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...
sommelier-wine-master
by swaylq侍酒师与葡萄酒 (侍酒师 / 葡萄酒 (Sommelier & Wine) — 葡萄酒鉴赏 + 侍酒服务的职业认知操作系统，从业者/侍酒师/学习者视角。覆盖: (a) 两大认证体系张力 — WSET (Wine & Spirit Education Trust, 英国, 知识+SAT 系统化品鉴方法, Diploma/L4 笔试导向) vs Court of Master Sommeliers (CMS, 美/英, 服务+盲品演绎法+理论三位一体, MS 头衔), 外加 Institute of Masters of Wine (MW, 学术研究+论文) 与 UC Davis 葡萄酒学/葡萄栽培学学院派; (b) 盲品 = 纯 tacit 校准技能 — 演绎品鉴网格 (deductive tasting: 看色/闻香/品味 → 结构线索 calculated structure → 推断品种/产区/年份/酒龄), WSET SAT vs CMS deductive grid 两套方法论; (c) 第一性张力 — codifiable 理论层 (产区/品种/酒法/风土/酿造/葡萄栽培) ⇄ tacit 校准层 (品鉴味觉记忆/盲品/侍酒服务), 这行的核心矛盾是「可背诵的知识」与「不可言传的味觉」之间; (d) 旧世界 vs 新世界框架 — 旧世界以风土/法定产区为组织原则 (AOC/DOCG/QbA 分级法), 新世界以品种为标签; 风土 (terroir) 是核心组织概念; (e) 侍酒服务/酒店层 — 餐厅 floor 的配餐 (food pairing)、醒酒/侍酒温度、酒单与酒窖管理、by-the-glass 与饮品项目经济学、盲品 service exam; (f) 葡萄酒商业层 — 三级分销体系 (美国 three-tier)、定价/配额 (allocation)、期酒 (en primeur)、投资酒 (Liv-ex) 与拍卖; (g) 智识/品味演进 — 帕克百分制 (Robert Parker / Wine Advocate 100-point) vs Jancis Robinson 20 分制散文派; 经典派 vs 现代派酿造; 自然酒/低干预 (natural/minimal-intervention) vs 传统技术派. 学派分歧: WSET 知识体系派 vs CMS 服务盲品派、旧世界风
food-order
by NJX-njxReorder Foodora orders + track ETA/status with ordercli. Never confirm without explicit user approval. Triggers: order food, reorder, track ETA.
ordercli-hardened
by faberlensFoodora-only CLI for checking past orders and active order status (Deliveroo WIP).
mian-hun
by voidful台灣拉麵客製化推薦引擎與知識百科 — Taiwan Ramen AI Skill. 1069+ shops, 6 broth types, personalized recommendations. Triggers on: 拉麵/ramen/推薦/豚骨/雞白湯/味噌/鹽味/醬油/沾麵/ 拌麵/排隊拉麵/台北拉麵/台中拉麵/高雄拉麵/想吃拉麵/今天吃什麼/ 麵屋/湯頭/麵體/叉燒/溏心蛋 and any Taiwan ramen related query.
doordash
by majiayu000Enables Claude to browse restaurants, manage orders, and track deliveries on DoorDash
yes-drink-bitter
by gabrielmoreiraGeneral SOP for common requests related to yes, drink, bitter.
taiwan-hungry-soul
by AppantasyArthurLai台灣吃食文化基因注入 Skill。當使用者詢問台灣小吃、夜市美食、特定食物推薦（鹹酥雞、臭豆腐、珍珠奶茶、滷肉飯、蚵仔煎等）、 「哪裡好吃」「有什麼推薦」、宵夜覓食等相關問題時啟用。也適用於使用者提到特定城市或地區搭配美食意圖的情境， 例如「台南吃什麼」「士林夜市必吃」「台北宵夜」。即使使用者只是隨口說「肚子餓」「想吃東西」「宵夜吃什麼」「帶朋友去哪吃」， 只要語境與台灣美食相關，都應觸發此 Skill。
ordercli
by hridesh-netFoodora-only CLI for checking past orders and active order status (Deliveroo WIP).
restaurant-meal-finder
by NanoRhinoOn-demand restaurant meal recommendation skill. When the user asks "what should I eat?" or wants dining suggestions, this skill first establishes the user's location, searches for nearby restaurants and delivery options, caches them locally, and then recommends specific calorie-appropriate meals from those real restaurants. The restaurant list is persisted so repeat queries don't require re-searching. Use this skill whenever the user asks for restaurant recommendations, what to order when eating out, nearby dining options that fit their diet, or fast-food / takeout / convenience store meal suggestions. This skill complements the meal-planner (which builds restaurant options into weekly plans) by handling real-time, on-the-spot dining decisions grounded in the user's actual nearby options.
ordercli
by 0xKoboldFoodora-only CLI for checking past orders and active order status (Deliveroo WIP).
umea-lunch
by duclm1x1Get today's lunch menus from restaurants in Umeå. Use when asking about lunch, restaurants, or food in Umeå. Fetches live data from umealunchguide.se.
order-food
by garavitgabrielOrder food delivery from Rappi. Use when the user wants to order food, get delivery, find restaurants, browse menus, or mentions Rappi.
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.