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...
pr-iterate
by jonathanpeppersIterate on a GitHub pull request from a coding agent (like Copilot coding agent) until it's ready for human review. Use this skill whenever the user asks to complete a PR, finish a PR, iterate on a PR, review and fix a PR, ship a PR, get a PR green, land a PR, or monitor a coding agent's PR. Also triggers when the user mentions PR numbers (e.g. "#108"), links to github.com pull requests, or says things like "when copilot is done", "clean up that PR", "make it green", or "iterate until CI passes". This skill handles the full lifecycle: code review, CI approval, test fixing, and repeated iteration until the PR is green and ready for human merge.
nes-decompile
by jonathanpeppersDecompile NES ROM files (.nes) into C# projects that can be rebuilt with dotnes. Use this skill whenever the user wants to decompile a ROM, reverse-engineer a .nes file, convert a ROM to C#, extract code from a NES ROM, create a project from an existing ROM, or do a round-trip test (transpile → decompile → retranspile). Also use when the user says things like "decompile this ROM", "turn this .nes into C#", "extract the code", "what does this ROM do", "reverse engineer", or "round-trip". This is the high-level decompilation tool — for low-level 6502 disassembly, use nes-rom-debug instead.
nes-emu-debug
by jonathanpeppersRun NES ROMs in the Mesen2 emulator to debug runtime behavior. Use this skill whenever the user wants to run a ROM and inspect what actually happens at runtime: read NES memory (RAM, palette, nametable, OAM), dump CPU/PPU/APU state after N frames, capture the screen buffer, compare runtime behavior between two ROMs, or verify that a sample displays correctly. Also use when the user says things like "run the ROM", "what does the screen look like", "check the palette", "inspect nametable", "read zero page", "dump memory", or "the ROM doesn't display correctly". This is the dynamic/runtime counterpart to nes-rom-debug (which does static binary analysis).
nes-rom-debug
by jonathanpeppersDisassemble and debug NES ROM files (.nes) produced by the dotnes transpiler. Use this skill whenever the user wants to disassemble a .nes ROM, inspect 6502 machine code, compare two NES ROMs side-by-side, debug transpiler output, investigate byte differences between a cc65 reference ROM and a dotnes ROM, or understand what 6502 instructions the transpiler emitted. Also use when the user mentions disasm, disassembly, PRG ROM, ROM bytes, NES addresses, or wants to look at the hex/binary output of a build. Even if the user just says something like "the ROM looks wrong" or "what did the transpiler emit", this skill applies.
code-reviewer
by jonathanpeppersReview dotnes PRs against established rules. Trigger on "review this PR", a GitHub PR URL, or code review requests. Checks transpiler correctness, 6502 assembly, NES program conventions, MSBuild integration, snapshot tests, C# patterns, and AI-generated code pitfalls.
restart
by jonathanpeppersRestart the WPF application to apply code or XAML changes. Use this skill when you need to restart the app after making changes, or when the UI needs to be refreshed because WPF hot reload is limited.
screenshot
by jonathanpeppersCapture a screenshot of the running WPF application UI. Use this skill when asked to see, view, capture, or screenshot the current state of the WPF application's user interface.
tree
by jonathanpeppersGet the visual tree structure of the running WPF application. Use this skill when asked to inspect, debug, or understand the element hierarchy, control structure, or layout of the WPF UI.
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.