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...
ride-along
by jay-steenbergenRun a ride-along session with an MSSA learner. Use when: starting a coding lesson, mentoring on a new concept, walking a veteran through their first project, learner asks 'help me build X and explain it', any non-trivial build that should also be a learning moment. Provides the full session shape: goal-setting, move-by-move build, naming concepts, after-action reviews.
ghc-prompting-for-completions
by jay-steenbergenGitHub Copilot track project #2. Learner builds 5 small functions by steering Copilot's inline completions with three prompt levers: comments-as-intent, signatures-as-shape, and naming-as-direction. Practices Ctrl+Enter for alternates, the open-tabs context trick, and recognizing when Copilot is guessing vs informed. Auto-load when the learner is in `github-copilot/ghc-prompting-for-completions` or asks how to steer Copilot, prompt inline completions, get better suggestions, use comments as prompts, or use the context window.
cso-kql-foundations
by jay-steenbergenCSO track project #1. Learner writes their first 8-10 KQL queries against the free Log Analytics demo workspace — `where`, `project`, `summarize`, `bin`, `join`, `top`, `render`. By the end the learner can read a security-relevant table, ask "who logged in from where" type questions, and explain why KQL is the lingua franca of the Microsoft security stack. Auto-load when the learner is in `cybersecurity-ops/cso-kql-foundations` or asks to learn KQL basics, write security queries, or use the LA demo workspace.
ghc-copilot-foundations
by jay-steenbergenGitHub Copilot track project #1. Learner installs the Copilot extensions, signs in, and writes a tiny calculator function with inline completions — learning Tab to accept, Esc to reject, Alt+] / Alt+[ to cycle, Ctrl+→ to accept word-by-word, and how to read ghost text. Auto-load when the learner is in `github-copilot/ghc-copilot-foundations` or asks to install Copilot, set up Copilot, learn the Copilot loop, or understand inline completions vs chat vs edit mode.
sca-monitoring
by jay-steenbergenSCA track project #8. Learner stands up a Log Analytics workspace, onboards the VM from project #5 via the Azure Monitor Agent and a Data Collection Rule, writes their first KQL queries against the collected logs, then creates an alert rule that emails them when CPU stays above 80% for 5 minutes. Auto-load when the learner is in `server-cloud-admin/sca-monitoring` or asks to learn Azure Monitor, Log Analytics, KQL basics, Azure Monitor Agent, Data Collection Rules, or how to alert on a VM metric.
cad-todo-cli
by jay-steenbergenCAD track project #2. Learner extends a console app into a working in-memory TODO manager with add/list/complete/remove commands, then refactors the data and behavior out of `Program.cs` into a dedicated `Todo` class and a `TodoStore` class. Introduces collections (`List<T>`), control flow (`switch`, `while`), file I/O (`File.ReadAllText`, `File.WriteAllText`), classes with properties, and the separation-of-concerns discipline that makes project #3's API conversion painless. Auto-load when the learner is in `cloud-app-dev/cad-todo-cli` or asks to learn collections, file I/O, classes, properties, or "how do I organize my C# code into more than one file."
wbd-whiteboard-foundations
by jay-steenbergenWhiteboarding track project #1. Learner stands at a whiteboard (or Excalidraw), drills the 5 shapes that actually matter (rectangle, rounded rectangle, cylinder, diamond, arrow), practices legibility under time pressure, and learns the layout rules (left-to-right flow, top-down hierarchy, label everything). Builds the muscle memory before any specific diagram type. Auto-load when the learner is in `whiteboarding/wbd-whiteboard-foundations` or asks how to start whiteboarding, draw clearly, layout a diagram, or use Excalidraw.
wbd-box-and-arrow-diagrams
by jay-steenbergenWhiteboarding track project #2. Learner draws three architecture diagrams (monolith, service-oriented, event-driven) using boxes, cylinders, queues, and labeled arrows. Learns the C4 model levels (system / container / component), when to use a cloud icon for "external," and why every arrow needs a verb. Auto-load when the learner is in `whiteboarding/wbd-box-and-arrow-diagrams` or asks how to draw an architecture diagram, component diagram, system diagram, or service topology.
wbd-capstone-present-a-system
by jay-steenbergenWhiteboarding track project #9 (capstone). Learner picks a real system they've built or use heavily, prepares 4 diagrams (architecture, sequence, state, ER), presents it live to another human in 15 minutes, records the session, captures every question the audience asked, redraws v2, and compares v1 vs v2. The skill graduates from drills into real communication. Auto-load when the learner is in `whiteboarding/wbd-capstone-present-a-system` or asks about presenting an architecture, whiteboarding capstone, system walkthrough, or technical presentation prep.
wbd-drawio-for-polished-diagrams
by jay-steenbergenWhiteboarding track project #7. Learner uses Draw.io / diagrams.net (free) to build polished architecture diagrams with cloud-provider icons, layers, and exports. Drills the Draw.io VS Code extension, AWS/Azure/GCP shape libraries, layer-based export, and the SVG-vs-PNG-vs-XML format question. Builds 2 diagrams: AWS 3-tier web app, Azure event-driven pipeline. Auto-load when the learner is in `whiteboarding/wbd-drawio-for-polished-diagrams` or asks about Draw.io, diagrams.net, polished diagrams, cloud icons, AWS/Azure architecture diagrams, or executive decks.
wbd-entity-relationship-diagrams
by jay-steenbergenWhiteboarding track project #5. Learner draws ER diagrams for relational data models. Drills entities, attributes, primary keys, foreign keys, and cardinality (one-to-one, one-to-many, many-to-many) using crow's foot notation. Walks 3 schemas: e-commerce, blog with tags, multi-tenant SaaS. Auto-load when the learner is in `whiteboarding/wbd-entity-relationship-diagrams` or asks how to draw an ER diagram, schema diagram, database diagram, or model relationships between tables.
wbd-mermaid-as-code
by jay-steenbergenWhiteboarding track project #6. Learner switches from hand-drawn diagrams to Mermaid, the text-based diagramming language that renders in GitHub markdown, VS Code, and PRs. Drills flowchart, sequence, state, and ER syntax. Learns the diagrams-as-code mindset: version control, code review, no PNGs. Auto-load when the learner is in `whiteboarding/wbd-mermaid-as-code` or asks about Mermaid syntax, diagrams in markdown, diagrams as code, or rendering diagrams in GitHub README.
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.