A-Stock Data is one very large SKILL.md that embeds working Python code for pulling real market data on Chinese stocks and related markets. It is organized in fifteen layers with 87 endpoints from 34 sources, with the code written out in the file itself.
The skill applies only when a task needs code that fetches data. Questions about concepts, opinions or strategy do not load it. It prefers sources that do not block IPs, rate-limits the Eastmoney calls it uses, and lists backup sources to switch to when a main one fails. The text is in Chinese.
What You Get
- Ready-to-run Python functions for fifteen layers of A-share data
- A routing table that maps each need to a section, function and source
- A backup-source guide and fallback functions for dragon-tiger lists, fund flows and announcements
- Rate-limited access helpers that protect against being blocked
- Ticker normalization that stops a code from silently returning another stock’s data
Common Use Cases
- Fetch daily K-lines with adjusted prices for a stock or ETF
- Download broker research reports and ratings for a company
- Pull the day’s limit-up pool, dragon-tiger list and northbound flows
- Check financial statements, valuation history and announcements for one name
- Collect futures, option and convertible bond data from exchange sources
What Makes It Unique
The code lives inside the skill file, so no extra files are needed, and the changelog documents silent failures found in real use, such as stale codes that return empty data with a normal HTTP status. It separates ‘no data exists’ from ‘the source is broken’ by raising errors, and it ranks sources by how likely they are to block you.
Under The Hood
The agent reads SKILL.md, picks the section for the data it needs and runs the Python code in it. That code makes HTTP requests to many public finance sites and exchange pages, such as Tencent, Eastmoney, Sina, Tonghuashun, Cninfo and the stock exchanges, and opens TCP connections to Tongdaxin servers and to the Baostock service. It needs several Python packages installed with pip. Some helpers keep a local cache and write downloaded files such as report PDFs. No account keys are required for the main endpoints. The agent runs shell commands and writes files on your machine, and it calls many third-party services that can change or block requests.