skills.rest
venhdev
venhdevCOMMUNITY
Explore all skills by this author →
GitHub

url-to-markdown

Convert public web page URLs into clean Markdown files.

Updated May 3, 2026
Search Tags:#batch processing#markdown conversion#web content extraction#url-to-markdown#llm context#offline archiving
One-click install
npx skills add https://github.com/venhdev/skills --skill url-to-markdown-venhdev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: url-to-markdown
Source: https://github.com/venhdev/skills/tree/main/skills/url-to-markdown
Command: npx skills add https://github.com/venhdev/skills --skill url-to-markdown-venhdev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @mozilla/readability, defuddle, jsdom, turndown, turndown-plugin-gfm, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Manually copying web content into Markdown loses original formatting and includes unwanted clutter like ads, navigation bars, and sidebars, while batch processing multiple URLs is time-consuming and prone to errors.

Core Features & Use Cases

  • Intelligent Content Extraction: Uses Mozilla Readability to automatically strip ads, nav elements, and sidebars, pulling only the main article content from any public web page.
  • Batch URL Processing: Convert single URLs, multiple URLs at once, or load URLs from .txt, .csv, or .json files to process dozens of web pages in seconds.
  • Customizable Output: Toggle inclusion of images, links, and metadata, or generate an ASCII page-structure map of headings for quick navigation of long articles. For example, if you have a list of 20 research article URLs, use this skill to convert all of them to clean, organized Markdown files ready to add to your personal knowledge base.

Quick Start

Provide your list of web URLs to the skill, and it will automatically convert them all to clean, well-formatted Markdown files saved to the .md directory.

Frequently Asked Questions about url-to-markdown

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

FAQPage Schema
How do I convert web page URLs to Markdown for LLM context preparation?▼

Web page URLs are converted to Markdown by extracting main article content using Mozilla Readability and transforming HTML with turndown. This strips ads and navigation bars, outputting clean Markdown files for offline access and LLM context preparation.

Can I batch process multiple URLs to Markdown files at once?▼

Yes, batch processing multiple URLs to Markdown is supported. You can provide individual URLs directly or load them from .txt, .csv, or .json files to convert dozens of web pages into Markdown files in seconds.

Do I need Node.js to extract web content and convert HTML to Markdown?▼

Yes, Node.js 18+ is required to run the web content extraction and HTML to Markdown conversion. The process relies on dependencies including defuddle, Mozilla Readability, and turndown to execute the transformation scripts.

What is the best way to extract main article content from web pages without ads and sidebars?▼

The best way to extract main article content is using Mozilla Readability, which automatically strips ads, navigation elements, and sidebars. It isolates the core article text before converting the HTML structure into clean Markdown formatting.

Can I customize Markdown conversion to toggle images, links, and metadata?▼

Yes, Markdown conversion is customizable to toggle the inclusion of images, links, and metadata. You can also generate an ASCII page-structure map of headings to navigate long research articles quickly.

What are the limitations of using Mozilla Readability for web content extraction?▼

Mozilla Readability is limited to extracting main content from public web pages and requires Node.js 18+ with dependencies like jsdom. It may not properly process dynamically loaded content or pages requiring authentication behind paywalls.

Related Skills

Explore More Content & Communication Skills→
danielscholldanielscholl

web

Fetch web pages and convert HTML to clean Markdown.

Community
Intermediate
LynxLabVNLynxLabVN

llm-wiki

Create and maintain interlinked markdown files for a persistent knowledge base.

Official
Advanced
richardnpaulrichardnpaul

google-workspace-ops

Coordinate Google Workspace assets across Drive, Docs, Sheets, and Slides.

Community
Intermediate
makerjackiemakerjackie
1

just-scrape

Extract structured JSON data and convert webpages to markdown via the just-scrape CLI.

Community
Intermediate