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...
configuring-home-assistant
by joshsymondsConfigures Home Assistant dashboards and automations on ultraviolet. Use when editing HA dashboards, Bubble Cards, YAML configs, or using hass-cli.
writing-nix-config
by joshsymondsPatterns for this nix-config flake repository. Use when editing .nix files, adding packages, creating modules, or debugging flake issues.
building-installers
by joshsymondsBuilds NixOS installer ISOs for hosts using the autoInstaller module. Use when creating installer USBs, adding new hosts to the installer system, or troubleshooting installer issues.
debugging-linux-games
by joshsymondsUse when a Steam, Proton, Wine, Lutris, or Heroic game misbehaves on Linux — crashes at launch, black screen, missing DLSS / Ray Tracing / Path Tracing / DLSS-RR / Frame Generation, anti-cheat failures, shader stutter, controller or HDR or Wayland-fullscreen problems, intro-video failures ("Failed to create SourceReader", MF_E_UNEXPECTED), NVAPI "Unknown function ID" log spam, gamescope dedup black-screens, vkd3d swapchain crashes. Especially before patching or forking DXVK, vkd3d-proton, dxvk-nvapi, gamescope, Wine, or Proton; before reading RE Engine, Unreal, Unity, Source 2, id Tech, or Decima logs; or when a game is mentioned with NVIDIA Blackwell, NixOS, niri, gamescope, proton-cachyos, GE-Proton, or proton-tkg. Triggers on phrases like "won't launch", "RT/PT grayed out", "Proton fix for", "/WineDetectionEnabled", "ProtonDB", "VKD3D_CONFIG", "PROTON_USE_WAYLAND", or any moment the impulse is "let me read the Proton/Wine/vkd3d source" before checking community fixes.
working-on-rimworld
by joshsymondsRimWorld reference module and mod development for Savecraft. Use when working on files in plugins/rimworld/, including reference modules (surgery, crops, combat, materials, drugs, raids, genes, research), the datagen XML parser, decompiling Assembly-CSharp.dll, or the Harmony mod. Triggers on RimWorld plugin code, XML Defs, datagen, reference.wasm, decompilation, patch verification, or RimWorld game formulas.
working-on-plugins
by joshsymondsGame plugin and adapter section design for Savecraft. Use when creating new plugins, designing GameState sections, adding sections to existing parsers, or working on section output in plugins/ or worker/src/adapters/. Triggers on section layout, progressive disclosure, GameState output, plugin sections, adapter sections, section sizing, or overview design.
working-on-mcp
by joshsymondsMCP server and OAuth development conventions for Savecraft. Use when working on MCP tools, OAuth flows, auth middleware, or the MCP handler in worker/src/mcp/, worker/src/oauth.ts, or worker/src/auth.ts. Triggers on MCP tool implementation, OAuth provider, token validation, Clerk integration, or protected resource metadata.
working-on-factorio
by joshsymondsFactorio plugin development for Savecraft. Use when working on files in plugins/factorio/, including the Lua mod (control.lua, info.json), WASM parser, reference modules (recipe_lookup, ratio_calculator), datagen pipeline, sprite sheet generator, or Factorio-specific views. Triggers on Factorio plugin code, Lua mod API, ratio calculator, recipe lookup, production chains, datagen, sprite sheets, or Factorio game data.
working-on-daemon
by joshsymondsGo daemon development conventions for Savecraft. Use when working on files in internal/, cmd/savecraftd/, or implementing daemon features like filesystem watching, plugin execution, WebSocket client, or push client. Triggers on Go daemon code, wazero, fsnotify, daemon interfaces, or daemon tests.
working-on-d2r
by joshsymondsD2R save file parser development for Savecraft. Use when working on files in plugins/d2r/, including d2s binary parsing, item decoding, skill trees, attribute parsing, or shared stash. Triggers on D2R plugin code, d2s format, Huffman decoding, item properties, treasure classes, or Reign of the Warlock.
managing-mtga-data
by joshsymondsD1 database access and MTGA reference data pipeline for Savecraft. Use when working with D1 databases, wrangler d1 commands, MTGA data imports, clearing or reimporting card/draft/rules data, debugging why imports skip, or running mtga-carddb, 17lands-fetch, scryfall-fetch, rules-fetch, tagger-fetch tools. Triggers on "D1", "wrangler", "MTGA data", "reimport", "pipeline state", "import skipping", "draft ratings", "card data stale", "force import", "update-mtga".
deploying-to-production
by joshsymondsProposes production releases for Savecraft components by finding latest git tags, diffing changes, and suggesting version bumps. Use when the user asks to deploy, release, tag, ship, or check what needs deploying to production. Triggers on "deploy to production", "what needs releasing", "propose version bumps", "cut a release", "tag for production", "ship it".
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.