← 返回 Skills 市场
benzema216

Trading Coach

作者 BENZEMA · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
10555
总下载
15
收藏
74
当前安装
1
版本数
在 OpenClaw 中安装
/install trading-coach
功能描述
🏆 AI交易复盘教练 — 把你的券商CSV变成可执行的改进洞察! 自动FIFO配对持仓,8维度质量评分(入场/出场/趋势/风险...),10维度AI洞察。 支持富途(中/英)、老虎、中信、华泰等主流券商。 触发条件: 用户提供交易CSV、要求分析交易表现、评估交易质量、生成复盘报告、 计算盈亏统计、识别交易模式问题、"帮我复盘"、"分析我的交易"。
安全使用建议
Review the referenced GitHub repository and its dependencies before running it, use a virtual environment or other isolation, and run it only on copied CSVs with account identifiers and unnecessary personal data removed. Treat generated scores and recommendations as informational, not as trading instructions.
功能分析
Type: OpenClaw Skill Name: trading-coach Version: 1.0.0 The SKILL.md file instructs the AI agent to `git clone` an external GitHub repository (`https://github.com/BENZEMA216/tradingcoach.git`) and subsequently execute Python scripts and install dependencies (`pip install -r requirements.txt`) from the downloaded content. This introduces a significant supply chain risk, as the actual code being executed is fetched from an external, unverified source not included in the bundle. While the stated purpose of the skill is benign trading analysis, the instruction to download and execute arbitrary external code is a high-risk capability.
能力评估
Purpose & Capability
The stated purpose is coherent: import broker CSVs, match trades, score trading quality, and generate review reports. The outputs may influence financial decisions, so they should be treated as educational analysis rather than financial advice.
Instruction Scope
The trigger phrases are purpose-related but broad, including generic requests like “帮我复盘” and “分析我的交易,” without an explicit confirmation step before processing sensitive trading records.
Install Mechanism
SKILL.md instructs users to clone an external GitHub repository, install dependencies from requirements.txt, and run Python scripts that are not included in the reviewed skill bundle. This is disclosed and purpose-aligned, but under-scoped for a security-reviewed artifact.
Credentials
Brokerage CSV fields such as symbols, prices, quantities, timestamps, fees, and profit/loss data are proportionate to the analysis purpose but financially sensitive, and the skill does not prominently warn users to minimize or redact data.
Persistence & Privilege
The provided artifacts do not show credentials, account mutation, privileged access, background workers, autorun behavior, hidden persistence, or data exfiltration.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install trading-coach
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /trading-coach 触发
  4. 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 of Trading Coach — an AI-powered trading review tool. - Automatically imports and matches trading records from major Chinese brokerages (Futu, Tiger, CITIC, Huatai, etc.). - Generates professional-grade review reports and actionable improvement insights based on broker CSV files. - Provides 8-dimension position scoring (entry/exit/trend/risk/behavior/news/execution...) - Delivers 10-dimension AI-powered trading analysis, highlighting patterns and areas for improvement. - Supports quickstart CLI workflow and detailed scoring/insight documentation. - Outputs clear summaries of trading statistics and personalized recommendations.
元数据
Slug trading-coach
版本 1.0.0
许可证
累计安装 371
当前安装数 74
历史版本数 1
常见问题

Trading Coach 是什么?

🏆 AI交易复盘教练 — 把你的券商CSV变成可执行的改进洞察! 自动FIFO配对持仓,8维度质量评分(入场/出场/趋势/风险...),10维度AI洞察。 支持富途(中/英)、老虎、中信、华泰等主流券商。 触发条件: 用户提供交易CSV、要求分析交易表现、评估交易质量、生成复盘报告、 计算盈亏统计、识别交易模式问题、"帮我复盘"、"分析我的交易"。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 10555 次。

如何安装 Trading Coach?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install trading-coach」即可一键安装,无需额外配置。

Trading Coach 是免费的吗?

是的,Trading Coach 完全免费(开源免费),可自由下载、安装和使用。

Trading Coach 支持哪些平台?

Trading Coach 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 Trading Coach?

由 BENZEMA(@benzema216)开发并维护,当前版本 v1.0.0。

💬 留言讨论