global-stock-data skill
A skill with US and global market data: options, VIX, short selling, insider trades, rates and FX, with no API keys
- 1,840 ★ on the repository
- Last commit
- Apache-2.0
Extended access
Why this level
- The code calls about a dozen external sources, some of whose terms prohibit automated access, and complying with those terms is on you
- The name and email from `SEC_CONTACT` go into the User-Agent header of requests to the SEC
- The skill runs embedded Python that you should review before the first run
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/global-stock-dataDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The code calls about a dozen external sources, some of whose terms prohibit automated access, and complying with those terms is on you
- The name and email from `SEC_CONTACT` go into the User-Agent header of requests to the SEC
- The skill runs embedded Python that you should review before the first run
This is third-party code. Review the repository files before installing.
What it does
global-stock-data is a single `SKILL.md` file with embedded Python. It gathers data scattered across about a dozen sources into calls an agent can make, so you stop dealing with Eastmoney prefixes, Yahoo auth and SEC EDGAR CIK mapping. The author counts 16 layers, over 50 endpoints and 17 sources, and none needs a key. It covers quotes and candles (US back to 1984, and Japan, Taiwan, Korea, India and Europe through a ticker suffix), MA, MACD, RSI and Bollinger indicators computed locally, statements and XBRL metrics. Separate layers cover CBOE options with Greeks and 0DTE flow, the VIX since 1990 and its term structure, daily short volume and FINRA short interest, the SEC filing stream (Form 4 insider trades, 8-K, 13F), an EDGAR-based screener, the Treasury yield curve, CFTC reports and policy rates for 38 central banks. Every source is labelled with a license tier and its terms are quoted verbatim. The project distributes only code, and you fetch the data yourself under each source's own terms.
Who it is for. For private investors and analysts who ask Claude Code or Codex to pull US and global market data and want to see the terms behind each source.
Good fit when
- You need a CBOE options chain with Greeks and a 0DTE flow estimate for a ticker
- You want VIX history since 1990 and its term structure to tell contango from backwardation
- You want Form 4 insider trades and quarterly 13F fund holdings with weights
- You need central bank rates, SOFR, ECB FX and Treasury auction results in one request
- You need a market-wide screener on EDGAR data for any XBRL tag
Not a fit when
- You are building a commercial product: the author advises using tier S sources only, and the rest are for personal research
- You need streaming real-time quotes for trading: the skill makes on-demand requests
- You need Hong Kong exchange CCASS data: the author removed that layer because of the source's terms
Example request
Show me today's VIX and its term structure, and insider trades at Apple over the last 30 daysLimitations
- Before using the SEC layers, set your real name and email in `SEC_CONTACT` inside `SKILL.md`: the SEC rejects requests without a declared User-Agent, and the code raises an error if the field is empty.
- License tiers differ. Tier S allows commercial use (EDGAR, Treasury, Federal Reserve, ECB, BIS, TWSE and others). FINRA and EIA spot prices are tier B, CBOE, Eastmoney, Sina and Tencent are tier C, and Yahoo and Nasdaq are tier D, meaning personal study at your own risk.
- For commercial work rely on tier S only. The Taiwan layer returns the latest trading day only; history comes from Yahoo.
- You need Python 3.9 or newer and the `requests` package, plus `tzdata` on Windows. The author tested with Claude Code; for Codex and OpenClaw you paste `SKILL.md` into the context.
How to disable. Delete the `~/.claude/skills/global-stock-data` folder. For Codex and OpenClaw remove the pasted `SKILL.md` text from the system prompt or the project context file.
FAQ
How do I install global-stock-data in Claude Code?
Create the `~/.claude/skills/global-stock-data` folder, download `SKILL.md` into it from the README address and run `pip install requests`. Then put your name and email in `SEC_CONTACT`. After starting Claude Code, say something like "check AAPL's financials" and the skill activates.
Do I need API keys?
No, all 17 sources work without authentication. The SEC layers only need a declared contact in the User-Agent.
Can I use the data in a commercial product?
Only data from tier S sources: EDGAR, Treasury, the Federal Reserve, ECB, BIS, TWSE and others. The author warns that official does not mean free to use for any purpose. The other tiers are for personal research.
What about Codex or OpenClaw?
Paste `SKILL.md` into the system prompt or the project context file. The embedded Python runs as is, because the file is structured Markdown with code inside.
Which markets beyond the US are covered?
Yahoo candles through a ticker suffix cover Japan, Taiwan, Korea, India, Europe and Hong Kong. Taiwan has the official TWSE and TPEx APIs, and global rates and FX come from the BIS, ECB, Federal Reserve and New York Fed layers.
Discussion
No questions or reviews yet.
