html-to-markdown

Converts HTML or live web pages into structured Markdown with metadata and link inventories.

18|1|Updated Apr 8, 2026
One-click install
npx skills add https://github.com/appautomaton/webmaton --skill html-to-markdown-appautomaton
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: html-to-markdown
Source: https://github.com/appautomaton/webmaton/tree/main/skills/html-to-markdown
Command: npx skills add https://github.com/appautomaton/webmaton --skill html-to-markdown-appautomaton

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires nodriver, markmaton, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the challenge of converting complex, JavaScript-heavy web pages into clean, readable Markdown, ensuring that AI agents can process web content without the noise of boilerplate HTML or broken layouts.

Core Features & Use Cases

  • Browser-Based Capture: Uses headless browser automation to render dynamic content before conversion, ensuring JS-heavy pages are captured correctly.
  • Deterministic Conversion: Transforms HTML into structured Markdown with metadata, link inventories, and image tracking.
  • Use Case: Use this to ingest documentation, research articles, or dynamic web reports into your agent's context window for analysis or summarization.

Quick Start

Use the html-to-markdown skill to capture the content of the provided URL and convert it into a clean Markdown format.

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 HTML to Markdown from JavaScript-heavy web pages?

To convert HTML to Markdown from dynamic pages, you can use headless browser automation to render the content first. This skill uses nodriver to capture the fully loaded page and then parses the output into structured Markdown.

What is the best way to scrape web content for AI context ingestion?

The best way to scrape web content for AI ingestion is to convert live web pages into clean Markdown. This removes HTML boilerplate and creates structured text with metadata and link inventories, making it ideal for agent analysis.

Does this HTML to Markdown conversion handle dynamic web reports?

Yes, this HTML to Markdown conversion handles dynamic web reports by using a headless browser to render JavaScript-heavy content before parsing it. This ensures that dynamically loaded data is captured correctly.

Can I use static URL fetching to convert HTML to Markdown?

Yes, you can use static URL fetching to convert HTML to Markdown. This skill supports both static fetching for simple pages and headless browser-based rendering for complex, dynamic web applications.

Do I need nodriver to convert web pages into Markdown?

Yes, you need nodriver for browser automation when converting dynamic web pages into Markdown. The skill also requires markmaton to perform the high-fidelity HTML-to-Markdown parsing.

What limitations exist when converting dynamic HTML to Markdown?

A limitation when converting dynamic HTML to Markdown is that pages must be fully renderable in a headless browser environment. Complex JavaScript interactions that require manual user input may not be captured correctly.