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...
pixel-snapper
by kyhRecover the true low-resolution pixel grid from upscaled or AI-generated fake pixel art PNGs. Use for snap-to-grid cleanup, native-resolution sprite assets, palette-quantized game art, and known-layout spritesheets. Bundles uv Python scripts ported from Hugo Duprez's spritefusion-pixel-snapper.
pixel-art
by kyhGenerate 2D pixel art game assets, characters, sprite sheets, background removal, and game backgrounds. Trigger for "pixel art character", "sprite sheet", "walk cycle", "game sprites", "isometric sprites", "side-scroller assets", "RPG character sprites", "idle animation", "attack animation", "jump animation", "game background", "parallax background", "isometric map", "2D game art", "pixel art animation", "top-down character", "explosion sprite sheet", "animated FX from video", "fire/magic effect". Covers character generation (nano-banana-pro / gpt-image-2), sprite sheet animation (nano/edit or fal-ai/gpt-image-2/edit), top-down 4-directional walkers, background removal (Bria), background generation (parallax layers or isometric map), and animated VFX derived from a generated video rendered with additive blend.
game-playbook
by kyhThe end-to-end recipe for building a GREAT browser game from a one-line idea, plus the craft checklist that separates a tech demo from something fun. Use when the user says 'make a game', 'build a <genre> game' ('make a pixel art top-down slasher', 'build a platformer', 'make a shooter'), 'create a game', or asks to make a game better: 'it feels flat/static/boring', 'add polish/craft', 'screen shake', 'hit stop', 'make it feel good', 'why does my game feel cheap'.
game-feel
by kyhDeep game-feel and juice reference — input forgiveness windows, movement curves, hit stop, trauma-based screen shake, squash & stretch, camera kick, audio feel — with concrete numbers from the canonical sources (Swink, Vlambeer, Celeste, Smash). Use when tuning how a game FEELS: 'the controls feel floaty/sluggish/slippery', 'jumping feels bad', 'hits don't land', 'make combat feel weighty', 'add juice', 'coyote time', 'input buffering', 'screen shake feels wrong', or any movement/impact tuning pass. The game-playbook craft checklist covers the basics; this is the deep module with the tuning values.
vfx
by kyhReal-time 2D VFX cookbook — layered explosions, hit sparks, muzzle flashes, trails, smoke, pickups, heals, shockwaves, weather — with particle parameter recipes, color/readability rules, and mobile-browser performance budgets, from Diablo's VFX talk, Riot's style guide, saint11, and the GDC VFX bootcamps. Use when: 'add effects', 'make the explosion better', 'hits need more impact' (visual side), 'add a trail/aura/sparkle', 'the effects look muddy/noisy', 'particles tank the framerate', or any Phaser particle emitter / blend mode / post-FX work.
level-design
by kyhLevel, wave, and arena design patterns from the canon (Nintendo's kishōtenketsu, Scott Rogers' Disneyland weenies, Celeste's room design, Valve's experiential density) — structure, pacing, teaching through geometry, guiding the eye, wave grammar for endless games. Use when designing or generating levels, waves, arenas, or difficulty progression: 'design levels for my platformer', 'the level feels empty/confusing', 'players don't know where to go', 'make better waves', 'how should difficulty ramp', 'add more levels'.
onboarding
by kyhFirst-30-seconds design, invisible tutorials, difficulty curves, failure/retry loops and assist modes for link-shared browser games — distilled from George Fan's PvZ tutorial rules, Jenova Chen's flow thesis, Koster's Theory of Fun, Juul's Art of Failure, and Celeste's Assist Mode. Use when: 'players don't get it', 'people quit immediately', 'does it need a tutorial?', 'too hard/too easy', 'tune the difficulty', 'make the start better', 'add an easy mode', or auditing a game's first minute before shipping.
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.