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...
fluent-feedback-formatter
by m98Canonical feedback template for every learner answer in the Fluent system — celebrate correct parts, correct mistakes with category and brief explanation, show the full correct version, score out of 10, and classify severity (🔴 critical / 🟡 moderate / 🟢 minor). Use in every practice session (fluent-writing, fluent-vocab, fluent-speaking, fluent-reading, fluent-review) immediately after the learner submits an answer.
fluent-learn
by m98Main adaptive language-learning session that mixes skills (writing, speaking, vocabulary, reading) and exercise types based on the learner's current level, weak patterns, and due reviews. Triggered only when the learner types /fluent-learn. Greets the learner, shows today's plan, asks what to practice, runs interleaved exercises one at a time, and updates all databases at the end.
fluent-reading
by m98Run an interactive reading comprehension session with a short target-language text followed by main-idea, detail, vocabulary-in-context, inference, and true/false questions. Triggered only when the learner types /fluent-reading. Presents the text, waits for the learner to read, then asks questions one at a time with immediate feedback, and optionally adds new vocabulary to the spaced-repetition queue.
fluent-review
by m98Run today's spaced-repetition review queue — items scheduled by SM-2 that need reinforcement before the learner forgets them. Triggered only when the learner types /fluent-review. Pulls due items from spaced-repetition.review_queue.today, generates a targeted exercise for each, evaluates the response, updates SM-2 parameters, and reshelves items into the correct future queue.
fluent-speaking
by m98Run an interactive typed conversation session simulating spoken practice — free-flowing dialogue, role-plays, and opinion questions prioritizing communication over perfect grammar. Triggered only when the learner types /fluent-speaking. Asks questions one at a time in the target language, evaluates clarity and naturalness first and grammar second, and updates all databases at the end.
fluent-writing
by m98Run an interactive writing practice session (emails, letters, forms, short texts) with systematic error analysis, category-tagged corrections, and detailed feedback. Triggered only when the learner types /fluent-writing. Selects a scenario matched to mastery, lets the learner compose, then analyzes grammar, register, vocabulary, structure, and spelling before updating all databases.
fluent-vocab
by m98Run an interactive vocabulary drill session with flashcard-style prompts, spaced repetition, and per-answer feedback. Triggered only when the learner types /fluent-vocab. Reads spaced-repetition / mistakes / mastery DBs to pick words, presents one word at a time, scores each answer, and calls fluent-db-updater at the end.
fluent-db-updater
by m98Atomically update all 6 Fluent learner databases (learner-profile, progress, mistakes, mastery, spaced-repetition, session-log) at session end by calling .claude/hooks/update-db.py with a single JSON payload. Use at the end of every practice session — fluent-writing, fluent-vocab, fluent-speaking, fluent-reading, fluent-review, fluent-learn — to persist the session's errors, review results, new vocabulary, and session metadata.
fluent-progress
by m98Show the learner's language learning progress, statistics, mastery levels, streak, and achievements. Use when the learner asks "how am I doing", "show my progress", "stats", "dashboard", "what's my streak", "how many words have I learned", or invokes /fluent-progress. Read-only — safe to auto-invoke.
fluent-session-analyzer
by m98Parse Fluent `/results/*.md` session files to extract error patterns, strengths, accuracy trends, and focus areas for the next session. Use when the tutor needs to analyze the learner's recent performance — planning the next lesson, recommending focus areas, or answering "what should I practice next?".
fluent-setup
by m98One-time interactive onboarding that creates the learner's personalized language-learning profile — name, target language, native language, current/target CEFR level, timeline, daily minutes, and learning goals. Triggered only when the learner types /fluent-setup. Also handles profile updates and resets for returning users. Must never auto-invoke because re-running can reset progress.
fluent-sm2-calculator
by m98SM-2 spaced-repetition algorithm reference for the Fluent language learning system. Use whenever the tutor schedules the next review of a vocabulary item, grammar rule, or error pattern — i.e. after every answered review question. Defines the 0-5 quality scale, interval formula, easiness-factor update, and mastery-level transitions that keep the spaced-repetition database correct.
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.