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...
chgis-tgaz
by kltngQuery the China Historical GIS (CHGIS) Temporal Gazetteer (TGAZ) API to search for historical Chinese placenames from 222 BCE to 1911 CE. Use this skill when searching for information about historical Chinese places, administrative units, or geographic locations during the dynastic period. Applicable for queries about historical place names, administrative hierarchies, or when users mention specific Chinese locations with historical context.
cbdb-api
by kltngQuery the China Biographical Database (CBDB) API to retrieve comprehensive biographical data about historical Chinese figures. Use this skill when searching for information about Chinese historical figures, scholars, officials, or literary figures from the 7th century BCE through the 19th century CE. Applicable for queries about biographical details, social relationships, official positions, or when users mention specific Chinese names or CBDB person IDs.
cjk-calendar
by kltngConvert between Chinese, Japanese, Korean, and Vietnamese lunisolar calendar dates and Gregorian/Julian dates. Use when the user needs to look up historical East Asian dates, convert era names (年號) like 康熙, 天保, 崇禎 to Western dates, compute sexagenary cycle (干支) day/month/year, or work with Julian Day Numbers. Supports ~220 BCE to 1945 CE with 1,637 eras and 131,808 lunar month records. Runs entirely locally with a SQLite database.
jbdb-api
by kltngQuery the Japan Biographical Database (JBDB) API to retrieve biographical data about historical Japanese figures. Use this skill when searching for information about Japanese historical figures, samurai, monks, artists, poets, or other individuals. Applicable for queries about biographical details, kinship relations, non-kinship associations, events, personal history, occupations, or when users mention specific Japanese names or JBDB person IDs.
tgaz-query
by kltngQuery and explore the TGAZ (Temporal Gazetteer) SQLite database of 82,000+ historical Chinese placenames spanning 763 BCE to 1911 CE. Use this skill whenever the user asks about historical Chinese places, administrative geography, dynastic jurisdictions, place name evolution, or wants to query tgaz.db. Also trigger when the user mentions CHGIS, TGAZ, historical gazetteer, Chinese historical GIS, or asks questions like "what was X called in dynasty Y", "what counties existed in year Z", "where was X located", or any spatial/temporal query about Chinese historical geography. This skill is relevant even for casual questions like "tell me about ancient Chang'an" or "Tang dynasty cities near the Yellow River".
argue-against-me
by kltngStructured academic debate — Claude adopts an opposing position (from named historiographical schools or disciplinary counter-positions) and challenges your thesis through formal rounds with adjustable intensity. Produces a scorecard, revised thesis, and bibliography gap analysis. Use when stress-testing arguments, preparing for peer review, or strengthening a thesis before publication.
cbdb-local
by kltngQuery the China Biographical Database (CBDB) locally via SQLite for biographical data on 656K+ historical Chinese figures from the 7th century BCE through the 19th century CE. Use when searching for Chinese historical figures, scholars, officials, or literary figures — their biographical details, family/kinship networks, official postings, social associations, examination records, or addresses. Runs entirely locally after initial database download (~556 MB). Faster and more flexible than the API version.
columbia-clio
by kltngSearch Columbia University Libraries' CLIO catalog for books, journals, manuscripts, and other holdings via its Blacklight JSON API. Use this skill whenever the user wants to look up items in Columbia's library, check availability of books at Columbia, search by title/author/subject with faceted filtering by format/language/location, or retrieve detailed catalog records including call numbers and holdings data. Triggers when referencing Columbia University collections or Ivy League library holdings.
harvard-library-catalog
by kltngSearch Harvard Library's 13M+ bibliographic records via LibraryCloud and retrieve MARC/MODS data via PRESTO. Use this skill whenever the user wants to look up books, manuscripts, finding aids, or other items in Harvard's library catalog, verify bibliographic information (title, author, ISBN, publication date), find digital collections, or retrieve detailed catalog records. Also triggers when a user extracts a book title from a document and wants to find its full bibliographic metadata.
hathitrust-catalog
by kltngLook up bibliographic records and digitized volumes in HathiTrust's 17M+ volume collection by ISBN, OCLC, LCCN, ISSN, or HathiTrust ID. Use this skill whenever the user wants to check if a book has been digitized, find which libraries hold a copy, get MARC metadata for a known identifier, or link a bibliographic reference to its HathiTrust digital version. Also triggers when cross-referencing identifiers from other library catalogs (Harvard, Library of Congress) against HathiTrust holdings.
tgaz-query
by kltngQuery and explore the TGAZ (Temporal Gazetteer) SQLite database of 82,000+ historical Chinese placenames spanning 763 BCE to 1911 CE. Use this skill whenever the user asks about historical Chinese places, administrative geography, dynastic jurisdictions, place name evolution, or wants to query tgaz.db. Also trigger when the user mentions CHGIS, TGAZ, historical gazetteer, Chinese historical GIS, or asks questions like "what was X called in dynasty Y", "what counties existed in year Z", "where was X located", or any spatial/temporal query about Chinese historical geography. This skill is relevant even for casual questions like "tell me about ancient Chang'an" or "Tang dynasty cities near the Yellow River".
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.