Global Stock Data — Full-Stack US/HK Market Data Skill
Packs quotes, options Greeks, 0DTE flow, SEC filings, short volume and a free market screener from 11 zero-auth sources into one self-contained SKILL.md your AI assistant can call directly.
Strong safety practices: mandatory SEC UA declaration with fail-fast, thread-safe rate limiting (8 req/s vs SEC's 10), per-source compliance tiers with verbatim terms, proactively excluded the HKEX scraper layer, explicit 'code not data' distribution. Deductions: still automates access to C-tier sources (Sina/Tencent/Eastmoney/Yahoo front-end endpoints), a compliance gray zone; data flow depends on multiple unsigned third-party endpoints with no isolation from external behavior changes.
Self-contained code, clean exception semantics (DataNotAvailable/RuntimeError/ValueError), content-driven 403 disambiguation of S3 AccessDenied, locked rate limiter. But no committed test suite or CI covering key paths is visible in the sources; several layer implementations (CBOE, Layers 9–12) are truncated in the provided SKILL.md, so completeness of all claimed endpoints cannot be confirmed; many 'tested' claims are not independently reproducible in a static read.
Clear trigger conditions (activation list + keyword table), explicit non-fit boundaries (US-only layers guard against HK tickers via assert_us_ticker, HK options declared unsupported), good Chinese support. Deduction: core new layers depend on overseas services (SEC/FINRA/CBOE/Yahoo); the README itself acknowledges mainland-China direct connections may be unstable and recommends proxies.
Well-layered docs, routing quick-reference table, semantic versioning v2.0.3, detailed CHANGELOG, Apache-2.0 license, community contribution credits. Deductions: no CI/test directory evidence, individual maintainer, tier conclusions are time-sensitive with no stated re-verification cadence, and the Nasdaq earnings calendar is offered despite unverified terms.
Claims 30+ endpoints across 11 sources, zero-auth, minimal dependency (requests only), with differentiated value (CBOE Greeks, FINRA short volume, EDGAR screener) over yfinance-style alternatives. However, static review cannot confirm outputs are directly usable; v2.0.2 records that two quote functions previously crashed 100% of the time, showing real endpoint fragility — external API changes can silently break features.
CHANGELOG includes before/after fix tables, internal consistency checks (PE = price/EPS, market cap cross-checked against share count), self-reproduction curl commands, and third-party corroboration via community issues. But all 'verified' claims are author self-reported; no independent test suite or CI workflow in the repo to cross-check, so reproducibility cannot be confirmed statically.
- You must replace SEC_CONTACT with your real name and email before using SEC layers, or SEC will reject requests.
- C-tier sources (CBOE/Yahoo/Eastmoney/Sina/Tencent) are for personal research only; for commercial use rely solely on S-tier sources and verify FINRA (B-tier) terms yourself.
- SEC/FINRA/CBOE/Yahoo may be unreachable or unstable from mainland-China networks; use a proxy or prefer Eastmoney/Sina/Tencent sources.
- This static review did not execute any endpoint; upstream API changes can silently break functions — smoke-test before relying on them.
- Compliance tier conclusions date from a 2027-07-24 terms reading; re-verify source terms before commercial use.
What does this skill do, and when should you use it?
A single-file Agent Skill (SKILL.md with embedded Python) that gives AI coding assistants full-stack access to US and Hong Kong market data: quotes, K-lines, technical indicators, fundamentals, fund flow, options and SEC filings. V2.0 uses a 13-layer architecture with 30+ endpoints across 11 data sources, all zero-auth, requiring only `requests`. Its standout feature is a compliance tier (S/B/C) for every source, with terms of service quoted verbatim, plus a strict code-not-data distribution policy. The author reports a full regression pass on 2026-07-24, but the repo ships no automated test suite.
