← Back to Skills Marketplace
daidaotian

joinquant聚宽平台的策略助手,DR成熟框架

by daidaotian · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
330
Downloads
1
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install joinquant-strategy
Description
提供聚宽量化策略开发模板、代码片段和API参考,助力策略快速编写与风险管理实践。
README (SKILL.md)

joinquant-strategy Skill\r

\r 帮助在Cursor中编写聚宽(JoinQuant)量化策略的工具集。\r \r

主要功能\r

  • 提供聚宽策略的标准模板\r
  • 包含常用代码片段\r
  • 提供API快速参考\r
  • 集成最佳实践示例\r \r

目录结构\r

\r

joinquant-strategy/\r
├── README.md            # Skill 说明文档\r
├── templates/           # 策略模板目录\r
│   ├── basic_template.py            # 基础策略模板\r
│   ├── dual_strategy_template.py    # 双策略模板\r
│   └── etf_rotation_template.py     # ETF轮动策略模板\r
├── snippets/            # 代码片段目录\r
│   ├── data_fetching.md       # 数据获取常用代码\r
│   ├── order_handling.md      # 下单处理代码\r
│   ├── risk_control.md        # 风险控制代码\r
│   └── technical_analysis.md  # 技术分析代码\r
├── api_reference/       # API参考文档\r
│   ├── core_functions.md      # 核心函数说明\r
│   ├── data_functions.md      # 数据获取函数说明\r
│   └── order_functions.md     # 下单函数说明\r
└── examples/            # 示例策略\r
    └── momentum_etf_strategy.py    # 动量ETF策略\r
```\r
\r
## 功能说明\r
\r
### 策略模板\r
- **basic_template.py**: 基础策略模板,包含完整的策略结构和基本逻辑\r
- **dual_strategy_template.py**: 双策略模板,基于示例实现的双策略框架\r
- **etf_rotation_template.py**: ETF轮动策略模板,用于实现ETF轮动交易策略\r
\r
### 代码片段\r
- **data_fetching.md**: 数据获取常用代码,包括历史数据、财务数据等获取方法\r
- **order_handling.md**: 下单处理代码,包括委托下单、撤单等操作\r
- **risk_control.md**: 风险控制代码,包括止损、止盈、仓位管理等\r
- **technical_analysis.md**: 技术分析代码,包括常用技术指标计算\r
\r
### API参考文档\r
- **core_functions.md**: 核心函数说明,包括策略初始化、运行等核心功能\r
- **data_functions.md**: 数据获取函数说明,详细介绍数据API的使用方法\r
- **order_functions.md**: 下单函数说明,详细介绍下单API的使用方法\r
\r
### 示例策略\r
- **momentum_etf_strategy.py**: 动量ETF策略,基于示例整理的完整策略实现\r
\r
## 使用方法\r
\r
在Cursor中使用此skill时,可以:\r
\r
1. **快速开始**:使用`/template`命令选择策略模板\r
2. **代码补全**:输入`/snippet`查看常用代码片段\r
3. **API查询**:输入`/api 函数名`快速查看API用法\r
4. **最佳实践**:参考`examples/`目录学习复杂策略的编写\r
\r
## 注意事项\r
\r
- 本工具包提供的代码和模板仅供参考,实际使用时需要根据具体情况进行调整\r
- 策略开发过程中,应注意风险管理和回测验证\r
- 请遵守 JoinQuant 平台的相关规定和限制\r
\r
## 版本信息\r
\r
- 版本: 1.0.0\r
- 最后更新: 2026-03-10\r
Usage Guidance
This package is internally consistent with its stated purpose, but before installing consider: 1) Verify the source/trustworthiness — the skill's source/homepage is unknown; review the included code yourself or with a developer. 2) Understand runtime context — these templates contain code that will place orders when run on JoinQuant; do not run against a live account until you have tested in a sandbox/backtest. 3) Credentials and execution are handled outside the skill — the skill doesn't request API keys, but executing strategies on JoinQuant normally requires linking your account/API credentials to the platform; keep those credentials secure. 4) Audit any changes before you let an autonomous agent execute code that can place trades. Overall the skill appears coherent and appropriate, but exercise normal caution when enabling trading-related code from an unverified source.
Capability Analysis
Type: OpenClaw Skill Name: joinquant-strategy Version: 1.0.0 The joinquant-strategy skill bundle is a legitimate collection of templates, code snippets, and API documentation designed to assist users in developing quantitative trading strategies for the JoinQuant platform. All analyzed Python files (e.g., momentum_etf_strategy.py, basic_template.py) and Markdown instructions (SKILL.md, README.md) contain standard financial logic and platform-specific API calls without any evidence of malicious intent, data exfiltration, or prompt injection attacks.
Capability Assessment
Purpose & Capability
Name/description (JoinQuant strategy helper) match the provided templates, examples, snippets and API reference. All required artifacts (strategy templates, example code, documentation) are appropriate for the stated purpose; no unrelated services, binaries, or credentials are requested.
Instruction Scope
SKILL.md simply describes how to use templates, snippets, and API docs inside Cursor. The runtime instructions do not direct the agent to read arbitrary system files, environment variables, or to transmit data to external endpoints. The included code uses JoinQuant APIs (jqdata) and platform-specific functions, which is expected for trading strategy templates.
Install Mechanism
No install spec is present (instruction-only with static code files). Nothing is downloaded or written by an installer; risk from install mechanism is minimal.
Credentials
The skill does not declare or require any environment variables, credentials, or config paths. The code assumes use of the JoinQuant runtime (jqdata) but does not request unrelated secrets or platform credentials in the skill bundle.
Persistence & Privilege
Skill flags show always:false and default invocation settings. It does not request permanent agent-wide presence or attempt to modify other skills or system settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install joinquant-strategy
  3. After installation, invoke the skill by name or use /joinquant-strategy
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
init v1.0.0
Metadata
Slug joinquant-strategy
Version 1.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is joinquant聚宽平台的策略助手,DR成熟框架?

提供聚宽量化策略开发模板、代码片段和API参考,助力策略快速编写与风险管理实践。 It is an AI Agent Skill for Claude Code / OpenClaw, with 330 downloads so far.

How do I install joinquant聚宽平台的策略助手,DR成熟框架?

Run "/install joinquant-strategy" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is joinquant聚宽平台的策略助手,DR成熟框架 free?

Yes, joinquant聚宽平台的策略助手,DR成熟框架 is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does joinquant聚宽平台的策略助手,DR成熟框架 support?

joinquant聚宽平台的策略助手,DR成熟框架 is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created joinquant聚宽平台的策略助手,DR成熟框架?

It is built and maintained by daidaotian (@daidaotian); the current version is v1.0.0.

💬 Comments