wechat-mp-reader

What This Skill Does

The wechat-mp-reader skill provides OpenClaw with the capability to browse and parse content from WeChat official account (MP) articles. WeChat articles are notoriously difficult to scrape due to anti-bot measures, which often trigger CAPTCHAs if requests are malformed. This skill automates the critical process of URL normalization, ensuring every request includes the '?scene=1' parameter, which is essential for bypassing these restrictions and accessing the public article body. By leveraging a browser tool, it waits for the specific DOM elements (like #js_content) to hydrate before extracting the text, ensuring a clean and reliable result for the AI to process.

Installation

To integrate this skill into your OpenClaw environment, execute the following command in your terminal: clawhub install openclaw/skills/skills/bernylinville/wechat-mp-reader This will download the necessary definitions from the source repository and register the reader as an available agent capability.

Use Cases

This skill is perfect for researchers, journalists, or content analysts who monitor the Chinese digital ecosystem. Use it to: 1) Aggregate long-form insights from niche WeChat industry accounts. 2) Summarize breaking news stories or corporate announcements published via official channels. 3) Archive historical content from disappearing or restricted public accounts.

Example Prompts

1. "Read the article at https://mp.weixin.qq.com/s/example123 and summarize the key technical points regarding the new AI regulation."
2. "Extract the full text from this WeChat article (https://mp.weixin.qq.com/s/abc456) and save it to my knowledge base."
3. "Go to this URL: https://mp.weixin.qq.com/s/xyz789 and tell me the author's primary argument about market trends."

Tips & Limitations

Always double-check that your URL is a valid WeChat public article link. If the skill returns empty content, the page may have been deleted, or the network speed may be insufficient for the selector to trigger; simply retry the operation. If you encounter a CAPTCHA screen, it means the URL was not properly normalized—the skill handles this automatically, but ensure no conflicting parameters are being injected by other agents. Note that this skill is optimized for text content and may not capture interactive elements, videos, or audio embedded within the article.