BitSoulStockSkill is an all-in-one A-share stock analysis skill for OpenClaw, targeting retail investors and quant beginners. It provides AI-driven insights, comprehensive data, and analytical tools to serve as a personalized wealth assistant.

How It Works

This skill employs a Mixture-of-Experts (MoE) architecture for stock selection and trading decisions, integrating AI Agents and LLMs for reasoning and user-friendly advice. It offers personalized weight updates based on user interaction and shares official strategy weight schemes. A robust backtesting framework and aggregation of A-share market news/opinions are also included.

Quick Start & Requirements

Installation options include OpenClaw's one-click install (http://installskill.aicodingyard.com/stockskill_install.txt), GitHub cloning (git clone https://github.com/BitSoulTech/BitSoulStockSkill.git then pip install -r requirements.txt), or ClawHub. Requires Python 3.7+ and OpenClaw compatibility (qClaw, AutoClaw, EasyClaw, Feishu Miaoda). Dependencies: requests, pandas, sqlalchemy, numpy. Free data (6 months) requires registration/token from https://www.aicodingyard.com.

Highlighted Details

• Free historical data service (weekly updates) covering market data, fundamentals, financials, sector data, dragon-tiger lists, and index data.
• Over 100 built-in quantitative indicators (technical, fundamental, trading) with custom factor support.
• AI-powered MoE system for stock analysis, trading signals, and personalized recommendations.
• Configurable backtesting framework and aggregation of A-share market news/community viewpoints.

Maintenance & Community

The project welcomes contributions via Pull Requests to enhance its capabilities. Specific community channels or maintainer details are not provided in the README.

Licensing & Compatibility

Licensed under the Apache-2.0 License, which is generally permissive for commercial use and integration into closed-source projects.

Limitations & Caveats

Full 10-year historical data requires a paid VIP service; free tier is limited to six months. Strategy review functionality is planned but not yet implemented.