← Back to Skills Marketplace
608
Downloads
5
Stars
0
Active Installs
4
Versions
Install in OpenClaw
/install qmt
Description
QMT迅投量化交易终端 - 内置Python策略开发、回测引擎和实盘交易，支持中国证券市场全品种。
Usage Guidance
This bundle is documentation and examples for the QMT / xtquant trading client and appears coherent. Before using: (1) do not run example code against a real brokerage account — test with a sandbox or paper/trading-enabled test account; (2) review the xtquant package source and only install it from a trusted source (pip package provenance); (3) be aware the demos assume a local QMT/miniQMT client (Windows) and local data paths; (4) never paste real account credentials into code you did not audit, and confirm broker permissions before enabling automated orders.
Capability Analysis
Type: OpenClaw Skill
Name: qmt
Version: 1.0.3
The skill bundle provides a comprehensive integration for the QMT (Quant Market Trading) platform, a legitimate quantitative trading terminal. The content consists of extensive documentation (SKILL.md, xtdata.md, xttrader.md), API references, and a connectivity demo (demo.py) for the official xtquant SDK. The instructions for the AI agent focus on best practices for financial data handling, such as data validation and multi-step analysis, and do not contain any evidence of malicious intent, data exfiltration, or harmful prompt injections.
Capability Assessment
Purpose & Capability
Name/description claim a QMT trading terminal and the package files, requirements (python3, xtquant) and examples all match that purpose. Required binaries/env/configs are proportional to a Python trading SDK that connects to a local QMT/miniQMT client.
Instruction Scope
SKILL.md and included demos contain direct examples of trading calls (order_shares, cancel, connect/subscribe) and reference local QMT paths and account IDs. This is expected for a trading integration, but those instructions, if executed, will interact with brokerage APIs and can place real trades — the agent/docs do not themselves request secrets but they do assume access to a running QMT/miniQMT client and broker-enabled accounts.
Install Mechanism
No install spec is provided (instruction-only plus docs). requirements.txt lists xtquant and numpy which is appropriate for the described SDK; nothing is downloaded from arbitrary URLs and no archive extraction is present.
Credentials
The skill does not request environment variables, secrets, or unusual config paths. It does expect local QMT/miniQMT installation directories and account identifiers to be used by the examples — those are reasonable for a trading SDK but are sensitive (account IDs, broker access) and should be handled carefully by the user.
Persistence & Privilege
Skill is not always-enabled and does not request persistent system privileges or attempt to modify other skills. It is user-invocable and may be invoked autonomously by the agent (platform default), which is normal for skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install qmt - After installation, invoke the skill by name or use
/qmt - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.3
- 新增 demo_project 示例目录，包含 demo.py 示例脚本和 README.md 说明文件。
- 便于用户快速参考和上手 QMT 策略开发。
v1.0.2
**Summary:**
This version updates the documentation to Simplified Chinese and enriches advanced strategy examples.
- Documentation (SKILL.md) fully translated from English to Simplified Chinese.
- Expanded advanced strategy examples, adding a complete RSI strategy and a full multi-stock rotation strategy.
- No code or functional changes to the skill itself.
v1.0.1
**Version 1.1.0 update summary: Refined documentation and expanded user guidance.**
- Added detailed documentation files: README.md, QUICK_REFERENCE.md, xtdata.md, xttrader.md, and requirements.txt.
- Expanded and clarified strategy examples, operation modes, and API usage in core docs.
- Enhanced comparisons among QMT, miniQMT, and Ptrade platforms.
- Improved data coverage and feature explanation for Chinese securities instruments.
- Added notes on advanced usage, multi-stock strategy examples, and practical tips.
- No changes to the codebase; content/documentation update only.
v1.0.0
QMT skill initial release:
- Professional quantitative trading platform for Chinese securities with built-in Python strategy development, backtesting, and live trading.
- Supports full desktop client (QMT) and lightweight mode (miniQMT).
- Provides event-driven Python strategy framework, historical and real-time data access, and built-in order functions.
- Includes backtesting engine with customizable parameters and metrics.
- Covers stocks, indices, futures, options, ETFs, bonds, and financial data.
- Documentation and example strategies included.
Metadata
Frequently Asked Questions
What is QMT?
QMT迅投量化交易终端 - 内置Python策略开发、回测引擎和实盘交易，支持中国证券市场全品种。 It is an AI Agent Skill for Claude Code / OpenClaw, with 608 downloads so far.
How do I install QMT?
Run "/install qmt" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is QMT free?
Yes, QMT is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does QMT support?
QMT is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created QMT?
It is built and maintained by coderwpf (@coderwpf); the current version is v1.0.3.
More Skills