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...
cld-overlay
by koukoOutward between-group conflict resolution: draw one Mermaid CLD per stakeholder perspective (2-4 distinct groups), overlay them on a shared canvas, find the policy that improves all CLDs (straddle finding). Stop forcing, start listening. Each side's mental model is internally consistent within its own frame; the surface dispute is rarely the actual disagreement. The wise policy is usually a third option neither side proposed because their original CLD did not contain it. For single-team inward harmony (not between-group conflict), use team-mental-model instead. NOT for zero-sum disputes on fixed resources, single decision-maker problems, power-asymmetric situations where one party can simply impose, or workshops where key stakeholders (customers, regulators, unions, downstream users) are absent from the room. Triggers: "they keep arguing about X", "same fight every quarter", "same fight every retro", "we've tried compromise and nobody is happy", "stop forcing start listening", "each side accuses the other of
hansei
by kouko反省 — 責めではなく学びのための内省的振り返り。失敗や期待外れの後に 「なぜ気づけなかったか」を掘り下げたいときに使う。実装や情報提供には 使わない。retrospective, reflection, postmortem.
aristotle-first-principles
by koukoFirst Principles Thinking — decompose problems to fundamental truths and rebuild from scratch, rejecting analogy and convention. Use when user wants to rethink a problem from zero, not when they want to analyze what exists or compare options. 第一原理思考。第一原理・根本から考え直す。
aristotle-four-causes
by koukoAristotle's Four Causes — analyze any subject through material, formal, efficient, and final causes. Use when user wants to deeply understand what something is and why it exists, not when they want implementation. 四因説・本質分析。四原因説・本質の分析。
4dx-d2-lead-measures
by koukoCoaches the user to identify weekly-actionable lead measures (predictive AND influenceable) for a WIG across solo / team-leader / team-member scopes, plus audit-mode diagnosis of an existing lead list or KPI dashboard. Use when the user has a WIG but is about to track lag metrics or adopt a generic KPI dashboard, BEFORE picking the behaviors that actually move the WIG. EN: "Help me find lead measures", "Audit our lead measures", "Are our 12 KPIs real leads?" JP: 「lead measure を決めたい」「うちの lead measure を診断して」「これ本当に lead？」 zh-TW: 「幫我找 lead measure」「主管覺得我們的 lead 要調整」「12 個指標哪些是真 lead？」 Do NOT use for stale-lead momentum rescue (→ 4dx-sustain-momentum-rescue) or cross-discipline 4DX audit (→ 4dx-audit).
deep-read
by koukoDeeply understand ONE large document or book — build a structured understanding (sections, claims, methodology, caveats, argument-structure) of a single source, depth-on-one-source vs deep-research's breadth-across-many. Use when the user wants to thoroughly comprehend one long document, paper, or book, run inside any coding agent host using the host's own tools (zero API-key setup).
argument-deconstruct
by koukoReverse-engineer the structure of any long-form argument — op-ed, proposal, manifesto, political text, paper introduction. Surfaces the claim-grounds-warrant chain, makes hidden warrants explicit, detects missing rebuttals, identifies Burke pentad ratios, and produces an argument map with ethical position. Use when user asks "拆解這個論證 / 反駁這份提案 / find the warrant / where does this argument fail". Do NOT use for non-argumentative texts (use artifact-deconstruct), for hidden-assumption hunts (use assumption-surface), or for codebase reasoning (use sourceatlas). 論証の脱構築。論證逆向解構。
using-git-worktrees
by koukoUse when working on parallel branches simultaneously (multiple feature branches in flight; long-running experiments alongside production work; design-then-build cycles where the design branch outlives a single session). Examples: "I want to work on feature X while keeping main checked out for the bug fix", "set up a worktree for the v2 redesign", "experimental refactor I don't want polluting my main checkout", "this branch will run for weeks, give it its own dir". Native git worktree workflow per P3-C — no wrapper tool, just `git worktree add` with a documented `.worktrees/` subdirectory convention + `.gitignore` discipline. Refuses the "just stash and switch" rationalization when work-in-progress on the current branch makes branch-switching painful. Git worktree・並行ブランチ・experimental branch。Git worktree・平行 branch・實驗 branch。
ikigai
by kouko生き甲斐 — 4軸分析でプロジェクト・キャリア・製品の存在意義を診断する。 目的の欠如、方向性の迷い、PMF未達を感じるときに使う。 単なるSWOT分析や市場調査には使わない。 生きがい・目的・存在意義・PMF。Ikigai, purpose, raison d'etre, life purpose.
data-tw
by koukoLayer 1 (Data) skill for Taiwan equities + macro. Bundles 8 clients (yfinance, MOPS, TWSE/TPEx OpenAPI, FinMind, CBC, DGBAS, NDC, stat.gov.tw) behind a `pack.py` facade with 5 pack types — snapshot, memo-fetch, comps-multiples, screener-batch, regime-pack. MOPS + TWSE OpenAPI are Tier A primary; FinMind is Tier 2 fallback / by-design gap supplier (per-stock T86 三大法人 daily flow, .TWO price history). Pure I/O — no analysis. Single-ticker (`--ticker`) and batch (`--tickers`) modes. 台股資料層（公開觀測站＋證交所 OpenAPI＋總經，Tier A 為主，FinMind 補位）。 台湾データ層（MOPS／TWSE／マクロ統合、Tier A 中心）。
translation-creative
by koukoTranslate ad copy / marketing brief / headline / catchphrase via faithful or transcreation mode. 5D reflection in transcreation. S1 back-translation = MUST in transcreation, SHOULD in faithful. Variants opt-in via --variants=N.
translation-doc
by koukoTranslate markdown / technical documentation preserving code blocks, URLs, HTML, math blocks, frontmatter, mermaid + ASCII diagrams. Web search ON, S1+S2 SHOULD, M1+M2+M3 strict.
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.