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...
jlpt-doc-hieu-tong-hop
by nguyendinhsinh361Generate JLPT "đọc hiểu tổng hợp" (integrated / comparative comprehension / 統合理解) reading items as styled HTML files and output CSV training data for AI fine-tuning. Each item contains **TWO short Japanese passages A and B (total 600–800 characters)** on the same topic — with contrasting / complementary / debating viewpoints — tested via **2 multiple-choice questions per item that probe comparison and integration across A and B**. All questions use the fixed label `question_comprehensive_understanding`. This skill applies ONLY to N1 (≈600-750 chars total) and N2 (≈600-800 chars total). Other JLPT levels do NOT have this reading type. Skill này bao gồm TOÀN BỘ luồng: gen → QC loop (checklist PASS/FAIL) → sửa. Gen từng bài một, kiểm tra đến khi đạt chất lượng mới chuyển sang bài tiếp theo. Output chỉ gồm HTML + CSV (không có screenshot PNG). Use this skill whenever the user wants to: gen bài đọc hiểu tổng hợp, tạo nội dung integrated / comparative reading, generate JLPT 統合理解 / comparative passages, produce AI f
jlpt-doc-hieu-chu-de
by nguyendinhsinh361Generate JLPT "đọc hiểu chủ đề" (thematic comprehension / 主張理解) reading comprehension passages as styled HTML files and output CSV training data for AI fine-tuning. Each passage is an abstract/logical Japanese essay of 900–1200 characters — typically an editorial, critique, or philosophical essay — testing grasp of the author's overall thesis and main arguments via 3 multiple-choice questions per passage. **CHỈ áp dụng N1 (3 câu, ~1000-1200 chars) và N2 (3 câu, ~900-1100 chars)** — N3/N4/N5 KHÔNG có dạng này. Skill này bao gồm TOÀN BỘ luồng: gen → QC loop (checklist PASS/FAIL) → sửa. Gen từng bài một, kiểm tra đến khi đạt chất lượng mới chuyển sang bài tiếp theo. Output chỉ gồm HTML + CSV (không có screenshot PNG). Skill này chỉ dành riêng cho dạng "đọc hiểu chủ đề" (主張理解). Use this skill whenever the user wants to: gen bài đọc hiểu chủ đề, tạo nội dung thematic comprehension, generate JLPT 主張理解 passages, produce AI fine-tuning data for the "đọc hiểu chủ đề" section of JLPT N1 or N2, kiểm tra chất lượng, qual
jlpt-doan-van-dai
by nguyendinhsinh361Generate JLPT "đoạn văn dài" (long-passage / 長文読解) reading comprehension passages as styled HTML files and output CSV training data for AI fine-tuning. Each passage is a long Japanese prose text (550–1150 characters depending on level) testing deep comprehension of outline, logical development, author's ideas, and reference phrases via 3-4 multiple-choice questions per passage. **CHỈ áp dụng N1 (3 câu, ~1000 chars) và N3 (4 câu, ~550 chars)** — N2/N4/N5 KHÔNG có dạng này. Skill này bao gồm TOÀN BỘ luồng: gen → QC loop (checklist PASS/FAIL) → sửa. Gen từng bài một, kiểm tra đến khi đạt chất lượng mới chuyển sang bài tiếp theo. Output chỉ gồm HTML + CSV (không có screenshot PNG). Skill này chỉ dành riêng cho dạng "đoạn văn dài" (長文読解). Use this skill whenever the user wants to: gen bài đoạn văn dài, tạo nội dung đoạn văn dài, generate long-passage reading comprehension, create JLPT 長文 passages, produce AI fine-tuning data for the đoạn văn dài section of JLPT N1/N3, kiểm tra chất lượng, quality check, review bài
jlpt-doan-van-ngan
by nguyendinhsinh361Generate JLPT "đoạn văn ngắn" (short-passage / 短文読解) reading comprehension passages as styled HTML files and output CSV training data for AI fine-tuning. Each passage is a short Japanese prose text (80–290 characters depending on level) testing content understanding via a single multiple-choice question. Skill này bao gồm TOÀN BỘ luồng: gen → QC loop (checklist PASS/FAIL) → sửa. Gen từng bài một, kiểm tra đến khi đạt chất lượng mới chuyển sang bài tiếp theo. Output chỉ gồm HTML + CSV (không có screenshot PNG). Skill này chỉ dành riêng cho dạng "đoạn văn ngắn" (短文読解). Use this skill whenever the user wants to: gen bài đoạn văn ngắn, tạo nội dung đoạn văn ngắn, generate short-passage reading comprehension, create JLPT 短文 passages, produce AI fine-tuning data for the đoạn văn ngắn section of JLPT N1-N5, kiểm tra chất lượng, quality check, review bài, QC. Also trigger when the user mentions: gen bài đoạn văn ngắn, tạo short passage, generate JLPT 短文, short reading passage N1/N2/N3/N4/N5.
