skills.rest
shiqkuangsan
shiqkuangsanCOMMUNITY
Explore all skills by this author →
GitHub

tooyoung:ink-reader

Extract clean Markdown content from URLs using Jina Reader, WebFetch, and Playwright MCP.

17|4|Updated Jan 25, 2026
Search Tags:#markdown#web scraping#content extraction#playwright#url reader#jina reader
One-click install
npx skills add https://github.com/shiqkuangsan/oh-my-daily-skills --skill tooyoung-ink-reader
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tooyoung:ink-reader
Source: https://github.com/shiqkuangsan/oh-my-daily-skills/tree/main/skills/ink-reader
Command: npx skills add https://github.com/shiqkuangsan/oh-my-daily-skills --skill tooyoung-ink-reader

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill allows you to effortlessly extract and read the content of any web URL, overcoming platform-specific challenges and login requirements.

Core Features & Use Cases

  • Universal URL Reading: Reads content from various platforms including WeChat, Zhihu, Bilibili, X/Twitter, and generic websites.
  • Intelligent Fetching: Employs a multi-layered fallback strategy (Jina Reader, WebFetch, Playwright MCP) for optimal content retrieval.
  • Use Case: When you encounter an interesting article on a platform that's difficult to read directly, use this skill to get a clean, Markdown-formatted version.

Quick Start

Use the ink-reader skill to read the content from the url https://example.com/article.

Frequently Asked Questions about tooyoung:ink-reader

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract web content from a URL into clean markdown?▼

To extract web content into clean markdown, this Skill reads any given URL using an intelligent multi-layer fallback strategy. It retrieves content through Jina Reader, WebFetch, and Playwright MCP to ensure optimal extraction.

Can I extract article content from platforms like WeChat, Zhihu, or Bilibili?▼

Yes, you can extract article content from platforms like WeChat, Zhihu, Bilibili, and X/Twitter. The Skill auto-detects the platform and applies fallback strategies to overcome retrieval challenges and produce clean markdown.

What is the best way to scrape web pages that require JavaScript rendering?▼

The best way to scrape JavaScript-rendered web pages is using a multi-layered fallback approach. This Skill initially attempts static retrieval via Jina Reader and WebFetch, falling back to Playwright MCP for dynamic rendering.

Does Jina Reader work with all websites for content extraction?▼

Jina Reader does not work universally with all websites for content extraction. When static fetching fails, this Skill implements a fallback strategy utilizing Claude Code's WebFetch and Playwright MCP to ensure the content is retrieved.

How do I read and save a web article while bypassing login requirements?▼

To read and save web articles bypassing some login requirements, this Skill extracts the content using its multi-layer fetching strategy. It outputs clean markdown and offers a save mode for clipping the retrieved content locally.

Why does web scraping fail on certain URLs and how to handle it?▼

Web scraping fails on certain URLs due to bot detection or rendering requirements. This Skill handles such failures by automatically falling back from Jina Reader to WebFetch, and finally to Playwright MCP for dynamic rendering.

Related Skills

Explore More Content & Communication Skills→
while-basicwhile-basic

enact/firecrawl

Extract web page content as Markdown or structured data via the Firecrawl API.

Community
Advanced
jykimjykim
1

markdown-to-docx

Convert Markdown documents to .docx with Korean font support and inline formatting.

Community
Intermediate
pacphipacphi
14

playwright

Automate browser interactions and screenshots via Playwright MCP on a VNC display.

Community
Advanced
zhizhunbaozhizhunbao

web-scraping

Automate web scraping and data extraction with Playwright and BeautifulSoup.

Community
Intermediate