← 返回 Skills 市场
horizoncove

tradedaily

作者 horizoncove · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
349
总下载
0
收藏
5
当前安装
1
版本数
在 OpenClaw 中安装
/install trader-daily
功能描述
[中文] 量化交易员日常任务管理系统 - 专为股票交易员设计的每日工作流程管理工具。 包含:开盘/收盘/日终汇报模板、实时持仓监控、风控提醒、交易日志记录。 使用场景:(1) 管理每日交易任务时间表 (2) 生成汇报给上级的简报 (3) 监控持仓风险 (4) 记录交易日志 (5) 复盘分析 [English] Q...
安全使用建议
This skill appears to implement what it claims (report generation and risk monitoring), but there are practical and privacy issues to resolve before using it. Specifically: (1) SKILL.md paths (scripts/, config/, references/) do not match the package folder names (scripts_files/, config_files/, references_files/) — verify and fix paths or move files before running. (2) The scripts require the Python requests package but no install instructions are provided — install requests or add a requirements/install step. (3) The risk monitor uses an unencrypted HTTP API (qt.gtimg.cn) for prices; consider using HTTPS or verifying the integrity of price data in your environment. (4) The included config/portfolio.json contains realistic personal holdings — treat it as sensitive data; remove or replace it if you will publish/share the skill. (5) Some commands listed in the README (portfolio_status, trading_log) are not implemented; expect limited functionality until those are added. Recommendation: run the code in an isolated environment, inspect/clean the bundled config files, add an explicit install/requirements step, and fix the path inconsistencies before trusting this skill with real data.
功能分析
Type: OpenClaw Skill Name: trader-daily Version: 1.0.0 The skill bundle provides a legitimate set of tools for quantitative traders, including report generation and risk monitoring. The Python scripts (generate_report.py, risk_monitor.py) perform standard file I/O and use a public Tencent API for real-time stock data without any signs of malicious intent, data exfiltration, or prompt injection.
能力评估
Purpose & Capability
Name/description, the two Python scripts, and the included config/templates are consistent with a daily trading/task/reporting tool. The risk_monitor script legitimately fetches market prices from a public provider (qt.gtimg.cn) which aligns with the stated portfolio-monitoring feature. However, the bundle contains a realistic-looking portfolio file ('Alex的真实持仓'), which is surprising for a published skill and could unintentionally expose sensitive financial data if installed or shared.
Instruction Scope
SKILL.md instructs running commands like python3 scripts/generate_report.py --portfolio config/portfolio.json and references paths like references/daily-schedule.md and config/portfolio.json, but the actual files in the package live under differently named folders (scripts_files/, references_files/, config_files/). That mismatch will likely cause FileNotFound errors. The quick-reference lists commands (e.g., portfolio_status, trading_log) that are not implemented. The risk_monitor script performs outbound HTTP requests for prices (expected) but does not send portfolio data externally — only stock codes go to the public price API.
Install Mechanism
There is no install spec (instruction-only install). The Python scripts import the third-party requests library but the SKILL.md does not declare this dependency or provide setup instructions; installation may fail if requests is not present. The risk_monitor calls an HTTP (not HTTPS) endpoint (http://qt.gtimg.cn/q=...), which is a public price API but uses unencrypted HTTP — consider network eavesdropping / MITM concerns.
Credentials
The skill requests no environment variables or credentials (appropriate), and scripts do not exfiltrate secrets. However, bundling an apparently 'real' portfolio (config_files/portfolio.json with name 'Alex的真实持仓' and realistic balances) is disproportionate for a generic skill release and risks leaking sensitive personal/financial data if the skill is published or shared. No other unrelated credentials are requested (good).
Persistence & Privilege
The skill does not request persistent presence (always:false) and does not modify other skills or system-wide settings. It runs as user-invocable code and does not declare autonomic elevated privileges.
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 trader-daily
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /trader-daily 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
test
元数据
Slug trader-daily
版本 1.0.0
许可证 MIT-0
累计安装 6
当前安装数 5
历史版本数 1
常见问题

tradedaily 是什么?

[中文] 量化交易员日常任务管理系统 - 专为股票交易员设计的每日工作流程管理工具。 包含:开盘/收盘/日终汇报模板、实时持仓监控、风控提醒、交易日志记录。 使用场景:(1) 管理每日交易任务时间表 (2) 生成汇报给上级的简报 (3) 监控持仓风险 (4) 记录交易日志 (5) 复盘分析 [English] Q... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 349 次。

如何安装 tradedaily?

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

tradedaily 是免费的吗?

是的,tradedaily 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

tradedaily 支持哪些平台?

tradedaily 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 tradedaily?

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

💬 留言讨论