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...
product-owner-expert
by ozkayasYazılım geliştirme süreçlerinde backlog yönetimi, user story yazımı ve önceliklendirme konusunda uzmanlaşmış Product Owner yeteneği. Belirsiz fikirleri net, uygulanabilir gereksinimlere dönüştürür; INVEST prensiplerine uygun user story'ler yazar; RICE veya MoSCoW ile backlog önceliklendirir; Gherkin formatında kabul kriterleri hazırlar; kapsamlı PRD dokümanları üretir. Kullanıcı "user story yaz", "backlog'u önceliklendir", "PRD hazırla", "kabul kriterleri ekle" veya ürün gereksinimiyle ilgili bir talep getirdiğinde bu skill'i aktive et.
jlpt-n5-listening-select-audio-tester
by ozkayasValidate JLPT N5 Listening Mondai 3 (発話表現 / selectAudio) derived-data.json files. Performs 6 passes: (1) mechanical schema validation via script, (2) semantic/linguistic N5-level review, (3) TTS script generation, (4) Imagen 3 image generation, (5) Gemini TTS audio generation, (6) final question.json build. Use when the user asks to 'selectAudio test et', 'derived-data doğrula', 'expression question test', or after generating a question with the select-audio-creator skill.
jlpt-n5-listening-variation-tester
by ozkayasValidate derived-data.json files produced by jlpt-n5-listening-variation-creator, then verify the generated image.png, convert it to WebP for mobile, generate TTS audio, and build the final question.json for Firebase. Use this skill when the user asks to test, validate, check, or verify a listening variation. Performs six passes: (1) mechanical schema validation via script, (2) semantic/linguistic review by Claude, (3) visual image check by Claude reading image.png, (3.5) image optimization to WebP, (4) Gemini TTS audio generation, (5) build final question.json. Trigger on requests like 'variation test et', 'validate derived-data', 'listening varyasyonu doğrula', 'check derived-data.json', or after generating a variation with the creator skill.
jlpt-n5-reading-passage-creator
by ozkayasGenerate JLPT N5 reading passages (short or mid type) in JSON format. Use this skill when the user asks to create, generate, or produce N5 reading passages, comprehension texts, or reading questions. Handles the full pipeline: Japanese core content generation, 5-language translation, file saving, and optional Firebase upload. Trigger on requests like 'N5 okuma metni üret', 'create N5 reading passage', 'short passage oluştur', 'mid passage yaz', 'generate reading comprehension', 'JLPT N5 okuma sorusu oluştur'.
jlpt-grammer-question-tester
by ozkayasValidate JLPT grammar question JSON files produced by jlpt-n5-grammer-essential-grammer-question-creator. Use this skill when the user asks to test, validate, check, or verify JLPT grammar questions in JSON format. Checks three things: (1) schema/format correctness of all fields, (2) correctAnswer is a valid 0-based index within options, (3) question level is n5. Trigger on requests like soruları test et, validate questions, JSON dogrula, check grammar questions, or after generating questions with the creator skill.
jlpt-listening-multi-language-expander
by ozkayasTransform a JLPT N5 Listening 'question.json' into a 'Fat JSON' architecture supporting 6 UI languages: TR, EN, DE, FR, ES, and KO. This skill extracts the Japanese core content and generates high-quality, N5-appropriate translations for all fields (transcription, vocabulary, grammar, and logic). Use when the user wants to add international support to a listening question or migrate to the multi-language schema.
jlpt-n5-listening-point-comprehension-creator
by ozkayasGenerate JLPT N5 Listening Point Comprehension (Mondai 2 / selectText) questions by creating variations of source questions from clip folders. Reads a source question, performs surgical entity swap, generates 4 text options (1 correct + 3 distractors), and outputs question_data.json. Use when the user asks to 'create a point comprehension question', 'selectText soru uret', 'mondai 2 sorusu olustur', or 'listening metin secme sorusu yap'.
jlpt-n5-listening-point-comprehension-tester
by ozkayasValidate JLPT N5 Listening Point Comprehension (selectText) question_data.json files. Performs mechanical schema validation, semantic/linguistic N5-level review, and generates TTS script for audio production. Use when the user asks to 'test selectText', 'validate point comprehension', 'selectText soruları test et', 'point comprehension doğrula', or after generating questions with the creator skill.
active-recall-pool-creator
by ozkayasGenerate and maintain active_recall_pool.json for the vocabulary SRS active recall system. Use when the user asks to create, extend, regenerate, or improve active recall checkpoints, sentences, hints, or translations. Trigger on requests like 'active recall oluştur', 'yeni checkpoint ekle', 'grammar hints düzelt', 'active recall pool genişlet', 'create active recall questions', 'add checkpoint for 60 words'. Also use when reviewing or fixing quality issues in existing active recall content (poor hints, missing checkpoints, translation errors).
jlpt-grammer-sentence-building-question-tester
by ozkayasValidate JLPT sentence building (starQuestion) JSON files produced by jlpt-n5-grammer-sentence-building-question-creator. Use this skill when the user asks to test, validate, check, or verify sentence building questions in JSON format. Checks: (1) schema/format correctness of all fields, (2) correctOrder is a valid permutation of [0,1,2,3], (3) starPosition is 0-3, (4) scrambledWords has exactly 4 items, (5) level is n5. Trigger on requests like 'sentence building soruları test et', 'validate sentence building questions', 'cümle birleştirme soruları doğrula', 'check starQuestion JSON', or after generating questions with the sentence building creator skill.
jlpt-n5-grammer-sentence-building-question-creator
by ozkayasGenerate JLPT N5 sentence building (starQuestion) questions in JSON format. Use this skill when the user asks to create, generate, or produce N5 sentence building questions, word-order exercises, or scrambled sentence questions. Output is a JSON object containing a "questions" array with starQuestion type items, each including sentencePrefix, sentenceSuffix, 4 scrambledWords, starPosition, and correctOrder. Trigger on requests like "N5 cümle birleştirme sorusu üret", "create N5 sentence building questions", "generate word order questions", "JLPT N5 mondai2 soru oluştur", or "scrambled sentence questions".
jlpt-n5-grammer-text-integration-question-creator
by ozkayasGenerate JLPT N5 text-level grammar (Mondai 3) questions in JSON format. Use this skill when the user asks to create, generate, or produce N5 text-level grammar questions, text integration exercises, or "metin tamamlama" questions. Output is a JSON object with a "textFlow" type, containing "title", "textSegments", and "blanks" array. Trigger on requests like "N5 Mondai 3 sorusu üret", "create N5 text integration questions", "generate text-level grammar", or "JLPT N5 metin bütünleme sorusu oluştur".
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.