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...
multi-stock-comparator-v1
by keigoks-ivan收到 2-5 檔個股 ticker(可選 DCA / DD)後,從本地 dca/ 或 dd/ 目錄讀取最新報告,執行短中長期(<12M / 2-3Y / 3-5Y / 5-10Y)四層時間框架對比分析 + 基本面財務體質四表對比(§A.2)+ 競爭態勢對比(§A.3 份額消長/二維護城河/head-to-head/圈外威脅/互斥假設裁決),輸出 HTML 比較報告至 docs/comparisons/。v1.7 準確性協議:財報 staleness gate(報告日後有財報必查漂移)、估值同源(dd-screener latest.json)、價格重抓連 IRR re-rate 重算、寫稿後 self-review gate 過了才上 index。當用戶提及『這兩三檔哪個好』、『多檔比較』、『同類對比』、『該選哪一家』、『DCA / DD 對比分析』時,必須觸發此技能。
stock-analyst
by keigoks-ivan收到股票 ticker 後，執行完整買側深度研究（DD）。v12.4 變更：EPS estimates source 接 Koyfin/Excel buy-side consensus（步驟零' 最高優先），DD universe 涵蓋 141/146 ticker（含 ADR / TW listings 自動換 USD）；ticker 不在 Excel 自動 fallback yfinance（步驟零）→ web_search（步驟一）；§13 估值需在註腳明標「EPS 來源：Excel snapshot YYYY-MM-DD」供 audit；FY+3 可直接用 Excel consensus 不再需要機械外推，但 §8 邏輯 sanity check 仍必做（若 Excel 與業務邏輯明顯矛盾須在 §13 標明分歧）。v12.3 變更（保留）：核心 reshape — 估值章節（§2+§13）從 ~40% 砍至 ~18%，基本面章節（§5+§8+§9+§11+§12）從 ~35% 擴至 ~55%。① §2 瘦身（9 子節→7 子節：A 體質檢核併入 B、E R:R+Bear Case 大幅瘦身砍 QC-29 壓力測試 4 情境表，只留 3 R:R 數字+1 line Bear anchor）；② §13 大幅瘦身（砍 13.0 估值體系診斷/13.3 Reverse DCF/13.5 五角驗證表+8 因素定錨+便宜理由五問，只留 13.1/13.2/13.4+1 段結論）；③ §7 砍低估值四問+便宜理由四問；④ §5 擴充（5.F single thing 新增—binary discrete event、5.B 假設加 sourced floor+漂移觸發條件、5.C 風險加時間尺度分層 ⚡🔥🐢）；⑤ §8 擴充（8.B 成長品質強化—定價 vs 量具體%+3Y 趨勢，8.H 客戶結構深度新增—top1/5/10+dual-track risk+in-house risk）；⑥ §9 大改（強制 execution moat+pricing power moat 二維拆解+SaaS/銀行/保險 single-axis escape rule+護城河趨勢雙線標+QC-23 威脅三級分類強制使用）；⑦ §11 擴（議價權三段獨立—對上游/對下游/地緣+營收三維+單位經濟逐業務段）；⑧ §13.4 強制對的 p
stock-analyst
by keigoks-ivan收到股票 ticker 後，執行完整買側深度研究（DD）。v12.3 變更（直接從 v12.0/v12.2 跳號，同步解決 v12.1/v12.2 metadata 滯後）：核心 reshape — 估值章節（§2+§13）從 ~40% 砍至 ~18%，基本面章節（§5+§8+§9+§11+§12）從 ~35% 擴至 ~55%。① §2 瘦身（9 子節→7 子節：A 體質檢核併入 B、E R:R+Bear Case 大幅瘦身砍 QC-29 壓力測試 4 情境表，只留 3 R:R 數字+1 line Bear anchor）；② §13 大幅瘦身（砍 13.0 估值體系診斷/13.3 Reverse DCF/13.5 五角驗證表+8 因素定錨+便宜理由五問，只留 13.1/13.2/13.4+1 段結論）；③ §7 砍低估值四問+便宜理由四問；④ §5 擴充（5.F single thing 新增—binary discrete event、5.B 假設加 sourced floor+漂移觸發條件、5.C 風險加時間尺度分層 ⚡🔥🐢）；⑤ §8 擴充（8.B 成長品質強化—定價 vs 量具體%+3Y 趨勢，8.H 客戶結構深度新增—top1/5/10+dual-track risk+in-house risk）；⑥ §9 大改（強制 execution moat+pricing power moat 二維拆解+SaaS/銀行/保險 single-axis escape rule+護城河趨勢雙線標+QC-23 威脅三級分類強制使用）；⑦ §11 擴（議價權三段獨立—對上游/對下游/地緣+營收三維+單位經濟逐業務段）；⑧ §13.4 強制對的 peer group tier（禁止跨業務模式 tier 錯誤 anchor）；⑨ dd-meta 新增 optional moat_execution+moat_pricing_power sub-scores。v12.0/v12.2 核心保留：訊號燈 A+/A/B/C/X、護城河 5 級品質+體質 veto、估值燈、Pure MA 六狀態機、大盤豁免、QC-22~36 規則、dd-meta JSON validator。當用戶提及 ticker、個股分析、DD 報告、股票研究、估值分析時，必須觸發此技能。
