微信公众号内容总结

抓取微信公众号文章并转换为Markdown，提取正文内容后总结核心观点或直接输出完整文章。

Security Scan

The skill's code and runtime instructions match its stated purpose (fetch a WeChat article, convert to Markdown, optionally download images, then summarize or output); nothing in the files requests unrelated credentials or network endpoints.

Purpose & Capability

Name/description (fetch WeChat articles, convert to Markdown, summarize) align with the included script and SKILL.md. The script uses requests/BeautifulSoup/html2text to fetch and convert article HTML and can save images — all coherent with the described purpose.

Instruction Scope

SKILL.md confines actions to fetching the article, converting to Markdown, optionally downloading images, saving a .md file, then deleting it. It references specific workspace paths (/home/node/.openclaw/...) and uses PYTHONPATH=/tmp/pylibs; both are environment-specific but consistent with running the included script. There is no instruction to read unrelated system files, credentials, or to transmit data to unknown external endpoints. The required cleanup step (deleting generated .md) is emphasized; this is plausible but users should be aware it removes local files.

Install Mechanism

There is no formal install spec (instruction-only), which is low-risk. The SKILL.md suggests pip installing html2text and beautifulsoup4 into /tmp/pylibs if missing — this will write packages to disk and pulls from PyPI. The packages named are reasonable and proportionate for the task.

Credentials

The skill requests no environment variables, credentials, or config paths. The script uses only network access (HTTP GET) and local file write/read for output and optional image downloads — these are expected for the stated purpose.

Persistence & Privilege

Skill is not always-enabled and does not request elevated/system-wide persistence. It writes output files in the workspace or a specified output directory and can create an images/ subdirectory when saving images. It does not modify other skills or global agent settings.

Assessment

This skill appears to do what it says: fetch a public mp.weixin.qq.com article, convert it to Markdown, optionally download images, and let the agent summarize or output the article. Before installing/running: 1) Review or run the included wechat2md.py in a sandbox to confirm behavior; 2) be aware it performs network requests and writes files (and the SKILL.md instructs you to delete generated .md files afterwards); 3) the SKILL.md suggests pip installing html2text/beautifulsoup4 into /tmp, which will download code from PyPI—only proceed if you trust those packages or install them via your usual package manager; 4) the script will not bypass WeChat JS verification or paywalled content; 5) consider copyright and privacy implications of fetching and storing article content and images. If you need stronger isolation, run the script in a container or VM.

微信公众号文章读取技能

概述

使用 wechat2md.py 脚本抓取微信公众号文章内容并转换为 Markdown 格式。抓取后可对内容进行总结或直接输出原文。

前置条件

依赖已安装在 /tmp/pylibs：

• html2text
• beautifulsoup4
• requests

如遇 ModuleNotFoundError，运行：

pip3 install html2text beautifulsoup4 --target=/tmp/pylibs -q

标准流程

Step 1：抓取文章

cd /home/node/.openclaw/workspace-research/skills/WeChat-mp
PYTHONPATH=/tmp/pylibs python3 wechat2md.py "<文章链接>"

文章会保存为同名 .md 文件在当前目录下。

Step 2：读取内容

读取生成的 .md 文件，提取正文内容。

Step 3：总结或输出

按用户需求执行：

• 总结（默认）：提炼核心观点、主要话题、关键结论
• 完整内容：直接输出 .md 原文内容，不做删减

Step 4：清理文件

重要！总结完成后必须删除生成的 .md 文件。

rm -f "/home/node/.openclaw/workspace-research/skills/WeChat-mp/<文件名>.md"

除非用户明确要求保留，否则一律删除。

注意事项

• 脚本会自动处理懒加载图片（data-src → src）
• 如需下载图片到本地，可加 --save-images 参数
• 网络错误或文章被删时，脚本会输出明确错误信息
• 微信 JS 验证（"环境异常"）目前无法绕过，如脚本失败说明文章需要真人验证，只能告知用户无法提取

总结模板

## 文章核心观点总结

### 一、核心结论
[一句话概括]

### 二、主要观点
**1. [主题]**
- 要点1
- 要点2

### 三、关键结论
| 结论 | 说明 |
|------|------|
| ... | ... |

### 四、延伸思考
[可选]