yhslgg-archyhslgg-archCommunity·1 Agent Skills Included

url-reader

Extract and save web articles from Chinese platforms

Reads any URL and extracts clean Markdown content from WeChat, Xiaohongshu, Douyin, Taobao, Zhihu, and other major Chinese platforms. Automatically detects the platform and picks the best reading strategy, falling back from Firecrawl to Jina to Playwright when sites block scraping. Saves articles and images locally, eliminating manual copy-pasting and messy formatting.
npx skills add yhslgg-arch/url-reader --all -g -y

All Skills in This Repository (1)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install url-reader?

Run `npx skills add yhslgg-arch/url-reader --all -g -y` in your terminal to install it globally.

How to read WeChat articles with AI?

Just paste the WeChat article link in your chat. The skill detects the platform and uses Playwright with a saved login session to extract the full content.

Which platforms does url-reader support?

It supports WeChat, Xiaohongshu, Toutiao, Douyin, Taobao, Tmall, JD, Baidu, Zhihu, Weibo, Bilibili, and any generic website.

What happens when a site blocks scraping?

The skill automatically falls back through three strategies: Firecrawl first, then the free Jina Reader, and finally Playwright browser automation for login-protected pages.

Does url-reader save images too?

Yes. It downloads all article images alongside the Markdown content into a dated local folder for easy archiving.

Related Repositories in Content & Communication

View All in Content & Communication