← Back to Skills Marketplace
Quant Data Platform
by
jason-aka-chen
· GitHub ↗
· v1.0.0
· MIT-0
140
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install quant-data-platform
Description
Comprehensive quantitative data platform for A-share market. Real-time quotes, historical data, alternative data (sentiment, news, fundamentals), factor data...
Usage Guidance
This skill appears to do what it claims: provide A‑share real‑time and historical data using tushare/akshare. Before installing, consider: 1) Provide a TUSHARE_TOKEN if you want real data — the SKILL.md shows this but the registry metadata does not list it; verify you have a valid token and store it securely (not committed to code). 2) The skill will create and write cache files under ~/.quant_data/cache — if you prefer isolation, run it in a virtualenv or container and/or change cache_dir. 3) The pip packages recommended are common, but review and pin versions before installing into production. 4) The skill source and homepage are unknown; if you need higher assurance, review the full quant_data.py file yourself or request the maintainer/source provenance. If you accept those caveats, the skill is internally consistent with its stated purpose.
Capability Analysis
Type: OpenClaw Skill
Name: quant-data-platform
Version: 1.0.0
The skill bundle provides a legitimate framework for a quantitative data platform targeting the Chinese A-share market. The implementation in `quant_data.py` uses standard libraries (Tushare, Akshare) and includes typical features like in-memory caching and mock data generation for testing, with no evidence of malicious intent, data exfiltration, or prompt injection.
Capability Assessment
Purpose & Capability
The name/description (quant data for A‑share) aligns with the included code and the recommended dependencies (tushare, akshare, pandas, numpy). However, SKILL.md demonstrates use of a TUSHARE_TOKEN while the registry metadata lists no required environment variables — this is an inconsistency that should be clarified (the platform does legitimately use a Tushare token).
Instruction Scope
The SKILL.md instructions stick to data acquisition, caching, and usage examples. They instruct installing tushare/akshare and optionally exporting TUSHARE_TOKEN. The instructions do not ask the agent to read unrelated system files or send data to unknown external endpoints. They do recommend creating/using a cache directory in the user's home (~/.quant_data/cache), which means data and cached files will be written to disk.
Install Mechanism
There is no automated install spec in the registry (instruction-only), and SKILL.md simply recommends pip installing well-known Python packages (tushare, akshare, pandas, numpy). This is a low-risk, common install pattern. No downloads from untrusted URLs or obscure installers are present.
Credentials
The code and documentation expect an optional/required TUSHARE_TOKEN (and use os.getenv to read it). The registry metadata did not declare required env vars or a primary credential — this mismatch should be corrected. The skill creates a cache directory in the user's home (~/.quant_data/cache), so it will write files to disk. No other secret or unrelated credential access is requested.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or system-wide settings. It runs with normal agent invocation privileges. Creating its own cache directory is standard for this type of tool and not elevated privilege.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install quant-data-platform - After installation, invoke the skill by name or use
/quant-data-platform - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of quant-data-platform.
- Provides comprehensive quantitative data platform for the Chinese A-share market.
- Supports real-time quotes, historical K-line and minute data, tick data, and order book.
- Delivers alternative data including sentiment analysis, news, fundamentals, insider trading, and short interest.
- Offers a wide range of technical, fundamental, alternative, and custom factor data.
- Implements robust data quality monitoring for completeness, accuracy, timeliness, and consistency.
- Includes sample usage, API reference, data sources, caching strategy, and rate limiting details.
Metadata
Frequently Asked Questions
What is Quant Data Platform?
Comprehensive quantitative data platform for A-share market. Real-time quotes, historical data, alternative data (sentiment, news, fundamentals), factor data... It is an AI Agent Skill for Claude Code / OpenClaw, with 140 downloads so far.
How do I install Quant Data Platform?
Run "/install quant-data-platform" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Quant Data Platform free?
Yes, Quant Data Platform is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Quant Data Platform support?
Quant Data Platform is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Quant Data Platform?
It is built and maintained by jason-aka-chen (@jason-aka-chen); the current version is v1.0.0.
More Skills