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...
create-mascot-pack
by TeXmeijinCreate or modify pixel-art mascot packs for claude-code-mascot-statusline plugin. Use when: creating a new character pack from scratch, modifying existing pack sprites, fixing visual issues in half-block rendering, iterating on sprite design, or adding new states to a pack. Triggers: "create pack", "new mascot", "pixel art", "make character", "edit sprite", "fix sprite", "パック作成", "キャラ作成", "スプライト編集", "new pack", "mascot pack", "インベーダー", "キャラクター"
case
by TeXmeijinOpens a browser UI for the user to answer multiple-choice design/policy decisions with recommended defaults, per-question free-text override, and shared notes; returns structured JSON. TRIGGER when about to enumerate '1. X? 2. Y? 3. Z?' style questions in chat, or when presenting 2+ decisions at once, or when a single decision has a clear recommendation worth an explicit ack. トリガー: 「いくつか方針を決めて」「選択肢を整理して」「推奨つきで意思決定したい」「〜にするか〜にするか」。SKIP: a single yes/no confirmation, or a question whose answer is derivable from code/conversation.
ghostty-applescript
by TeXmeijinWrite Ghostty terminal AppleScript layout scripts. Generates automation scripts for windows, tabs, pane splits, and command execution with correct syntax. Use for "Ghostty layout", "Ghostty AppleScript", "terminal pane layout script", or Zellij KDL to AppleScript conversion.
layered-flow-chart
by TeXmeijinCreate, update, and refine interactive hierarchical flow diagrams as single-file HTML with drill-down navigation. Outputs a FigJam/Miro-like visual with stacking modal layers - clicking a node opens a deeper detail view. Use this skill when users ask to: - Visualize a processing flow, architecture, or pipeline as an interactive diagram - Create a layered/hierarchical flow chart with drill-down - Diagram a codebase flow with expandable detail levels - "Make a flow diagram of X" or "Visualize the X process" - Update an existing flow chart to reflect code changes - Improve or refine an existing flow chart (layout, detail, boundary connections) Triggers: "flow diagram", "flow chart", "process visualization", "layered chart", "interactive diagram", "drill-down diagram", "処理フロー図", "フローチャート", "フロー図解", "update flow", "refine flow", "フロー更新", "フロー改善"
layered-sequence-diagram
by TeXmeijinCreate, update, and refine interactive hierarchical sequence diagrams as single-file HTML with drill-down navigation. Outputs a UML-style sequence diagram with stacking modal layers - clicking an interaction block opens a deeper detail view. Use this skill when users ask to: - Visualize inter-component communication as a sequence / interaction diagram - Create a layered sequence diagram with drill-down - Diagram API call chains, request/response flows, or event sequences - "Make a sequence diagram of X" or "Show me how X communicates with Y" - Update an existing sequence diagram to reflect code changes - Improve or refine an existing sequence diagram Triggers: "sequence diagram", "interaction diagram", "message flow", "call sequence", "request flow", "communication diagram", "シーケンス図", "インタラクション図", "メッセージフロー", "呼び出しシーケンス", "update sequence", "refine sequence", "シーケンス更新", "シーケンス改善"
pj-flow
by TeXmeijinPJ管理フロー（長期記憶＋Threadの積み上げ）を任意リポジトリに展開するスキル。デフォルトでは `.claude/my-projects/<slug>/` 配下にProject長期記憶（CLAUDE.md）とThread（OBJECTIVE.md→OUTPUT.md）を積むが、runner / repo 方針に応じて `.agents/my-projects/` 等へカスタム可能。トリガー：「<slug>を再開」「続きやる」「PJ立ち上げ」「新スレッド作って」「OUTPUT書いて」「pbcopyして」「PJクローズ」「このやりとりをPJ管理下に置きたい」「○○PJに合流させたい」「PR/Issueから In Progress PJを作って」「pj-flow にマイグレ」「pj-flow の挙動を直したい」「pjflow」。Claude Code / Codex Agent Skill 両対応。
ghostty-applescript
by TeXmeijinWrite Ghostty terminal AppleScript layout scripts. Generates automation scripts for windows, tabs, pane splits, and command execution with correct syntax. Use for "Ghostty layout", "Ghostty AppleScript", "terminal pane layout script", or Zellij KDL to AppleScript conversion.
non-committed-analyzer
by TeXmeijin未コミットの変更ファイルを全て読み込み、施策の意図を分析し、コミット分割案・メッセージ候補・検証手順・テスト案を提示する。トリガー：「コミット分析」「変更まとめて」「何やってたっけ」「commit analyze」「未コミット確認」「変更の棚卸し」
prompt-refiner
by TeXmeijinRefines rough coding requests into execution-ready prompts. Use when the user gives a short, vague, frustrated, or under-specified implementation request and needs a better prompt for another coding agent.
yarn-classic-to-pnpm
by TeXmeijinUse when starting a migration of an existing Yarn Classic 1.x repository or subdirectory to pnpm, or auditing a Yarn-to-pnpm PR for exact transitive package version drift across yarn.lock, pnpm-lock.yaml, package-manager list output, and node_modules. Triggers include "yarn classic to pnpm", "pnpm migration", "Yarnからpnpm移行", "既存Yarn repoをpnpm化", "lockfile drift", "孫パッケージのバージョン一致", and "pnpm importで一致するか確認".
video-to-gif
by TeXmeijinConvert multiple video files (MOV/MP4) into a single merged GIF with customizable speed per segment. Use this skill when users want to: - Merge multiple videos into one GIF - Create demo GIFs from screen recordings - Combine video clips with different playback speeds - Convert videos to optimized GIFs with compression Triggers: "create GIF from videos", "merge videos to GIF", "convert MOV to GIF", "combine videos into animated GIF"
centering-judge
by TeXmeijin画像（PNG）からUI要素の整列（縦中央揃い / 左端揃い / 間隔均等 等）を画素単位で静的判定するスクリプトを、命題ごとに新規実装してから走らせる skill。LLM の主観で「揃ってる」と誤判定するのを防ぐためのメタ手法。固定スクリプトを呼ぶのではなく、検証したい命題ごとに ROI / 判定式 / debug overlay を設計し直す。scripts/ にケース別の参考実装（中央揃い / 左端揃い）を同梱。トリガー：「中央寄せ判定」「縦揃え確認」「左端揃え判定」「centering check」「alignment check」「画像で揃ってるか確認して」
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.