jlpt-doan-van-ngan
by nguyendinhsinh361Generate JLPT "đoạn văn ngắn" (short-passage / 短文読解) reading comprehension passages as styled HTML files and output CSV training data for AI fine-tuning. Each passage is a short Japanese prose text (80–290 characters depending on level) testing content understanding via a single multiple-choice question. Skill này bao gồm TOÀN BỘ luồng: gen → QC loop (checklist PASS/FAIL) → sửa. Gen từng bài một, kiểm tra đến khi đạt chất lượng mới chuyển sang bài tiếp theo. Output chỉ gồm HTML + CSV (không có screenshot PNG). Skill này chỉ dành riêng cho dạng "đoạn văn ngắn" (短文読解). Use this skill whenever the user wants to: gen bài đoạn văn ngắn, tạo nội dung đoạn văn ngắn, generate short-passage reading comprehension, create JLPT 短文 passages, produce AI fine-tuning data for the đoạn văn ngắn section of JLPT N1-N5, kiểm tra chất lượng, quality check, review bài, QC. Also trigger when the user mentions: gen bài đoạn văn ngắn, tạo short passage, generate JLPT 短文, short reading passage N1/N2/N3/N4/N5.
jlpt-doan-van-vua
by nguyendinhsinh361Generate JLPT "đoạn văn vừa" (medium-passage / 中文読解) reading comprehension passages as styled HTML files and output CSV training data for AI fine-tuning. Each passage is a medium-length Japanese prose text (250–620 characters depending on level) testing the learner's ability to understand causal relations, reasoning, author's ideas, reference phrases, and key vocabulary via 2-3 multiple-choice questions per passage (N1/N2/N5 = 2 câu, N3/N4 = 3 câu). Skill này bao gồm TOÀN BỘ luồng: gen → QC loop (checklist PASS/FAIL) → sửa. Gen từng bài một, kiểm tra đến khi đạt chất lượng mới chuyển sang bài tiếp theo. Output chỉ gồm HTML + CSV (không có screenshot PNG). Skill này chỉ dành riêng cho dạng "đoạn văn vừa" (中文読解). Use this skill whenever the user wants to: gen bài đoạn văn vừa, tạo nội dung đoạn văn vừa, generate medium-passage reading comprehension, create JLPT 中文 passages, produce AI fine-tuning data for the đoạn văn vừa section of JLPT N1-N5, kiểm tra chất lượng, quality check, review bài, QC. Also trigger wh
topik-read-qc
by nguyendinhsinh361QC dữ liệu TOPIK Đọc. Đọc CSV, kiểm tra toàn bộ tiêu chí, tự động sửa lỗi, lặp đến 0 lỗi.
topik-write-qc
by nguyendinhsinh361QC dữ liệu TOPIK Viết. Đọc CSV, kiểm tra toàn bộ tiêu chí, tự động sửa lỗi, lặp đến 0 lỗi.
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.