web-content-scraper

What problem does it solve?

This Skill enables reliable extraction of the main article content from web pages while filtering noise like ads, headers, footers, and navigation. It also downloads relevant images and preserves their source URLs for copyright attribution, delivering clean, markdown-ready content for AI contexts.

Core Features & Use Cases

• Main content extraction: Retrieve the primary article or page content and convert it to markdown.
• Image attribution: Download images with alt text and preserve source attribution metadata.
• Robust to site variations: Works across blogs, documentation pages, and care guides by targeting common content regions and removing boilerplate.
• Use Case: Feed collected web content into your moss wall knowledge base to answer questions with both text and referenced images.

Quick Start

• Provide a URL to scrape (e.g., https://example.com/article) and return the cleaned main content as markdown, including image captions and attribution URLs.