wechat-article-reader

读取微信公众号文章链接，提取关键信息并生成摘要

Security Scan

The skill's code, instructions, and declared permissions are consistent with a WeChat article reader: it only requests HTTP access to fetch and parse mp.weixin.qq.com pages and does not ask for credentials or unexpected system access.

Purpose & Capability

Name/description (WeChat article reader) align with code and manifest. Dependencies (requests, BeautifulSoup, lxml, fake-useragent) are appropriate for fetching and parsing web pages. Triggers and network permissions correspond to the stated purpose.

Instruction Scope

SKILL.md instructs fetching mp.weixin.qq.com links, parsing HTML, and summarizing content. The runtime instructions do not request unrelated files, credentials, or system state. The README/skill.json mention platform integrations but the code itself does not attempt to post to external services beyond fetching the article.

Install Mechanism

No install spec is included (instruction-only installation), and the packaged requirements.txt references common PyPI packages. There are no downloads from unknown URLs or archive extraction instructions in the skill package.

Credentials

The skill requests no environment variables or credentials. It does require network access (network:read / network:http) which is reasonable. One caveat: the fake-useragent dependency may perform runtime network requests to fetch user-agent data on first use—this is a library behavior rather than credential access and could be mitigated by using a static UA string or a cached local database.

Persistence & Privilege

always:false (not force-included) and user-invocable:true. skill.json includes URL/keyword triggers, so the skill can auto-trigger when mp.weixin.qq.com links or keywords appear—this is consistent with the skill's purpose but you should be aware posting such links can cause automatic invocation and network fetches.

Assessment

This skill appears to do what it claims: it fetches mp.weixin.qq.com article pages, parses them, and returns summaries. It does not request credentials or unusual system access. Before installing, consider: (1) the skill needs outbound HTTP access to reach WeChat article pages (ensure your environment or policy allows this), (2) the fake-useragent dependency may make additional network calls to populate its UA database—if this is a concern you can pin a static User-Agent or pre-warm a cache, (3) the skill auto-triggers on matching URLs/keywords per skill.json, so posting WeChat links will cause it to run automatically; if you want to avoid automatic runs, remove or restrict triggers, and (4) audit and run the included tests in a sandboxed environment before enabling in production.

读取微信公众号文章链接的Skill，可以提取文章标题、作者、发布时间等关键信息，并生成内容摘要。

功能特性

• 自动识别微信公众号文章链接
• 提取文章关键信息（标题、作者、发布时间、公众号名称）
• 生成文章内容摘要
• 支持飞书平台使用

使用方法

方法1：直接发送链接

直接将公众号文章链接发送给OpenClaw：

https://mp.weixin.qq.com/s/xxxxx

方法2：明确指令

读取这篇文章：[链接]

方法3：请求摘要

帮我总结这篇公众号文章：[链接]

返回信息格式

Skill将返回以下关键信息：

📄 文章标题：[标题]
👤 作者：[作者]
🏢 公众号：[公众号名称]
📅 发布时间：[时间]

📝 内容摘要：
[AI生成的摘要]

🔑 关键点：
• 关键点1
• 关键点2
• 关键点3

技术说明

• 使用requests获取网页内容
• 使用BeautifulSoup解析HTML
• 处理微信公众号的反爬机制
• 智能提取文章正文内容

依赖项

• requests>=2.31.0
• beautifulsoup4>=4.12.0
• lxml>=4.9.0
• fake-useragent>=1.4.0

注意事项

• 仅支持微信公众号官方文章链接（mp.weixin.qq.com）
• 部分文章可能因公众号设置无法访问
• 建议配合飞书WebHook使用以获得最佳体验

常见问题

Q: 为什么有些文章无法读取？ A: 可能是文章已删除、设置为私密，或需要关注公众号才能阅读。

Q: 摘要质量如何保证？ A: Skill会提取文章核心段落，由OpenClaw的大模型能力进行智能摘要。

Q: 支持其他平台的文章吗？ A: 当前版本仅支持微信公众号，后续版本可能扩展到其他平台。