Related
SkillsA skill with Chinese A-share market data: quotes, research reports, financials, news and 11 more categories from 34 sources, no keys
A skill that queries Arkvol for China, Hong Kong and US market data and retells it with the date, indicators and limits of use
A skill that answers probability questions from market data: prediction markets, rates, yields and derivatives
A skill helps an agent retrieve Chinese-equity data and preserve source responses with timestamps and explicit gaps
Five skills for investment research: tech company earnings, value investing, market sentiment, US liquidity and the Bitcoin cycle
A skill and MCP server that give an agent quotes, candles and ticker search for the China, Hong Kong and US markets
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| global-stock-data (this card) | no | 1,840 | ||
| a-stock-data | no | 11,529 | data for the Chinese stock market, while global-stock-data focuses on the US and global rates | |
| FinanceMCP | no | key is optional | 869 | a financial data MCP server, while this is a single skill file with no separate process |
README in short
The README describes the 16-layer architecture, the license tier scale with quotes from source terms, a three-step quick start, endpoints by group (price, value, flows, filings, macro, rates, Taiwan, energy) and an FAQ. It explains why the Hong Kong exchange layer was removed while Yahoo and Nasdaq stayed.
README badge
Original SKILL.md
--- name: global-stock-data description: 美股港股全栈数据工具包（官方源优先）— 十六层架构·50+端点·17数据源·全部零鉴权。在原有行情/K线/技术指标(MA/MACD/RSI/KDJ/布林带)/基本面/资金面/期权/SEC Filing/工具八层之上，新增：CBOE官方期权链(完整希腊字母+IV+0DTE流+异动识别)、FINRA全市场每日空头成交量、SEC EDGAR申报事件流(Form4内部人/8-K/13F机构持仓)、EDGAR全市场横截面筛选、美债收益率曲线/CFTC COT/财报日历；V2.1 新增全球利率汇率层(BIS 38家央行政策利率、欧洲央行汇率/利率/欧元区收益率曲线、纽约联储SOFR/EFFR、美联储H.10汇率/H.6货币存量、美国财政部国债拍卖/联邦债务)，Yahoo K线修复全历史日线与时区并支持日本/台湾/韩国/印度/欧洲等市场代码；V2.2 新增CBOE波动率指数历史与VIX期限结构、FINRA做空余额(每月两期)、SEC Form 4内部人逐笔交易与13F机构持仓解析、台股官方OpenAPI(证交所+柜买中心,可商用)、美国能源信息署EIA原油/天然气价格与库存。每个数据源标注合规级别与条款原文。内嵌全部调用代码，自包含零依赖外部文件。适用于美股港股个股分析、全市场筛选、财报解读、期权与0DTE策略、做空数据追踪、内部人交易与13F持仓、SEC文件检索、资金流与机构持仓分析、全球利率汇率与央行政策跟踪、VIX波动率、台股、原油天然气等场景。 origin: custom version: 2.2.0 --- > 📦 项目主页：https://github.com/simonlin1212/global-stock-data — 更新、反馈、支持作者 > > 作者：Simon 林 · X [@linsizhen](https://x.com/linsizhen) · 邮箱：simonlin0423@gmail.com # 美股港股全栈数据工具包 V2.2 — 官方源优先 十六层数据架构，50+ 个端点，17 个数据源，全部零鉴权，实测可用（2026-07-24 全量回归验证；V2.1 新增与修复部分 2026-10-11 实测；V2.2 新增部分 2026-10-12 实测）。层数按「原有八层 + V2.0 五层（CBOE 期权链单算一层）+ V2.1 一层 + V2.2 两层（台股、能源）」计；V2.2 的波动率指数、做空余额、Form 4 / 13F 解析是原有层里的新小节，不另计层。 **V2.0 设计原则：官方源优先。** 新增层的主力数据取自美国政府（SEC EDGAR / Treasury / CFTC）、 自律组织（FINRA）与交易所（CBOE / Nasdaq）的公开端点；V2.1 再加国际清算银行、欧洲央行、 美联储、纽约联储四家官方机构；V2.2 再加台湾证交所、柜买中心与美国能源信息署 EIA。**每个数据源都标注了合规级别与条款原文** （见下方「数据源合规分级」）——"官方"不等于"可自由使用"，各源差异极大。 **本工具只分发代码，不分发、不转售任何市场数据**；数据由使用者自行按各源条款获取。 **使用方式：** 将本文件放入 `~/.claude/skills/global-stock-data/SKILL.md`，Claude Code 会自动识别并在美股/港股相关对话中激活。 ``` 行情层（实时/延时） ├── 新浪财经 → 美股 gb_XXXX 36字段 / 港股 rt_hkXXXXX 25字段 ├── 腾讯财经 → 美股 usXXXX 71字段 / 港股 r_hkXXXXX 78字段 └── 东财 push2 → 美股/港股 secid 实时行情，含中文名/涨跌幅/换手率 K线层（日/周/月/分钟） ├── 新浪 → 美股日K (回溯至1984年) └── Yahoo chart → 美股+港股+日本/台湾/韩国/印度/欧洲等 (v8 API, 零crumb, 全历史日线) [D级] 技术指标层（纯计算，零额外依赖） └── MA/EMA + MACD + RSI + KDJ + 布林带 基于K线OHLCV，纯Python计算 基本面层 ├── 东财 datacenter → 美股/港股三表(资产负债+利润+现金流) + GMAININDICATOR(关键指标) ├── Yahoo crumb → 23个模块(财务数据+关键指标+分析师+机构持仓) └── SEC EDGAR XBRL → 美股503个GAAP指标 (仅美股) 资金面层 └── 东财 push2his → 日级资金流(主力/大单/中单/小单) 美股+港股