web-to-markdown

Extract web article content and metadata into Markdown files.

1|1|Updated Mar 29, 2026
One-click install
npx skills add https://github.com/yuyuxinli/moodcoco --skill web-to-markdown-yuyuxinli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: web-to-markdown
Source: https://github.com/yuyuxinli/moodcoco/tree/main/.claude/skills/web-to-markdown
Command: npx skills add https://github.com/yuyuxinli/moodcoco --skill web-to-markdown-yuyuxinli

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Converts long or complex web articles into clean, readable Markdown files and saves them locally so users can read, archive, and reference content offline without manual copy-paste or formatting work.

Core Features & Use Cases

  • Automatic extraction and conversion: Detects the main article container, converts HTML to Markdown (headings, lists, code blocks, images, tables, blockquotes).
  • Metadata and chunking: Extracts title, author, date, and splits very long articles into sequential chunks for reliable transfer.
  • Browser-driven workflow: Injects JavaScript into an open Chrome tab to run extraction and supports reading subsequent chunks, then saves assembled Markdown via a Python helper.
  • Use Cases: Archiving long-form essays, saving blog posts or public WeChat articles for research, and capturing multi-page or dynamically loaded content for offline reading.

Quick Start

Open the article in Chrome and ask the agent to extract the page and save it as a Markdown file into ./参考文章/{title}.md.

Frequently Asked Questions about web-to-markdown

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

FAQPage Schema
How do I save a web article as a Markdown file for offline reading?

To save a web article as a Markdown file, open the page in Chrome and let the agent automatically detect the main content container, extract metadata, and convert HTML elements into clean Markdown saved locally via a Python helper.

Can I extract content from dynamically loaded multi-page articles into Markdown?

Yes, you can extract content from dynamically loaded multi-page articles by injecting JavaScript into Chrome to read and reassemble sequential content chunks into a single Markdown file for reliable local archival.

Does web scraping into Markdown work with WeChat public account pages and Medium posts?

Yes, web scraping into Markdown works with WeChat public account pages and Medium posts, as the automatic selector detection extracts long-form article content and metadata from these specific platforms for local saving.

How do I convert HTML headings, lists, and tables to Markdown format?

To convert HTML headings, lists, and tables to Markdown format, the extraction process automatically parses the article container and translates standard HTML elements into their corresponding Markdown syntax for local files.

Do I need a specific browser environment to extract article content and metadata?

Yes, you need an open Chrome session with the mcp__claude-in-chrome__* browser tooling, because the extraction relies on JavaScript injection to detect selectors, chunk long content, and save the assembled Markdown file locally.