investment-data

What This Skill Does

The investment-data skill is a powerful, enterprise-grade tool designed for quantitative traders, financial analysts, and developers who need high-quality, verified A-share market data. Built upon the robust investment_data project, this skill provides comprehensive historical and daily market snapshots. It excels at multi-source data validation, ensuring that information—from end-of-day pricing and limit-up/limit-down statuses to complex index weightings—is accurate and reliable. The skill supports multiple output formats including Qlib, CSV, and JSON, making it highly compatible with existing data science workflows and backtesting frameworks.

Installation

To integrate this skill into your OpenClaw ecosystem, execute the following command in your terminal: clawhub install openclaw/skills/skills/chayjan/investment-data-1-0-0

Ensure you have configured your environment variables, specifically INVESTMENT_DATA_DIR for storage and an optional TUSHARE_TOKEN if you require real-time data updates. You can further customize your experience by editing the config/config.yaml file to set your preferred data sources and update schedules.

Use Cases

• Quantitative Backtesting: Easily import historical pricing data into Qlib-compatible formats to validate trading strategies.
• Portfolio Monitoring: Generate reports on specific stock lists or track index weights to manage asset allocations.
• Automated Research: Schedule automated daily data updates at 9:00 AM to ensure your local databases are always ready for pre-market analysis.
• Historical Analysis: Study long-term trends including delisted companies to minimize survivor bias in financial models.

Example Prompts

1. "查询 000001.SZ 从 2024 年 1 月 1 日到 2024 年 12 月 31 日的每日行情数据，并将结果导出为 CSV。"
2. "获取沪深 300 指数最新的成分权重，并告诉我目前有哪些股票触及了涨跌停限制。"
3. "更新我的本地数据库，确保包含最新的 A 股历史交易数据，并检查是否有退市记录。"

Tips & Limitations

• Storage Requirements: The dataset is substantial; ensure you have at least 5GB of free disk space before running extensive downloads.
• Data Latency: While daily updates are automated, the data is typically T+1, meaning it is best suited for end-of-day analysis rather than high-frequency millisecond trading.
• Network Connectivity: The skill requires access to GitHub and DoltHub; verify your proxy settings if you are operating in a restricted network environment.
• Data Quality: Utilize the multi-source verification feature to cross-reference data from different providers, which significantly reduces the impact of single-source errors.