WeChat Article Reader

该 Skill 在用户提供 mp.weixin.qq.com 链接时，调用浏览器工具打开页面、等待渲染后 snapshot 提取全文，再关闭标签并把内容呈现给用户（按需摘要或翻译）。材料说明公众号页面为 JS 渲染且有反爬，web_fetch 只能取到标题；遇到登录墙或内容违规下架时仅告知用户。

imwyvern

热度 95.39

最近更新 2026-05-11 17:29:44

分类：自动化依赖：联网浏览搜索应用场景：摘要总结 / 翻译

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add wechat-reader

Metadata

name: wechat-reader
description: Read WeChat public account (微信公众号) articles. Activate when the user shares a mp.weixin.qq.com link, asks to read/summarize a WeChat article, or mentions 公众号/微信文章. These pages are JS-rendered and blocked by web_fetch — this skill uses browser automation to extract full article text.

WeChat Article Reader

Why This Skill Exists

WeChat public account articles (mp.weixin.qq.com/s/...) are fully JS-rendered and have anti-scraping measures. web_fetch only returns the title. Browser automation is required to get the full content.

How to Read an Article

Detect mp.weixin.qq.com URLs in user messages
Open with browser tool:

browser(action="open", url="<article_url>", profile="openclaw")

Wait for render, then snapshot:

browser(action="snapshot", targetId=<id>, maxChars=15000)

Close the tab:

browser(action="close", targetId=<id>)

Present the content to the user (summarize or translate as requested)

Tips

Articles may contain images — snapshot captures alt text and captions
Very long articles: increase maxChars to 30000 or use multiple snapshots with scrolling
If the page shows "此内容因违规无法查看" (content removed), inform the user
Some articles require WeChat login — if snapshot shows a login wall, inform the user
For multiple articles, process sequentially to avoid resource waste