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...
vw-docling
by vesperworksConvert PDF/DOCX/PPTX/HTML/images/URLs to Markdown (or JSON/HTML/Text) using the docling CLI. Use when the user asks to "convert to MD", "Markdown化", "PDFをMDに", "テキスト化", "doclingで変換", "ファイルをMarkdownに", or similar. Automatically selects options based on input characteristics (Japanese OCR, scanned PDFs, tables, formulas, images). When invoked standalone without input arguments (e.g. `/vw-docling` alone), MUST use the AskUserQuestion tool to collect input path, characteristics, and output directory before executing. After docling finishes, MUST perform a quality check (base64-stripped head/tail sample) and, if the output is empty or filled with garbled OCR artefacts (Cyrillic/Greek junk, meaningless symbol-only lines), MUST offer AIOCR fallback ("LLMでAIOCRしますか？") via AskUserQuestion — on accept, re-process with Claude Vision (Read tool on the PDF/image) and write `-rebuild.md` then cp over. NOT for audio/ASR transcription (whisper等) — do not invoke for audio input.
vw-qmd-classifier
by vesperworksディレクトリ内のファイルパスとファイル名のみから qmd collection 設計を推論し、 既存 `~/.config/qmd/index.yml` を破壊しない `qmd collection add` / `qmd context add` の 適用コマンド列を生成するスキル。本文は一切読まないためトークン消費が小さい。 ファイル数に応じて階層サンプリングを自動適用するため大規模ディレクトリ（500+/5000+）でも 精度を保つ。Use when the user says 「qmd 分類して」「qmd で検索可能にして」「qmd collection 作って」 「/vw-qmd-classifier」等。NOT for ファイル本文の意味解析（読まない設計）and NOT for qmd CLI を自動実行すること（CLI コマンド列の出力までで止める）。
vw-research
by vesperworks対話型リサーチアシスタント。壁打ち・インタビュー・包括的調査を組み合わせ、コードベース・ドキュメント・Webを横断調査。
vw-tokscale-audit
by vesperworkstokscale の集計 JSON を統計的・構造的に解析し、トークンスパイク／モデルミスマッチ／セッション肥大／履歴リプレイ疑惑／オーバーヘッド過多の 5 カテゴリで異常を検出。アクティブな全クライアント（claude/codex/gemini/opencode 等）を横断集計し、怪しい TOP 5 と抑制案を推奨確率付きで提示。詳細レポートを `.brain/thoughts/shared/research/{date}-tokscale-audit.md` に保存する。Use when the user says 「トークン監査して」「tokscale 解析」「異常検出」「ヘビーユーザー特定」「セッションリーク調査」「課金スパイク調査」「/vw-tokscale-audit」等。NOT for 単純な消費量確認（`tokscale monthly --month` を直接実行すれば足りる）and NOT for リアルタイムモニタリング（バッチ集計の事後解析用途）。
vwnote
by vesperworksAtomic Notes 形式で技術用語や概念を短く整理して出力する skill。ユーザーが「ノートにして」「atomicnote にして」と言ったときの自然文トリガーとして使う。Claude の /vw:note 風のフォーマットを Codex で再利用したいときに使い、調査結果や会話内容を 3 行要約 + 詳細 + 背景 + 使い道 + 英語タグの形に整える用途に限定する。
vw-flow-viz
by vesperworksスキル/エージェントのフロー可視化。SKILL.mdやエージェント定義を解析し、プロンプト→エージェント→ツール呼び出しの流れとトークン消費をD3.js Sankeyで可視化するHTMLレポートを生成。
vw-clean
by vesperworksClaude のサンドボックスで rm / mv が拒否されたファイル、セッションで作った一時ファイル、同一内容の重複 MD、$TMPDIR/claude 配下の作業残骸などを特定し、ユーザーに「何を消すか」を一覧で説明・確認した上で、macOS の `trash` コマンド（ゴミ箱に送る＝復元可能）を生成して `pbcopy` でクリップボードに送る。ユーザーはターミナルに貼って実行するだけで片付く。Use when the user says 「掃除して」「不要ファイル消して」「rm できなかったやつ片付けて」「trash してまとめて」「/vw-clean」等。NOT for 重要ファイル／作業成果物の削除（必ず確認プロンプトを挟む）and NOT for `rm -rf` 系の破壊的一括削除（trash 経由で復元可能な範囲に限定）。
vw-index
by vesperworksGenerate a directory-level index.md summarizing a collection of Markdown files. Three-phase pipeline: (1) per-file summary caching with mtime-based invalidation, (2) context aggregation, (3) index generation. Domain-neutral; works in any project. Use when the user asks to "index a directory", "まとめを作って", "generate an overview of <dir>", or runs /vw:index explicitly.
vw-issue
by vesperworks壁打ち結果やリサーチレポートをGitHub Issueに変換。リサーチファイルや新アイデアからIssueを生成し、壁打ちで内容を磨く。
vw-note
by vesperworks技術用語の解説・記録（Atomic Notes形式）。用語を入力すると3行解説を生成し、.brain/thoughts/atomic/に保存。連続入力・MOC自動提案対応。
vw-pm
by vesperworksGitHub Projects PM Agent。議事録からタスク抽出・Issue化、Projects初期セットアップを行う。キラーUX:「雑に議事録を投げるとタスク化してくれる」
vw-wiki
by vesperworkskarpathy llm-wiki + gBrain パターンの LLM 育成型ナレッジベース（オントロジー層）を任意のディレクトリに構築・運用するスキル。操作は init（wiki/ ブートストラップ）/ ingest（ソース取り込み）/ query（wiki で回答 + file-back）/ lint（健全性検査）/ sync（git 監視パスの更新を一括取り込み）の 5 つ。ソースは git 参照（コミット SHA + ログ 1 行で出所記録）と raw/（git 外ソース）の 2 種。ルールの正規ソースは生成される wiki/SCHEMA.md に自包され、Cursor (Sonnet) など他エージェントでも同一ワークフローが動く。Use when the user says 「wiki を作って/育てて」「ingest して」「wiki に取り込んで」「ナレッジベース化して」「オントロジー作って」「wiki で答えて」「wiki を lint して」「sync して」「/vw-wiki」等。NOT for Claude Code の auto-memory（MEMORY.md）の管理、NOT for .brain/thoughts/ の Atomic Notes（vw-notetaker 参照）、NOT for 単発の Web リサーチ（deep-research / vw:websearch 参照）。
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.