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...
unity-material
by dyCuong03Unity material asset & shader property editing (Built-in / URP / HDRP). Use when users want to create / duplicate / assign materials, set color or emission, set textures (and tiling/offset), change shader, set float/int/vector properties, toggle shader keywords, set render queue, or change GI flags. Triggers (EN): material, .mat, shader, set color, set texture, emission, albedo, base color, metallic, smoothness, glossiness, normal map, render queue, shader keyword, tiling, offset, HDR color, bloom emission, PBR. Triggers (ZH): 材质, 材质球, 材质属性, Shader, 着色器, 颜色, 纹理, 贴图, 法线贴图, 发光, 自发光, 金属度, 光滑度, Render Queue, 渲染队列, 关键字, 平铺, 偏移.
unity-validation
by dyCuong03Project and scene health validation + cleanup helpers — find missing scripts / null references / non-convex MeshColliders / shader compilation errors / oversized textures / potentially unused assets, validate scene issues, remove missing-script placeholders, delete empty folders, get project structure overview. Triggers: validate, validation, health check, sanity check, project health, scene health, missing script, broken reference, null reference, missing prefab, duplicate names, empty folder, unused assets, oversized texture, large texture, non-convex collider, mesh collider performance, shader error, shader compile error, project structure, project overview, validate_scene, validate_find_missing_scripts, validate_fix_missing_scripts, validate_cleanup_empty_folders, validate_find_unused_assets, validate_texture_sizes, validate_project_structure, validate_missing_references, validate_mesh_collider_convex, validate_shader_errors, 验证, 校验, 健康检查, 项目健康, 场景健康, 丢失脚本, 缺失脚本, 引用检测, 空引用, 丢失引用, 重复命名, 空文件夹, 未使用资源…
unity-bookmark
by dyCuong03Scene View bookmarks — save the current selection plus Scene View camera pivot/rotation/size under a name, jump back to it later, list, delete. Use when users want to save, recall, or manage scene viewpoints + selections in the editor. Triggers: bookmark, bookmarks, save view, goto view, jump to view, scene view, camera position, viewpoint, viewpoints, named view, selection snapshot, 书签, 视角, 保存视角, 视图书签, 跳转视角, 选中快照, 命名视角.
unity-camera
by dyCuong03Unity Scene View + Game Camera control. Use when users want to move/rotate the editor view, create or configure scene cameras, change FOV / clip planes / culling mask, switch orthographic vs perspective, or capture a screenshot. Triggers (EN): Unity camera, scene camera, Game Camera, Scene View, viewport, FOV, field of view, near/far clip, culling mask, orthographic, perspective, look at, align view, screenshot, render to file. Triggers (ZH): 相机, 摄像机, 视角, 视野, 场景视图, 游戏相机, 截图, 渲染截图, 正交, 透视, 裁剪面, 剔除遮罩.
unity-shadergraph-design
by dyCuong03Source-anchored Shader Graph design rules for Unity 2022.3 / ShaderGraph 14 and Unity 6 current Graphics. Load before proposing graph structure, node chains, SubGraph boundaries, keyword strategy, property/blackboard layout, or ShaderGraph editing plans. Triggers: ShaderGraph, Shader Graph, shadergraph design, shadergraph architecture, shadergraph recipe, shadergraph pitfalls, shadergraph review, SubGraph, Master Stack, Blackboard, Keyword, Boolean Keyword, Enum Keyword, Material Keyword, Shader Keyword, PropertyNode, Custom Function Node, Sample Texture 2D, Sample Texture 2D Array, Sample Cubemap, Lerp, Step, Smoothstep, Remap, OneMinus, Normalize, Saturate, Time, UV, Tiling And Offset, Normal Vector, World Position, Object Position, Screen Position, Fresnel Effect, NormalFromHeight, Vertex stage, Fragment stage, Lit Target, Unlit Target, Sprite Lit Target, Fullscreen Target, URP shader, HDRP shader, Built-in shader, ShaderGraph 14, com.unity.shadergraph, shadergraph_list_supported_nodes…
unity-shadergraph
by dyCuong03Shader Graph asset creation, structure inspection, constrained blackboard editing, and constrained node-subset editing for `.shadergraph` / `.shadersubgraph`. Use when users want to create graphs, inspect real node/slot structure, edit properties or keywords, or perform safe low-level node operations. Triggers: Shader Graph, shadergraph, sub graph, blackboard property, shader keyword, node editing, slot connect, 着色图, 子图, ShaderGraph 属性, ShaderGraph 节点, ShaderGraph 连线.
unity-workflow
by dyCuong03Persistent operation history, snapshots, task/session undo, bookmarks, and batch planning/retry. Use when users want to record a task, snapshot before modification, undo/redo by task or session (conversation-level), list/delete tasks, manage scene-view bookmarks, generate combined execution plans, query assets pre-batch, or retry failed batch items. Triggers: workflow, task, task start, task end, session, session undo, session-level undo, conversation undo, snapshot, snapshot object, rollback, revert, persistent history, undo task, redo task, bookmark, save bookmark, goto bookmark, list bookmarks, plan skills, batch retry, retry failed, batch query assets, 工作流, 任务, 任务快照, 会话, 会话撤销, 对话级撤销, 快照, 回滚, 还原, 持久历史, 撤销任务, 重做任务, 书签, 保存书签, 跳转书签, 列出书签, 技能计划, 批量重试.
unity-dots
by dyCuong03Index of 96 senior-level Unity DOTS/ECS skills mined from EntityComponentSystemSamples — covering entities, jobs, Burst, physics, netcode, baking, and transforms. Read ROUTING.md first to locate the right sub-skill. Do NOT load this index file as a standalone skill.
unity-unitask-design
by dyCuong03Source-anchored design rules for Cysharp UniTask 2.5.10 (Unity 2018.4+). Load before writing any async UniTask / UniTaskVoid / PlayerLoopTiming / CancellationToken / WhenAll / ToUniTask code to avoid double-await crashes, forgotten .Forget(), wrong PlayerLoopTiming choices, WebGL ThreadPool crashes, and handle leaks. Triggers: UniTask, UniTaskVoid, UniTaskCompletionSource, PlayerLoopTiming, async UniTask, Forget, WhenAll, WhenAny, UniTask.Yield, UniTask.Delay, UniTask.NextFrame, WaitForEndOfFrame, WaitForFixedUpdate, WaitUntil, WaitWhile, SwitchToMainThread, SwitchToThreadPool, GetCancellationTokenOnDestroy, CancellationTokenSourceExtensions, UniTaskAsyncEnumerable, AsyncReactiveProperty, ToUniTask, AsyncOperation, UnityWebRequest, UniTaskTracker, AttachExternalCancellation, AsyncTrigger, OnDestroyAsync, 异步任务, 不分配异步, 取消令牌, 任务取消, 玩家循环, 异步流, 零分配, async await unity, unity async, unity cancellation, unity coroutine alternative, zero allocation async.
memory-safety
by dyCuong03Native container lifetime, allocator selection, and GC-avoidance rules for DOTS runtime code. Covers NativeArray/NativeList/NativeHashMap disposal patterns, Allocator.Temp vs TempJob vs Persistent guidance, and managed-allocation detection. Replaces the memory-checker subagent.
malformed-frontmatter
by dyCuong03This frontmatter is intentionally broken
editor-data-tools
by dyCuong03Guidance for Unity data processing, editor tooling, validators, and DOTS debugging helpers. Use when building authoring workflows, diagnostics, inspectors, or developer utilities. Always isolates editor code from runtime assemblies.
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.