← Back to Skills Marketplace
cnxufei-tech

Daily Review Assistant

by cnxufei-tech · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
483
Downloads
0
Stars
3
Active Installs
1
Versions
Install in OpenClaw
/install daily-review-assistant
Description
Generate A-share daily review report (stock-analysis/daily_review.py). Supports --email.
README (SKILL.md)

每日复盘小助手

功能

生成 A 股每日复盘 Markdown 报告(基于 AkShare),并可选通过 SMTP 发送邮件。

包含:

  • 全市场概览(指数、涨跌家数、成交额等)
  • 连板统计与明细(含成交额/换手/封板时间)
  • 板块涨幅榜(行业板块;失败时回退概念板块)
  • 龙虎榜(标题带总数;列出全部净买入个股,含涨幅;并附“其他上榜”简表)
  • 舆情监控(涨停股新闻标题关键词打分)
  • 次日策略

使用方式

命令触发(推荐)

  • 生成报告:/daily-review 2026-02-27
  • 发送邮件:/daily-review 2026-02-27 --email
  • 不传日期:默认今日

由助手在工作区执行:python3 stock-analysis/daily_review.py \x3Cdate> [--email]

手动生成

在工作区运行:

python3 stock-analysis/daily_review.py 20260227

日期支持:

  • YYYYMMDD
  • YYYY-MM-DD
  • 不传日期:默认今日

发送邮件(可选)

python3 stock-analysis/daily_review.py 20260227 --email

邮件配置文件:

  • 默认:stock-analysis/email_config.json
  • 可用环境变量覆盖:DAILY_REVIEW_EMAIL_CONFIG=/path/to/email_config.json

SMTP 密码(授权码)从环境变量读取:

  • 默认:SMTP_PASSWORD

配置示例:

  • stock-analysis/email_config.example.json

输出

  • 报告保存路径:stock-analysis/reports/YYYYMMDD.md

依赖

  • Python 3
  • akshare

注意

  • AkShare 数据源偶发断连,脚本已对板块接口做退避重试与回退。
  • 邮件发送使用 SMTP,建议使用服务商的“授权码”而不是登录密码。
Usage Guidance
This skill is an instruction-only wrapper that expects an existing 'stock-analysis' project in your workspace and an SMTP credential to send mail. Before installing or running it: ensure you actually have the stock-analysis/daily_review.py script and akshare installed; provide a dedicated email account with an app-specific/authorization code (not your primary password); verify the content of stock-analysis/email_config.json (or any file you point DAILY_REVIEW_EMAIL_CONFIG to) so you don't accidentally expose other secrets; and run the script in an isolated or test environment first. The missing script and undeclared env vars are the main inconsistencies — they don't prove malicious intent but do warrant caution.
Capability Analysis
Type: OpenClaw Skill Name: daily-review-assistant Version: 1.0.0 The skill is classified as suspicious due to a potential shell injection vulnerability described in `SKILL.md`. The instructions for the AI agent state it will execute `python3 stock-analysis/daily_review.py <date> [--email]`, where `<date>` is user-provided. If the OpenClaw agent directly substitutes this input without proper sanitization, it could allow a malicious user to inject arbitrary shell commands. Additionally, the skill indicates the underlying Python script will access sensitive information like an SMTP password from environment variables (`SMTP_PASSWORD`), which, while a common practice, necessitates careful review of the script (not provided) for secure handling.
Capability Assessment
Purpose & Capability
Name/description (daily A-share report, optional email) matches the instructions. Required binary python3 is appropriate. However, the SKILL.md references the script stock-analysis/daily_review.py and the akshare dependency while the skill bundle contains no code and does not declare akshare as a required dependency — the skill appears to assume an external workspace/project that it does not provide.
Instruction Scope
Instructions direct the agent to run python3 stock-analysis/daily_review.py, read/write files under stock-analysis/ (reports and email_config.json), and optionally send mail via SMTP. The SKILL.md also reads environment variables (DAILY_REVIEW_EMAIL_CONFIG, SMTP_PASSWORD) but the skill metadata did not declare these env vars. The package contains no script, so following the instructions will depend on files existing elsewhere; the instructions allow overriding config paths via env var which could point the script at arbitrary files.
Install Mechanism
No install spec — lowest install risk. Nothing is downloaded or written by the skill package itself. That said, dependencies (akshare) are listed in prose only and are not installed automatically.
Credentials
The instructions expect an SMTP password from an environment variable (default SMTP_PASSWORD) and allow overriding the email config path via DAILY_REVIEW_EMAIL_CONFIG, but the skill metadata declares no required env vars. Requesting an SMTP credential is reasonable for email functionality, but the undeclared env vars and the ability to point to arbitrary config paths increases the risk that sensitive files or credentials might be read or used unintentionally.
Persistence & Privilege
always is false and the skill does not request persistent privileges or modify other skills' configs. The skill will run commands in the workspace and write report files under stock-analysis/, which is expected for its purpose.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install daily-review-assistant
  3. After installation, invoke the skill by name or use /daily-review-assistant
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of daily-review-assistant. - Generates daily A-share market review reports in Markdown, with highlights like market overview, leaderboards, and strategy. - Optionally sends reports via SMTP email using configurable settings. - Supports flexible date input formats and fallback mechanisms for unstable data sources. - Output files stored under stock-analysis/reports/YYYYMMDD.md. - Requires Python 3 and AkShare; email sending uses SMTP with environment-based config.
Metadata
Slug daily-review-assistant
Version 1.0.0
License
All-time Installs 3
Active Installs 3
Total Versions 1
Frequently Asked Questions

What is Daily Review Assistant?

Generate A-share daily review report (stock-analysis/daily_review.py). Supports --email. It is an AI Agent Skill for Claude Code / OpenClaw, with 483 downloads so far.

How do I install Daily Review Assistant?

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

Is Daily Review Assistant free?

Yes, Daily Review Assistant is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Daily Review Assistant support?

Daily Review Assistant is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Daily Review Assistant?

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

💬 Comments