← 返回 Skills 市场
Quant Trading CN
作者
Guohongbin
· GitHub ↗
· v1.0.0
7260
总下载
1
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install quant-trading-cn
功能描述
量化交易专家 - 基于印度股市实战经验，支持策略生成、回测、实盘交易（Zerodha/A股适配）
安全使用建议
Review carefully before installing or using this with real broker credentials. Keep it to paper trading or read-only analysis unless you add explicit live-trading opt-in, per-order ownership checks, dry-run previews, confirmation gates, and strict limits on which files and broker resources the assistant may touch.
功能分析
Type: OpenClaw Skill
Name: quant-trading-cn
Version: 1.0.0
The skill bundle is designed to assist in building quantitative trading bots, involving interaction with live trading APIs and local file system operations. While the extensive documentation (KNOWLEDGE.md, NUANCES.md) focuses on secure and robust development practices, the skill explicitly instructs the AI agent to execute local shell scripts (`./scripts/wizard.sh`, `./scripts/universe-fetch.sh`, `./scripts/check-code.sh`) as described in `SKILL.md` and `README.md`. The content of these scripts is not provided, and their direct execution introduces a potential vulnerability surface (e.g., shell injection) if not properly secured. This inherent risk of executing unknown shell code, even if the stated purpose is legitimate, leads to a 'suspicious' classification.
能力评估
Credentials
Broker API credentials, market-data downloads, local trading-code analysis, logs, caches, and state files are broadly purpose-aligned, but account-wide liquidation and order cancellation are not proportionate without tighter scoping and user control.
Install Mechanism
The packaged artifact contains Markdown and JSON only, with no bundled executable scripts or install hooks inspected; however, referenced documentation recommends mutable external install paths such as unpinned npx and git clone commands.
Instruction Scope
The skill presents code-checking and auto-fix workflows plus live-trading examples, but the most risky shutdown pattern closes all positions and cancels all open or trigger-pending orders without showing ownership checks, dry-run behavior, or explicit confirmation.
Persistence & Privilege
No OS-level persistence, privilege escalation, scheduled tasks, or hidden background workers were found; the documented persistent files are trading bot configuration, .env credentials, logs, caches, state, and backups.
Purpose & Capability
The stated purpose is coherent for quantitative trading guidance, but the artifact goes into live Zerodha broker operations, credential setup, bot generation, and account-affecting order examples that can cause real financial loss.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install quant-trading-cn - 安装完成后，直接呼叫该 Skill 的名称或使用
/quant-trading-cn触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release - Quantitative trading expert based on Indian market experience
元数据
常见问题
Quant Trading CN 是什么？
量化交易专家 - 基于印度股市实战经验，支持策略生成、回测、实盘交易（Zerodha/A股适配）. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 7260 次。
如何安装 Quant Trading CN？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install quant-trading-cn」即可一键安装，无需额外配置。
Quant Trading CN 是免费的吗？
是的，Quant Trading CN 完全免费（开源免费），可自由下载、安装和使用。
Quant Trading CN 支持哪些平台？
Quant Trading CN 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Quant Trading CN？
由 Guohongbin（@guohongbin-git）开发并维护，当前版本 v1.0.0。
推荐 Skills