A robust quantitative data infrastructure providing real-time quotes, historical K-lines, and alternative sentiment data for the Chinese A-share market.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install quant-data-platform
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install quant-data-platform using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Quant Data Platform?
The Quant Data Platform is a specialized data infrastructure designed to empower quantitative traders and developers working within the Chinese A-share market. By leveraging Openclaw Skills, this tool provides a unified interface to access high-frequency real-time quotes, historical tick and bar data, and sophisticated alternative datasets including social sentiment and news analytics. It bridges the gap between raw financial feeds and actionable trading intelligence, making it an essential component for any algorithmic trading stack.
This skill focuses on data integrity and accessibility, offering built-in quality monitoring and automated consistency checks. Whether you are building a research environment or a live execution system, the platform ensures that your models are fed with clean, timely, and comprehensive market data.
Quant Data Platform Use Cases
- High-fidelity backtesting using historical daily and minute-level OHLCV data for strategy validation.
- Live trading execution and monitoring via real-time price feeds and order book depth.
- Alpha discovery through alternative data research, including sentiment analysis and insider trading reports.
- Systematic risk management using data quality checks to detect outliers or missing information.
How Quant Data Platform Works
- Initialize the platform using API tokens from major providers like Tushare or Akshare.
- Configure the local caching layer to optimize performance and manage API rate limits efficiently.
- Request specific market data subsets, such as real-time quotes or adjusted historical K-lines, using standardized Python methods.
- Apply technical or fundamental factors to the raw data using the built-in factor calculation engine.
- Run automated data quality validations to ensure the completeness and accuracy of the dataset before feeding it into trading algorithms.
Quant Data Platform Setup
To get started with this skill, install the required Python dependencies:
pip install tushare akshare pandas numpy
Next, configure your credentials by setting your environment variables:
export TUSHARE_TOKEN=your_token_here
You can then integrate the DataPlatform class into your Openclaw Skills scripts to begin fetching market data.
Quant Data Platform Data Schema & Taxonomy
The platform organizes market information into structured formats compatible with modern data science tools:
| Schema Type | Attributes | Description |
|---|---|---|
| Daily K-line | code, trade_date, open, high, low, close, volume, amount, turnover | Comprehensive price and volume history for stocks. |
| Factor Data | code, trade_date, factor_name, factor_value | Quantitative metrics including PE, PB, ROE, and momentum indicators. |
| Quality Metrics | completeness, accuracy, timeliness, overall | Statistical scores representing the reliability of fetched data. |
| Alternative | sentiment, news_limit, short_interest | Non-traditional datasets for advanced market sentiment analysis. |
Quant Data Platform Advanced Features
- Custom factor engine for defining and calculating user-specific trading indicators.
- Advanced caching strategy with granular expiration settings for real-time vs. historical data.
- Multi-source validation to cross-reference data points between Tushare and Akshare for maximum accuracy.
- Integrated sentiment analysis tools to quantify market mood from news and social feeds.
- Automated gap detection and missing data reporting to maintain high-quality datasets within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Twitter Browser Controller
A powerful browser-based automation tool for Twitter/X that operates like a human user via Chrome without requiring API keys.
Traffic Lights
A visualization skill for building multi-criteria assessment charts using traffic lights, Harvey balls, and weighted scoring models.
Weighted Column Chart Skill
A sophisticated data visualization skill that generates variable-width column and bubble charts to map profitability against market share.
OpenClaw WeChat Setup
This skill provides a streamlined process to install, authenticate, and manage the WeChat messaging channel for OpenClaw AI agents.
Video Script Generator
An automated AI agent skill that transforms product descriptions and target audience data into structured video scripts and shot-by-shot storyboards.
CSV Toolkit
A zero-dependency Python toolkit for manipulating, filtering, and converting CSV files directly from the command line.
Featured*
