protocol implementations, approval workflows. DO NOT USE FOR: distributed state machines (use Durable Functions or Temporal), event sourcing (use Marten), full BPMN workflow engines (use Elsa), simple boolean flags.
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.