Weixin Reader Oc Local

读取微信公众号文章内容。当用户发送微信公众号文章链接（mp.weixin.qq.com）时，使用此 skill 提取文章完整文字内容。此工具不需要登录即可提取微信文章，是读取微信文章的最佳方案。

Security Scan

The skill's instructions are narrowly scoped and match its stated purpose, but an unexplained metadata mismatch (owner/slug in _meta.json vs registry) and its reliance on an external tool to fetch content warrant caution before installing.

Purpose & Capability

The skill claims to extract Weixin (mp.weixin.qq.com) article text without login and its runtime instructions only call an 'extract_content_from_websites' tool and then filter HTML — this is proportionate to the stated purpose. However, the included _meta.json has a different ownerId and slug than the registry metadata, which is an inconsistency in provenance that should be explained by the publisher.

Instruction Scope

SKILL.md is limited: it instructs using extract_content_from_websites, filtering out navigation/ads, and returning title/author/date/body. It explicitly forbids using web_fetch. There are no instructions to read local files, environment variables, or other unrelated data.

Install Mechanism

No install spec and no code files — instruction-only skill. Nothing will be written to disk by the skill itself during install.

Credentials

No environment variables, credentials, or config paths are requested, which is proportionate for a content-extraction helper.

Persistence & Privilege

always is false and the skill is user-invocable; it does not request persistent elevated privileges or self-enablement. Autonomous invocation is allowed (platform default) but not by itself a red flag.

What to consider before installing

This skill's code/instructions themselves are simple and consistent with extracting Weixin article text, but two things to check before installing: (1) provenance: the _meta.json embedded in the skill lists a different ownerId/slug than the registry metadata — ask the publisher to explain and correct this mismatch, as it may indicate a copy/paste or tampered package; (2) the skill relies entirely on an external tool named extract_content_from_websites to fetch page content — confirm how that tool fetches pages (does it proxy content to a third party, log URLs, or require network access?), and whether that behavior is acceptable for any sensitive URLs you might supply. If you need confidentiality, test the skill with non-sensitive links first and verify the platform/tool privacy policy.

微信公众号文章读取

使用场景

• 用户发送微信公众号文章链接
• 用户说"帮我看看这篇文章写了什么"
• 用户说"提取这个微信文章的内容"

操作步骤

1. 使用 extract_content_from_websites 工具提取文章内容
2. 过滤掉页面中的 HTML 标签、导航、广告等无关内容
3. 提取并返回文章的：标题、作者、发布日期、正文内容

代码示例

{
  "tasks": [
    {
      "prompt": "提取文章的完整文字内容，包括标题、作者、发布日期和正文",
      "url": "用户提供的微信文章链接"
    }
  ]
}

注意事项

• 不要使用 web_fetch，它无法读取微信文章（需要登录）
• 必须使用 extract_content_from_websites 工具
• 微信公众号文章链接格式：https://mp.weixin.qq.com/s/xxx