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...
source-session
by emmahydeFind the Claude Code session that originated a given artifact — commit hash, PR, idea/decision, file, or feature name. Use when the user invokes /source-session [query] or asks "what session did we make X in" or "where did this come from". Searches ~/.claude/history.jsonl by correlating timestamps or keywords to session windows.
sandi-metz-design
by emmahydeDesign objects the Sandi Metz way — small, dependency-aware, message-passing, refactored mechanically toward abstractions you couldn't have predicted. Use when designing or refactoring OO code (especially Ruby/Rails), choosing between inheritance / composition / duck typing, smelling a god class, deciding what to test, or applying the Metz Rules. Sources: Practical Object-Oriented Design in Ruby (POODR), 99 Bottles of OOP, and Sandi's conference talks.
metzify
by emmahydeKnowledge base from "99 Bottles of OOP" (Milk/Ruby edition) by Sandi Metz, Katrina Owen & TJ Stankus. Use when applying Metz's frameworks for refactoring, finding the right abstraction, the Flocking Rules, Shameless Green, replacing conditionals with polymorphism, factories, code smells, or test design — while coding, studying the book, or referencing its concepts.
mermaid-architecture
by emmahydeUse when producing HTML architecture diagrams (ERDs, flowcharts, swimlanes, system maps). Enforces ELK layout with orthogonal connectors, classDiagram (NOT erDiagram), stadium-pill decisive-events (NOT diamonds), and post-render syntax-highlighting + node-category color coding.
clean-code-and-refactoring
by emmahydeWrite code that other people (and future-you) can change cheaply. Use when authoring new code, reviewing a PR, smelling duplication or long methods, picking names, or deciding whether to refactor before adding a feature. Distills Clean Code (Martin), 99 Bottles of OOP (Metz), and Code Complete 2e (McConnell).
teach
by emmahydeThis skill should be used when the user says "teach you about", "document our process", "explain how X works", "walk you through our system", or provides multi-part structured knowledge — processes, architectures, workflows, or any topic that has distinct logical components. Does NOT trigger for single isolated facts, corrections, or preferences — use /learn for those.
sector-design-brainstorming
by emmahydeUse when brainstorming game features, prioritizing systems, or creative planning for the Sector project. Triggers on feature proposals, "what should we build next", mining/combat/crew improvement discussions, or vertical slice planning. Requires cooperative dialogue with the user, not monologue.
idiomatic-ruby-and-rails
by emmahydeWrite Ruby and Rails the way the community writes them — blocks, attr_*, modules, ActiveRecord, scopes, strong parameters, the conventions Rails encodes. Use when authoring or reviewing Ruby/Rails code, choosing between class methods and scopes, picking between callbacks and service objects, designing controllers, deciding what belongs in a model, or asking "what's the Rails way to do X?" Sourced from canonical knowledge — Ruby docs, the Ruby Style Guide, the Rails Guides, the Rails Doctrine, POODR (paired with the dedicated `sandi-metz-design` skill).
reflect
by emmahydeThis skill should be used when the user says "reflect on patterns", "update self-model", "what have you learned about me", "self-reflection", or any request to review behavioral tendencies, update known patterns, or explicitly trigger a self-model review. Runs on-demand and complements the automatic every-5-consolidations trigger.
algorithms-and-data-structures
by emmahydeChoose the right algorithm and data structure for a problem, analyze its complexity, and recognize classic problem patterns. Use when picking a structure (array vs hash vs tree vs graph), analyzing whether code will scale, designing a non-trivial algorithm, or recognizing that a problem reduces to a known one. Distills CLRS, Sedgewick & Wayne (Algorithms 4e), Skiena (Algorithm Design Manual), and Knuth TAoCP Vol 3 (Sorting & Searching).
d2
by emmahydeD2 is a declarative diagram scripting language that turns text into production-quality diagrams. Use when the user wants to create, edit, or debug architecture diagrams, ERDs, sequence diagrams, grid layouts, or any text-to-diagram workflow.
algos
by emmahydeCombined knowledge base from "The Algorithm Design Manual" (Skiena) and "Algorithms, 4th Edition" (Sedgewick & Wayne). Use when choosing or analyzing an algorithm or data structure — complexity analysis, sorting, searching/symbol tables, heaps, graphs, shortest paths, strings, dynamic programming, greedy, backtracking, NP-completeness — when modeling a problem to a known algorithm, or when looking up the best-known approach for a problem.
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.