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...
sentry-issue
by decentralandInvestigate Sentry issues for the Decentraland Unity Explorer project. Trigger whenever a Sentry short ID is mentioned (e.g. UNITY-EXPLORER-M94, WEARABLE-PREVIEW-K3, "look at sentry issue M94", "can you check UNITY-EXPLORER-AB1") OR when a raw exception callstack is pasted. Fetches the issue and full stacktrace directly from Sentry, locates the relevant source files, identifies the root cause, provides reproduction steps, suggests fixes grounded in the project's patterns, and offers to set up a fix branch. Use this skill even if the user just pastes an issue ID without asking a specific question.
mvc-and-ui-architecture
by decentralandMVC UI architecture — controllers, views, window stacking, and shared space. Use when building UI controllers (ControllerBase), showing views via MVCManager, connecting UI to ECS via bridge systems, implementing context menus, settings panels, or coordinating panel visibility.
multiplayer-and-network-sync
by decentralandMultiplayer networking -- LiveKit rooms, movement encoding, interpolation, profile sync, entity-participant mapping. Use when working with RoomHub, movement systems, EntityParticipantTable, or remote player sync.
particle-system
by decentralandEmit particles (fire, smoke, sparks, snow, magic, fireworks) from an entity in a Decentraland SDK7 scene with the ParticleSystem component. Covers emitter shapes (Point, Sphere, Cone, Box), continuous rate vs Burst emission, lifetime/size/color/velocity ranges, gravity and additionalForce, blend modes (ALPHA/ADD/MULTIPLY), billboard and faceTravelDirection, sprite-sheet texture animation, simulation space (local vs world), playback state, and per-scene particle budget. Use when the user asks for particles, sparks, fire, smoke, dust, fog, fireworks, magic effects, snowfall, rain, embers, trails, or atmospheric effects. Do NOT use for procedural entity motion (see animations-tweens), GLTF model effects (see add-3d-models), or 2D UI effects (see build-ui).
deploy-worlds
by decentralandDeploy a Decentraland scene to a World (personal 3D space using a DCL NAME or ENS domain). Covers worldConfiguration setup, Places listing opt-out, and common deployment errors. Use when the user wants to deploy to a World, publish to a personal space, or use a DCL NAME/ENS domain. Do NOT use for Genesis City LAND deployment (see deploy-scene).
npcs
by decentralandCreate NPCs (non-player characters) in Decentraland scenes. Two approaches: the NPC Toolkit library (dcl-npc-toolkit) for GLB-based NPCs with built-in dialogue, movement, and state machines; and AvatarShape for avatar-look NPCs dressed in wearables. Use when the user wants to add an NPC, character, shopkeeper, quest giver, guard, or any non-player entity with behavior or dialogue. For live player data (position, profile, wearables) see player-avatar instead.
nft-blockchain
by decentralandNFT display and blockchain interaction in Decentraland. NftShape (framed NFT artwork), wallet checks (getPlayer, isGuest), signedFetch (authenticated requests), smart contract interaction (eth-connect, createEthereumProvider), and RPC calls. Use when the user wants NFTs, blockchain, wallet, smart contracts, Web3, crypto, or token gating. Do NOT use for player avatar data or emotes (see player-avatar).
add-interactivity
by decentralandEvent-driven interactivity for Decentraland entities. Covers pointerEventsSystem (onPointerDown/Up/hover on entities), proximity events (onProximityDown/Up/Enter/Leave for nearby interactions without aiming), trigger areas (enter/exit zones), raycasting, and one-shot key presses on entities. Use when the user wants clickable objects, hover highlights, proximity-based interactions, detecting when a player enters a zone, E/F key actions on an entity, or ray-hit detection. For system-level polling (held keys, WASD movement, cursor lock, InputModifier, action bar) see advanced-input. For screen-space UI buttons see build-ui.
styled-with-mui
by decentralandWrite MUI styled() components correctly in ui2, avoiding the Emotion component-reference selector trap. Triggers on "styled component", "cross-component hover", "${Component} selector in styled", "hover effect not working", "data-role selector". Use whenever creating or editing a styled() that targets another component.
test-writer
by decentralandWrites and modifies NUnit test classes (Tests/Tests/) for the Decentraland Explorer UI automation test suite. Trigger this skill whenever the user wants to create a new test class, add test methods to an existing class, modify test logic, or write test scenarios for any Explorer feature. Even if the user doesn't say "test" explicitly, trigger when they describe verifying UI behavior, checking that a panel opens/closes, asserting element state, or automating a user flow. If the test requires views, elements, or helper methods that don't exist yet, invoke the view-writer skill to create them before writing the test. Do NOT trigger for creating or modifying view classes (use view-writer), changing test infrastructure (BaseTest, GlobalSetup), or modifying Common/ primitives.
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.