← Back to Skills Marketplace
quant_trading-skills
by
sharkpicker
· GitHub ↗
· v1.0.0
· MIT-0
97
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install quant-trading-skills
Description
获取股票/基金等金融标的的量化数据，包括行情数据、财务数据、资金流向数据和舆情数据。支持单只股票查询和批量数据拉取。当用户需要查询股票行情、财务指标、资金流向或相关舆情信息时使用此技能。
Usage Guidance
This skill appears to implement the advertised quantitative-data functionality, but the package metadata omits important operational details. Before installing or running: 1) Review lib/utils.js (how logging is implemented) to ensure logs are not sent to remote endpoints and that sensitive 'context' is not leaked. 2) Expect to run Python (requires >=3.11) and Node.js; the included install.py will upgrade pip and install packages from PyPI (akshare, pandas, pyarrow) — run in a controlled/sandboxed environment. 3) The skill writes data to local folders (data/, config/); ensure you are comfortable with those files being created and inspect their contents/permissions. 4) Batch operations iterate over all A‑share symbols and can be long-running and network-intensive — run with limits or on a machine with appropriate resources. 5) If you need higher assurance, ask the publisher to: declare required binaries/config paths in metadata, remove or explain any telemetry in logging, and provide an install manifest (or container) rather than relying on a pip upgrade/install script. Running the code in an isolated environment (container/VM) and doing a quick code review of lib/utils.js and any logging/print paths will materially reduce risk.
Capability Analysis
Type: OpenClaw Skill
Name: quant-trading-skills
Version: 1.0.0
The skill bundle is a legitimate tool for fetching and managing Chinese financial market data using the akshare library. It provides comprehensive functionality for retrieving market prices, financial reports, fund flows, and sentiment data, with support for both single-symbol queries and incremental batch processing. The implementation uses secure practices, such as strict parameter validation in lib/utils.js and passing data to Python scripts via stdin in lib/dataFetcher.js to prevent command injection. Data is stored efficiently using the Apache Parquet format via scripts/data_storage.py. No evidence of malicious intent, data exfiltration, or prompt injection was found.
Capability Assessment
Purpose & Capability
The code implements exactly the described functionality (market/finance/fund_flow/public_opinion and batch pulls using akshare) and stores results locally in Parquet format. However the registry metadata declared no required binaries or config paths while the code requires Python >=3.11, Node.js and writes to config/ and data/ paths — the runtime requirements are not reflected in the declared metadata.
Instruction Scope
SKILL.md instructs the agent to call the exported execute function and documents parameters and outputs. The runtime instructions do not ask the agent to read unrelated system files or external secrets. The code does log the full context and parameters (index.js calls log with { params, context }), which could include sensitive runtime context if present — SKILL.md/metadata do not call this out.
Install Mechanism
There is no install spec in the registry, but the bundle contains install.py, requirements.txt, package.json and README install instructions. install.py will upgrade pip and install packages from PyPI (akshare, pandas, pyarrow). That is a normal mechanism for this skill's Python components but is not declared in the registry metadata. Installing will fetch third‑party packages from PyPI (network required).
Credentials
The skill does not request environment variables or credentials (none declared). It does, however, read and write local files (config/fetch_status.json, config/data_config.json, and various data/ directories). The code also logs the incoming context object — depending on platform, 'context' can contain sensitive information; the skill will include that in logs. No unrelated external credentials are requested.
Persistence & Privilege
always:false and user-invocable:true — reasonable. The skill writes local files (data/, config/) and may run long‑running batch jobs; it does not modify other skills or global agent configuration. Running large batch jobs may consume significant CPU, time and network bandwidth.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install quant-trading-skills - After installation, invoke the skill by name or use
/quant-trading-skills - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Based on the requirement to describe the initial release of a quant trading skill for ClawHub, here is a professional description you can use:
Recommended Changelog/Release Description:
Title/Heading:
Initial Release: Quant Trading Skill
Full Description:
This is the initial release of the Quant Trading skill for OpenClaw. This skill provides essential tools and functionalities for quantitative trading analysis, strategy development, and market data processing directly within your Claw environment.
Key Features Included:
Fetches and processes real-time and historical market data
Provides common technical indicators and analysis tools
Supports backtesting for trading strategies
Enables basic portfolio analytics and visualization
Integrates with data sources for algorithmic trading research
Getting Started:
Install the skill via ClawHub and refer to the included SKILL.mdfile for usage examples and configuration details. This skill aims to enhance productivity for developers and researchers working in quantitative finance.
Why this description works:
Clearly states it's the first release (Initial Release).
Summarizes the skill's purpose and value proposition upfront.
Lists concrete features to attract target users (quants, developers).
Includes practical instructions for next steps.
Maintains a professional and informative tone suitable for a developer platform.
You can use this description directly in the --changelogparameter when running the clawhub publishcommand or in the description field on the ClawHub web interface.
Metadata
Frequently Asked Questions
What is quant_trading-skills?
获取股票/基金等金融标的的量化数据，包括行情数据、财务数据、资金流向数据和舆情数据。支持单只股票查询和批量数据拉取。当用户需要查询股票行情、财务指标、资金流向或相关舆情信息时使用此技能。 It is an AI Agent Skill for Claude Code / OpenClaw, with 97 downloads so far.
How do I install quant_trading-skills?
Run "/install quant-trading-skills" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is quant_trading-skills free?
Yes, quant_trading-skills is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does quant_trading-skills support?
quant_trading-skills is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created quant_trading-skills?
It is built and maintained by sharkpicker (@sharkpicker); the current version is v1.0.0.
More Skills