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...
galaxy-math-strings-conversion
by KimPlaybitInteger and fixed-point math, trigonometry, random numbers, type conversions, string and text operations, color construction, bitwise operations, and number formatting for display in Galaxy script. Use when performing arithmetic, converting between int/fixed/string/text, building display strings, working with colors, or using NativeLib math helpers (ArithmeticIntClamp, Log, RandomPercent). Do not use for point/geometry math (use galaxy-points-regions-geometry).
galaxy-game-systems
by KimPlaybitBank save/load, spawner and wave systems, jungle/camp respawn, resource rewards, hero revive/death, tech tree upgrades, and game attribute lobby options in Galaxy script. Use when implementing persistent data storage, enemy wave spawners, neutral camp respawn timers, kill resource rewards, or player revive logic. Do not use for AI wave behavior (use galaxy-ai-and-techtree) or UI (use galaxy-ui-and-dialogs).
galaxy-ui-and-dialogs
by KimPlaybitDialog and dialog control creation, XML frame hookup, hero/upgrade selection panels, scoreboard panels, dialog events, HUD messages, localized text, minimap pings, and the SSF hooked-frame UI pattern in Galaxy script. Use when building or updating any in-game UI such as dialogs, buttons, labels, images, portraits, click handlers, or player-visible messages. Do not use for actor-based visuals (use galaxy-actor-and-visuals).
sc2-localization-and-text
by KimPlaybitStarCraft II localization and text files — GameStrings.txt, GameHotkeys.txt, ObjectStrings.txt, and TriggerStrings.txt across xxXX.SC2Data/LocalizedData folders. Use when adding, auditing, fixing, or translating localized text keys; checking missing translations; validating blank values, malformed lines, duplicate keys, or missing locale files; and maintaining hotkeys/text consistency across languages. Use the Localization Editor SC2 KSP tool and its CLI when available.
galaxy-units-and-groups
by KimPlaybitUnit creation, properties, behaviors, abilities, XP/leveling, unit groups, orders, death/kill events, custom values, and cargo in Galaxy script. Use when creating units, modifying HP/shields/energy, adding behaviors, issuing orders, querying or iterating unit groups, handling level-up events, or listening for unit death. Do not use for the AI that controls units (use galaxy-ai-and-techtree).
galaxy-players-and-alliances
by KimPlaybitPlayer data patterns, playergroups, alliance setup, race helpers, player resources, camera control, game attributes, difficulty, player state flags, player color, and game-over calls in Galaxy script. Use when initializing alliances at map start, iterating active players, reading or modifying minerals/gas, checking player race, or ending the game for a player or group. Do not use for unit ownership queries (use galaxy-units-and-groups).
galaxy-triggers-and-functions
by KimPlaybitTrigger declaration, event registration, async execution via TriggerExecute, the static parameter pattern for functions that use Wait, trigger management, cinematic sequencer queue, and common event types in Galaxy script. Use when creating triggers, attaching events, executing async functions, or building the trigger init chain. Do not use for unit-specific events (use galaxy-units-and-groups) or dialog events (use galaxy-ui-and-dialogs).
galaxy-sound-camera-environment
by KimPlaybitSound playback, music, camera movement and snapshots, cinematic mode, weather, lighting, and environment effects in Galaxy script. Use when playing sounds or music, moving or configuring the camera, entering cinematic mode, or controlling weather and lighting. Do not use for actor-level sound messages (use galaxy-actor-and-visuals).
galaxy-code-organization
by KimPlaybitFile structure, include order, and modular layout for Galaxy script projects. Use when splitting a monolithic script into multiple files, establishing the MapScript.galaxy bootstrap chain, organizing UI into sub-files, or setting up Enums/GlobalVariables/Header/MapInit. Covers which files are auto-generated by the editor and must never be edited (MapScript.galaxy, LibHASH.galaxy, LibHASH_h.galaxy). Do not use for language syntax questions (use galaxy-language-fundamentals).
galaxy-debug-data-catalog
by KimPlaybitDebug output, Data Table key-value storage, Catalog runtime field access, UserData, and asset preloading in Galaxy script. Use when reading or writing catalog fields at runtime, storing cross-trigger state in the Data Table, printing debug output, or preloading models and sounds. Do not use for bank save/load (use galaxy-game-systems).
galaxy-points-regions-geometry
by KimPlaybitPoints, regions, geometry, pathfinding, and map coordinate helpers in Galaxy script. Use when working with point creation, distance calculations, offsets, region checks, PointWithOffset, PointWithPolarProjection, region creation, or testing if a unit or point is inside a region.
galaxy-language-fundamentals
by KimPlaybitCore Galaxy language syntax, all primitive and engine handle types (including funcref/structref/arrayref), naming conventions, include/file structure, structs, arrays, control flow, and map initialization patterns. Use for any question about Galaxy syntax, type system, variable declarations, or the MapScript bootstrap chain. Also documents which files are auto-generated (MapScript.galaxy, LibHASH.galaxy) and must never be edited.
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.