Ships ready-to-call Python functions: real-time/delayed quotes (Sina 36 fields, Tencent 71 US / 78 HK fields, Eastmoney push2); daily/weekly/monthly/minute K-lines (US back to 1984); locally computed MA/EMA/MACD/RSI/KDJ/Bollinger; three financial statements, bilingual key metrics, analyst estimates, institutional holdings; CBOE official options chain with full Greeks, IV, 0DTE filtering and unusual-flow detection; FINRA Reg SHO market-wide daily short volume (12,112 symbols); SEC EDGAR same-day filing stream (Form 4/8-K/13F), full-text search since 2001, and XBRL frames cross-market screening (single tag covers 1,842–5,309 companies); Treasury yield curve, CFTC COT, earnings calendar. Includes a thread-safe rate limiter and a unified official-source gateway (SEC capped at 8 req/s with declared User-Agent).
- A retail investor asks Claude Code for quotes, financials and valuation directly: "AAPL's price and PE" or "Apple's latest income statement".
- An options trader monitors 0DTE and unusual flow: "Show NVDA's 0DTE options flow — unusual activity".
- A short-interest researcher tracks FINRA market-wide short volume: "TSLA's short volume ratio trend this week".
- A quant uses EDGAR frames as a free screener: "Rank all filers by R&D expense for CY2025Q1".
- A compliance-sensitive team that will only rely on tier-S sources (SEC EDGAR/Treasury/CFTC) and needs each source's terms spelled out.
- Tracking insider and institutional activity: same-day Form 4/13F filings, or full-text search for which 8-K first mentioned 'HBM4'.
What are this skill's strengths and limitations?
- Broad 13-layer, 30+ endpoint coverage from quotes to options Greeks to SEC filings, all zero-auth with only `requests` as a dependency
- Compliance tiering is a genuine differentiator: each source's terms quoted verbatim, and an HKEX CCASS layer was deliberately removed for violating those terms
- Solid engineering: thread-safe per-source rate limiting, SEC User-Agent enforcement, positive detection of S3-style 403 AccessDenied via a DataNotAvailable exception
- The Tencent US/HK field-offset table was calibrated field-by-field against live responses, with reproduction commands included
- Compliance conclusions rest on the author's single read of each source's terms on 2026-07-24; Treasury/CFTC and Nasdaq terms are self-admittedly unverified, and the CBOE layer still needs Cboe approval for commercial use
- No automated test suite — validation is the author's manual regression run
- Relies on third-party frontend endpoints (Sina/Tencent/Eastmoney) whose breakage risk falls on the user
- HK options and CCASS holdings are explicitly unsupported; direct connections to Yahoo/SEC can be flaky from mainland-China servers
- All V2.0 official-source layers (CBOE/FINRA/EDGAR/Treasury) are US-only; HK coverage is limited to quotes and fundamentals
How do you install this skill?
mkdir -p ~/.claude/skills/global-stock-data && curl -o ~/.claude/skills/global-stock-data/SKILL.md https://raw.githubusercontent.com/simonlin1212/global-stock-data/main/SKILL.md && pip install requests. Before using any SEC layer, you must change SEC_CONTACT in the file to your real name and email, or SEC rejects requests as an Undeclared Automated Tool (the code raises a clear error if you forget).
How do you use this skill?
In Claude Code, just prompt naturally — "check AAPL's financials", "NVDA's 0DTE options flow", "what's the 10Y-2Y Treasury spread right now" — and the skill activates on its own. Codex/OpenClaw users can paste SKILL.md into their system prompt or project context; the embedded Python runs as-is. Layers 6.1/9/10/11 are US-only and will reject HK tickers with a clear error.
How does this skill compare with similar options?
The author describes this as a sister project of a-stock-data, which covers China A-shares while this one covers US and HK; both can be installed together without conflict. The README also notes that yfinance and most open-source alternatives lack the V2.0 additions: CBOE Greeks + 0DTE flow, FINRA short volume, and the EDGAR filing stream / market-wide screener.