stock-analyst
by keigoks-ivan收到股票 ticker 後，執行完整買側深度研究（DD）。v12.3 變更（直接從 v12.0/v12.2 跳號，同步解決 v12.1/v12.2 metadata 滯後）：核心 reshape — 估值章節（§2+§13）從 ~40% 砍至 ~18%，基本面章節（§5+§8+§9+§11+§12）從 ~35% 擴至 ~55%。① §2 瘦身（9 子節→7 子節：A 體質檢核併入 B、E R:R+Bear Case 大幅瘦身砍 QC-29 壓力測試 4 情境表，只留 3 R:R 數字+1 line Bear anchor）；② §13 大幅瘦身（砍 13.0 估值體系診斷/13.3 Reverse DCF/13.5 五角驗證表+8 因素定錨+便宜理由五問，只留 13.1/13.2/13.4+1 段結論）；③ §7 砍低估值四問+便宜理由四問；④ §5 擴充（5.F single thing 新增—binary discrete event、5.B 假設加 sourced floor+漂移觸發條件、5.C 風險加時間尺度分層 ⚡🔥🐢）；⑤ §8 擴充（8.B 成長品質強化—定價 vs 量具體%+3Y 趨勢，8.H 客戶結構深度新增—top1/5/10+dual-track risk+in-house risk）；⑥ §9 大改（強制 execution moat+pricing power moat 二維拆解+SaaS/銀行/保險 single-axis escape rule+護城河趨勢雙線標+QC-23 威脅三級分類強制使用）；⑦ §11 擴（議價權三段獨立—對上游/對下游/地緣+營收三維+單位經濟逐業務段）；⑧ §13.4 強制對的 peer group tier（禁止跨業務模式 tier 錯誤 anchor）；⑨ dd-meta 新增 optional moat_execution+moat_pricing_power sub-scores。v12.0/v12.2 核心保留：訊號燈 A+/A/B/C/X、護城河 5 級品質+體質 veto、估值燈、Pure MA 六狀態機、大盤豁免、QC-22~36 規則、dd-meta JSON validator。當用戶提及 ticker、個股分析、DD 報告、股票研究、估值分析時，必須觸發此技能。
deep-conviction-analyst
by keigoks-ivan對單一個股執行深度定見分析（Deep Conviction Analysis / DCA），位於 DD 之上的『投資決策層』 — 假設 stock-analyst 的個股 DD 與 industry-analyst 的產業 ID 已存在，本 skill 透過 Phase A 三軸獨立搜尋（護城河 / 產業趨勢 / 業務財務）+ Phase B 矛盾辨識 + Phase C 基金經理決策框架，產出可執行的單檔 HTML 投資決策報告。v1.3 變更：Phase A4 DD 擷取改 dd-meta JSON 為 primary source（structured；HTML fallback）+ 章節 references modernize（§5.B 假設、§1 結論 — 對齊 DD v9.2+ 編號）+ 砍 obsolete「MA60/MA200/MA104w R:R」+「三引擎目標價」(v10.0 已廢除)；§5 Single Thing 加 DCA vs DD §5.F cross-check rule（v12.3 新增）；Phase A1 護城河可選 adopt execution + pricing power 二維拆解（v12.3 DD 強制框架，DCA 推薦對齊但保留獨立性）。觸發：用戶說『幫我跑 {ticker} dca』、『{ticker} dca』、『{ticker} 定見』、『deep conviction {ticker}』、『conviction analysis {ticker}』、『最終判斷 {ticker}』、『該不該進場 {ticker}』、『買不買 {ticker}』。輸出 docs/dca/DCA_{TICKER}_{YYYYMMDD}.html。
kl-property-scorecard-v1
by keigoks-ivan收到 KL（吉隆坡）具體建案名稱後，產出精煉的公開版評分卡 HTML 頁面，供部署至 myproperty.investmquest.com。評分人視角為以 10 年持有為基準的專業房地產投資人，產出標準化評分摘要而非完整 DD 報告。當用戶提及「公開版」、「scorecard」、「評分卡」、「網站版報告」、「給別人看的版本」、或指定要產出部署到 myproperty 的 HTML 時，必須觸發此技能。
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.