A comprehensive Python SDK for accessing JoinQuant (聚宽) quant trading data, including market prices, financial statements, and alpha factors.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install jqdatasdk-skill
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 jqdatasdk-skill 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 jqdatasdk: JoinQuant Quant Trading Data SDK?
jqdatasdk is a specialized Openclaw Skills integration designed for quantitative traders and financial analysts. It provides a robust Python interface to the JoinQuant (聚宽) data cloud, allowing users to programmatically retrieve a wide array of financial data points. This skill simplifies the process of gathering the raw data necessary for strategy development, backtesting, and deep market research.
By leveraging this skill, developers can access high-quality market data for the Chinese A-share market, including stocks, indices, and futures. The integration is built to work seamlessly with popular data science tools like Pandas and SQLAlchemy, making it an essential part of any quant developer's toolkit within the Openclaw Skills ecosystem. Whether you are performing technical analysis or building complex factor models, this skill provides the reliable data foundation required for professional-grade quantitative finance.
jqdatasdk: JoinQuant Quant Trading Data SDK Use Cases
- Automating the retrieval of daily or minute-level market price data for backtesting strategies.
- Querying complex financial fundamentals across thousands of stocks using structured SQLAlchemy queries.
- Monitoring market sentiment through money flow, margin trading, and short selling data.
- Generating alpha signals using pre-built Alpha101 and Alpha191 factor models.
- Filtering investment universes based on index membership, industry sectors, or custom financial health metrics.
How jqdatasdk: JoinQuant Quant Trading Data SDK Works
- Install the jqdatasdk library along with its dependencies like pandas and sqlalchemy.
- Authenticate your session using your JoinQuant credentials or an API token to establish a secure connection.
- Construct data requests using the specialized API functions for market, financial, or factor data.
- Utilize the SQLAlchemy-based query engine for advanced filtering and sorting of fundamental financial indicators.
- Receive data in structured formats, primarily Pandas DataFrames, ready for immediate analysis or storage.
jqdatasdk: JoinQuant Quant Trading Data SDK Setup
To get started with this skill, install the necessary package via pip:
pip install jqdatasdk
After installation, you must authenticate your account in your Python environment:
import jqdatasdk as jq
jq.auth('your_username', 'your_password')
# Verify authentication
print(jq.is_auth())
jqdatasdk: JoinQuant Quant Trading Data SDK Data Schema & Taxonomy
The skill organizes data into several core categories, typically returned as Pandas DataFrames. Below is the metadata taxonomy used within Openclaw Skills:
| Data Category | Description | Primary Fields |
|---|---|---|
| Market Prices | Time-series price data | code, date, open, close, high, low, volume |
| Fundamentals | Financial statement data | eps, roe, net_profits, total_assets, revenue |
| Security Info | Metadata for assets | code, display_name, start_date, end_date, type |
| Money Flow | Capital movement data | date, sec_code, net_amount_main, net_pct_main |
| Factors | Quantitative signals | pe_ratio, pb_ratio, alpha_101, factor_values |
jqdatasdk: JoinQuant Quant Trading Data SDK Advanced Features
- Custom API extension support by wrapping the JQDataClient instance for specialized data needs.
- Integration with SQLAlchemy for building complex, multi-table financial queries.
- Performance optimization using the @hashable_lru decorator for caching frequent data requests.
- Direct access to professional-grade factor libraries including Alpha 101 and Alpha 191.
- Batch processing capabilities for retrieving data for multiple securities in a single network request to maximize efficiency within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Wayfront MCP Skill
A comprehensive MCP integration for Wayfront workspaces to manage agency data including clients, orders, billing, and support tickets.
weknow (Universe Chord) Agent Skill
A specialized academic discussion platform enabling AI agents to engage in peer-reviewed research, knowledge construction, and interdisciplinary collaboration.
VLM Image Helper
A specialized visual aid designed to preprocess and enhance images to ensure maximum accuracy for Vision Language Models and OCR workflows.
News Search
An automated news aggregation skill that queries multiple search engines to provide deduplicated, real-time news results in Markdown or JSON.
AI Intelligent Customer Segmentation
An advanced AI-driven system for automated customer layering, RFM analysis, and precision marketing automation.
Progressive Validator
A multi-stage backtest validation framework designed to save hours of compute time by failing poor strategies early through progressive testing windows.
Featured*
