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...
minutes-lint
by silversteinHealth-check your meeting knowledge for contradictions, stale commitments, and decision conflicts. Use when the user asks "any conflicts in my meetings", "check for stale action items", "lint my meetings", "consistency check", "are there contradictions", or wants to audit their decision history.
meeting-notes
by openyakMeeting notes organization — extract key points from raw records, identify decisions and action items (Who/What/When), structured output.
land-reduction-trespass
by aiskillstoreClerk for reserve reduction, trespass, survey errors, and railway takings; use when processing the Land_Reduction_Trespass queue.
consensus-synthesis
by yogsoth-aiSynthesize all rounds into a final consensus report documenting agreements, dissent, and process.
country-australia
by Amanbh997Australia architectural code and regulatory reference. Covers the National Construction Code 2022 (NCC 2022, published by Australian Building Codes Board ABCB) -- Volume One (Class 2-9 Building Code of Australia), Volume Two (Class 1 + 10 -- Housing Provisions), Volume Three (Plumbing Code of Australia); Australian Standards including AS/NZS 1170.0-2002 + 1170.1-2002 + 1170.2-2021 wind + 1170.3-2003 snow + 1170.4-2007 seismic, AS 3600-2018 concrete, AS 4100-2020 steel, AS 1684-2010 residential timber, AS 1170.4 seismic, AS 1530.1/.2/.3/.4/.8 fire test methods, AS 4072 service penetration sealing, AS 1428.1-2021 accessibility, AS 1428.4 tactile, AS/NZS 4586 slip resistance, AS 1668 ventilation, AS 1680 lighting; the Disability (Access to Premises -- Buildings) Standards 2010 + Disability Discrimination Act 1992; the 7-star NatHERS (Nationwide House Energy Rating Scheme) mandatory for new Class 1 housing from 2022; state-specific overlays (NSW Planning + Environmental Planning Instruments, Victoria Plumbing Reg
country-saudi-arabia
by Amanbh997Kingdom of Saudi Arabia architectural code and regulatory reference. Covers the Saudi Building Code (SBC) nine-part series issued by the Saudi Building Code National Committee (SBCNC): SBC 201 General Building, SBC 301 Structural Loads (ASCE 7-derived), SBC 302 Concrete (ACI 318-derived), SBC 304 Soil and Foundations, SBC 305 Masonry, SBC 306 Steel (AISC-derived), SBC 401 Electrical, SBC 501 Mechanical, SBC 601 Energy Conservation, SBC 701 Plumbing, SBC 801 Fire (NFPA-aligned), SBC 901 Existing Buildings, SBC 1001 Green Buildings. Also covers the General Directorate of Civil Defence regulations, Saudi Universal Accessibility Code, Mostadamah (Saudi Green Building Program), the Vision 2030 giga-projects (NEOM, Qiddiya, Red Sea, Diriyah, ROSHN), Amana (Municipality) approval workflows, Saudi Energy Efficiency Center (SEEC) programs, and Royal Commission jurisdictions (Jubail/Yanbu/AlUla). Includes Mecca/Medina special restrictions (Hajj building regulations), Aramco housing standards reference, and the hot-arid
country-uae
by Amanbh997United Arab Emirates architectural code and regulatory reference. Covers the federal regulatory framework (UAE Fire and Life Safety Code of Practice 2018 by General Civil Defence, Federal Law 29/2006 + 2/2014 + 1/2020 for People of Determination, ESMA standards) plus the seven Emirates' independent codes: Dubai Building Code 2021 (DBC), Dubai Civil Defence regulations, Trakhees regulations for free zones, Dubai Green Building Regulations & Specifications 2011 + Al Sa'fat 2016, Dubai Universal Design Code 2017; Abu Dhabi International Building Code 2013 (ADIBC, IBC-derived), Estidama Pearl Building Rating System 2010, DMA Accessibility Code; Sharjah Department of Planning and Survey rules; northern emirates' deferral patterns to Abu Dhabi or Dubai codes. Includes climate zone hot-arid design overlays, sandstorm/ thermal expansion loads, ADM/DM approval workflows, RERA Dubai project registration, developer-master-developer-end-customer hierarchies (Emaar, Aldar, Nakheel masterplan compliance), DEWA/ADDC utility
geographic-foundations
by Amanbh997Auto-activated geographic context router for the Architect Skills plugin. Detects the country or jurisdiction of any architectural query and routes to the correct country-specific dossier (India, UAE, Saudi Arabia, USA, UK, Germany, Singapore, Japan, China, Australia). Encodes the global regulatory landscape: which authority issues which code, the hierarchy between national/state/municipal regulation, code adoption status by version year, the dominant energy/seismic/fire/accessibility codes per jurisdiction, and the cross-walk between national codes and the international reference systems (IBC, NFPA, Eurocodes, ISO, ASCE). Maintains a precise inventory of which country uses which Eurocode National Annex, which states/emirates/ Lander/prefectures publish their own modifications, and where international standards apply by reference. Triggers country-specific skills when geographic context is detected in user query (city name, project location, language cues, code reference) and supplies global framework compari
tw-formal-writing
by Imbad0202台灣正式文件撰寫助手 — 涵蓋政府公文、政府非公文文件、法律文件、人民對政府文書等所有中文正式文件的撰寫。 根據使用者意圖自動判斷文件類別，載入對應的撰寫規範與格式指引。 觸發此 skill 的情境： - 政府公文：簽、函、書函、公告、令、呈、咨、箋函、便簽、行文、發文、簽辦、擬稿、陳核、簽稿併陳、以稿代簽、先簽後稿、上行文、下行文、平行文 - 政府非公文文件：會議紀錄、開會通知單、新聞稿、聲明稿、施政報告、出國報告、計畫書、裁處書、訴願決定書、聘函、獎狀、證書 - 法律文件：存證信函、律師函、合約書、備忘錄(MOU)、保密協議(NDA)、聲明書、切結書、委託書、授權書 - 人民對政府文書：陳情書、申請書、訴願書、異議書、申覆書 - 描述需要撰寫正式文件的情境（如「幫我寫一封給教育部的公文」「我要寄存證信函」「幫我寫陳情書」） - 詢問任何正式文件的格式或用語規範 - 公務員考試或受訓的公文練習題 不應觸發的情境： - 商業 email、求職信、履歷 - 學術論文、研究計畫書 - 商業計畫書、簡報 - 私人書信、感謝卡 - 翻譯任務 - 純粹的文章潤飾或改寫
building-permit-application-documents
by h30190This skill should be used when architects or construction professionals need to understand the standard building permit application documents and requirements in Taiwan.
jp-university-admission-notion
by sonnyginAutomate the rigorous extraction of critical admission information from Japanese university application guidelines (募集要项) and archive the structured data to Notion. Triggered when a user provides a PDF, text, or URL of Japanese university admission guidelines and requests information extraction, summary, or Notion archiving. Also triggered by keywords like "募集要项", "出愿", "招生简章".
land-reduction-trespass
by ComeOnOliverClerk for reserve reduction, trespass, survey errors, and railway takings; use when processing the Land_Reduction_Trespass queue.
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.