REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
This repo is a collection of 27 skills
Bring realtime market data and research workflows into Claude Code, Cursor & beyond — 29 open-source Skills for stocks, options and commodities.如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/alphagbm-skills)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 skills | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | AlphaGBM | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 27 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 3,082 | 465,460 | 233,910 | 149,364 | 144,149 |
| 最近代码更新 | 2026年10月6日 | 2026年11月17日 | 2026年4月20日 | 2026年11月17日 | 2026年11月17日 |
| 许可证 | MIT | MIT | – | Apache-2.0 | MIT |
AlphaGBM 提供的 27 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
Install only the ones you use. Open a skill to see how to install it
If you want every one, let the AI install them in one go. Know 2 things first
Uploading to Claude on the web and apps: you need 27 uploads, one ZIP per skill. Open each skill in the list below to download it
Checked against official docs 2026年11月12日 · Source: support.claude.com, code.claude.com, learn.chatgpt.com, cursor.com
Put-spread Backtest reference method. Use when studying this focused method, not to run an API request. External API-key access for its legacy endpoints is not published in this release.
Supply-chain Bottlenecks reference method. Use when studying this focused method, not to run an API request. External API-key access for its legacy endpoints is not published in this release.
Build a contribution schedule and calculate a supplied price-path cost basis without predicting returns. Use when the user asks to dollar-cost averaging with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
Score Hong Kong and China A-share dividend candidates across yield quality, durability, cash flow, valuation and momentum. Use when the user asks to dividend strategy with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
Earnings IV Crush reference method. Use when studying this focused method, not to run an API request. External API-key access for its legacy endpoints is not published in this release.
Score ETF trend, risk, liquidity, cost and available tracking and theme signals while preserving data gaps. Use when the user asks to etf strategy with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
Greeks reference method. Use when studying this focused method, not to run an API request. External API-key access for its legacy endpoints is not published in this release.
Build an auditable grid from a price range, current price and capital. Use when the user asks to grid plan with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
Hedging Scenarios reference method. Use when studying this focused method, not to run an API request. External API-key access for its legacy endpoints is not published in this release.
Compare research records you provide to see changes in facts, scores and judgments. Use when the user asks to investment review with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
Volatility Snapshot via the published AlphaGBM interface. Use for this focused function, not as a promise that every website API accepts API keys.
Market Sentiment reference method. Use when studying this focused method, not to run an API request. External API-key access for its legacy endpoints is not published in this release.
Score observed price trend, confirmation, risk and participation without forecasting a price. Use when the user asks to momentum following with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
Separate reported claims from impact inferences, with related assets and next checkpoints. Use when the user asks to news impact with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
Compare option candidates and score components, with funding, expiry and assignment risks. Use when the user asks to options strategies with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
Options Score via the published AlphaGBM interface. Use for this focused function, not as a promise that every website API accepts API keys.
Strategy Builder reference method. Use when studying this focused method, not to run an API request. External API-key access for its legacy endpoints is not published in this release.
Payoff Simulation reference method. Use when studying this focused method, not to run an API request. External API-key access for its legacy endpoints is not published in this release.
Prediction Markets reference method. Use when studying this focused method, not to run an API request. External API-key access for its legacy endpoints is not published in this release.
Extract report views, ratings, key assumptions and risks with sources and dates. Use when the user asks to research report breakdown with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
Find published research and institutional views with sources, dates and related assets. Use when the user asks to research reports with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
Aggregate user-supplied disclosed buys and sells by source without automatically copying trades. Use when the user asks to smart money tracking with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
Stock Analysis via the published AlphaGBM interface. Use for this focused function, not as a promise that every website API accepts API keys.
Connect fundamentals, sentiment and risk to supporting and opposing evidence. Use when the user asks to stock opportunities with AlphaGBM. Use the bundled Python runner; never silently replace real results with demos.
Unusual Options Activity reference method. Use when studying this focused method, not to run an API request. External API-key access for its legacy endpoints is not published in this release.
Volatility Smile reference method. Use when studying this focused method, not to run an API request. External API-key access for its legacy endpoints is not published in this release.
Volatility Surface reference method. Use when studying this focused method, not to run an API request. External API-key access for its legacy endpoints is not published in this release.
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
开发者未说明 · SKILL.md 形式的 Skill 可用于支持 Agent Skills 的应用,如 Claude Code、Codex 和 Cursor
This repo has 27 skills. Pick one from the list above; its page shows every way to install it, including letting the AI install it and a ZIP
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
node -vMac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: 打开官方下载页,选择 LTS 版本和点选式安装程序:Mac 用 .pkg · Windows 用 .msi。双击后一路下一步即可,不需要 curl 命令
装好后关掉终端再打开,重新运行同一条命令,应显示版本号: node -v
安装一次,所有需要 Node.js 的工具都能用
npx skills add AlphaGBM/skills --skill alphagbm-stock-research摘自开发者 README,会下载并运行开发者的代码
提问、分享技巧或报告无法使用。按“有帮助”数量排序。