a-stock-data is a self-contained SKILL.md that integrates A-share and related market data from 34 sources into 87 zero-auth endpoints that AI coding assistants can use directly. It targets the problem that A-share raw data is scattered across sources with hard-to-use formats, headers, and auth quirks.
Project overview
It consolidates 34 scattered A-share data sources into 87 endpoints that work without registration or API keys (except iwencai), so AI coding assistants can retrieve market data directly instead of grappling with each source's formats and auth quirks.
Project type
Data Processing
Use cases
Data Analysis
Deployment
Refer to project documentation
License
Apache-2.0
Best for
Developers and researchers who use AI coding assistants and need A-share and related market data consolidated from many sources without per-source registration or API keys.
Key capabilities
All 34 sources work without registration or API keys except iwencai, with a backup-source quick reference for degradation when primary sources are blocked.
Four ready-made investigation flows: single-stock valuation, batch comparison, thematic report search, and new-target due diligence.
Limitations and risks
Only data retrieval is provided; no backtesting engine is included.
Eastmoney interfaces have rate-limit risk control and can block IPs; mootdx K-line commands stopped returning data in 2026-09. Use the documented backup-source quick reference when a primary source is blocked.
Getting started
mkdir -p ~/.claude/skills/a-stock-data; curl -o ~/.claude/skills/a-stock-data/SKILL.md https://raw.githubusercontent.com/simonlin1212/a-stock-data/main/SKILL.md; pip install mootdx requests pandas stockstats numpy baostock xlrd openpyx; then start Claude Code and make a natural-language request in Chinese such as asking it to check the valuation of stock 688017.