skills.rest
nieomylnieja
nieomylniejaCOMMUNITY
Explore all skills by this author →
GitHub

html-to-markdown

Convert web pages from URLs into clean Markdown using html-to-markdown-node.

3|Updated Jul 13, 2020
Search Tags:#markdown#conversion#url#web-scraping#web-content#token-reduction#html-to-markdown
One-click install
npx skills add https://github.com/nieomylnieja/dotfiles --skill html-to-markdown
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: html-to-markdown
Source: https://github.com/nieomylnieja/dotfiles/tree/main/config/agents/skills/html-to-markdown
Command: npx skills add https://github.com/nieomylnieja/dotfiles --skill html-to-markdown

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires html-to-markdown-node, and includes scripts (resource) components.

What problem does it solve?

Convert web pages into clean Markdown, removing clutter and navigation to save tokens and make content easier to read or analyze.

Core Features & Use Cases

  • Convert fetched HTML from URLs into clean Markdown suitable for reading, summarization, or documentation.
  • Remove boilerplate, ads, and navigation to reduce token usage and improve focus on content.
  • Use case: prepare online articles or documentation for offline reading or AI-assisted analysis.

Quick Start

Provide a URL to convert and the script will output the converted Markdown to stdout.

Frequently Asked Questions about html-to-markdown

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

FAQPage Schema
How do I convert web pages to Markdown to reduce token usage?▼

Converting HTML to Markdown removes boilerplate, ads, and navigation from web pages, leaving only the core article or documentation text. This significantly minimizes token usage when reading online content for AI-assisted analysis.

What is the best way to extract article content from a URL for offline reading?▼

The best way to extract article content from a URL for offline reading is to convert the fetched HTML into clean Markdown. This strips away web boilerplate and formats the text for easier reading, summarization, or analysis.

How do I fetch and convert HTML to Markdown using html-to-markdown-node?▼

Fetch and convert HTML to Markdown by running the script with a target URL. The script relies on the html-to-markdown-node library to fetch the web page and automatically convert its HTML content into readable Markdown.

Can I use a URL to prepare online documentation for AI-assisted analysis?▼

Yes, you can use a URL to prepare online documentation for AI-assisted analysis. The script fetches the web page, converts the HTML to Markdown, and removes clutter to improve focus on the content while saving tokens.

Does converting web content to Markdown remove ads and navigation boilerplate?▼

Yes, converting web content to Markdown removes ads and navigation boilerplate. The process strips away web page clutter to reduce token usage and ensure the output focuses purely on the extracted article or documentation text.

Related Skills

Explore More Content & Communication Skills→
logeshv586-codelogeshv586-code

web-reader

Extract titles, HTML, text content, and publication time from web page URLs.

Community
Intermediate
MicrockMicrock
322

fabric

Select and execute Fabric patterns from 242+ prompts via CLI.

Community
Advanced
sergicalsergical
1

semantic-compression

Compress text by removing grammatical scaffolding while preserving meaning for LLM inputs.

Community
Intermediate
dennislee928dennislee928
54

firecrawl-scraper

Scrapes and crawls websites into LLM-ready markdown or JSON.

Community
Advanced