GitHub radar
A-Stock Data: a Chinese market skill for AI agents
A standalone Skill file for Claude Code and Codex that provides AI agents with 54 endpoints of 19 Chinese A-share data sources (including stock quotes, research reports, fund flows, options, etc.) without authentication.
A-Stock Data is a standalone Skill file(structured Markdown + Python code) for Claude Code and Codex, which integrates Chinese A-share market information from 19 data sources into 54 callable endpoints without authentication. It includes 11 layers, including real-time stock quotes and order list information provided by mootdx and Tencent, research report information and PDF download provided by Eastmoney, smart money flow and industry hotspots provided by Tonghuashun, limit up pool, board of directors, ETF option Greek number and implied volatility information, interactive questions and answers between investors provided by cninfo, and macro economic index data such as PMI provided by the People’s Bank of China and the National Bureau of Statistics. There are also corresponding backup mechanisms for primary APIs that are subject to request quotas. This project was started for three and a half months and got more than 9 000 stars. The main readme is written in Chinese. You can also view the English version (README_en.md).
Why a vibe-coder should care
When developing AI agents to analyze China A-share stocks, it often involves connecting various APIs from multiple data sources, which may have different request quotas, authentication mechanisms, and data structures. With this skill, you don’t need to worry about these issues. Your agent only needs to connect to one context file for data access, and there are also backup mechanisms for primary APIs that are subject to request quotas. If you want to develop financial AI applications based on China A-share stocks, you don’t need to care about API integration.
How to install
Copy this and send it to your agent — Claude Code, Codex, any of them:
Install the a-stock-data skill from https://github.com/simonlin1212/a-stock-data — read README_en.md, create the directory ~/.claude/skills/a-stock-data, download SKILL.md, and run the pip install from the Quick Start section. Ask if you need any permissions.
Runs on a regular laptop — Python 3.9+ with a few packages required (mootdx, requests, pandas, stockstats).
Open on GitHub▌ More finds