crawlberg

Scrape webpages and convert HTML content to Markdown.

26|2|Updated Jun 8, 2026

Search Tags:#document conversion #information retrieval #web scraping #content aggregation #HTML to Markdown

Ready to run

npx skills add https://github.com/xberg-io/plugins --skill crawlberg

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: crawlberg
Source: https://github.com/xberg-io/plugins/tree/main/plugins/crawlberg/.cursor-plugin/skills/crawlberg
Command: npx skills add https://github.com/xberg-io/plugins --skill crawlberg

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires crawlberg-cli, chromiumoxide, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of web scraping and converting websites into Markdown, making it easier to access and work with online content.

Core Features & Use Cases

Web Scraping: Fetch and extract content from any webpage.
Markdown Conversion: Convert scraped HTML content to Markdown.
Use Case: Use this Skill to gather information from a website and quickly convert it into a readable Markdown format for documentation or reports.

Quick Start

Use the crawlberg skill to scrape the website 'https://example.com' and convert it to Markdown.

Frequently Asked Questions about crawlberg

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

FAQPage Schema

How do I convert HTML from a website to Markdown?▼

To convert HTML to Markdown, this Skill automates web scraping using a headless browser to fetch webpage content and translate the HTML structure into readable Markdown format. It streamlines content aggregation and website archiving.

What is the best way to automate web scraping for information retrieval?▼

The best way to automate web scraping for information retrieval is using a CLI tool integrated with a headless browser. This approach fetches target URLs, extracts the raw HTML, and automatically converts the output to Markdown.

Do I need a headless browser environment to scrape websites and convert to Markdown?▼

Yes, you need a headless browser environment and the crawlberg CLI to scrape websites and convert to Markdown. The underlying chromiumoxide dependency requires this setup to properly fetch and render dynamic HTML content.

Can I use this approach for website archiving and content aggregation?▼

Yes, you can use this approach for website archiving and content aggregation because it fetches live webpages and converts the HTML content into a static, readable Markdown format. This makes storing and organizing retrieved documentation highly efficient.

Why use a headless browser for HTML to Markdown conversion instead of a simple fetch?▼

Using a headless browser for HTML to Markdown conversion handles JavaScript-rendered content that a simple fetch would miss. The chromiumoxide dependency ensures dynamic page elements are fully loaded before extraction.