Does it save images from the articles?

This skill is specifically designed to extract and save clean text content and headings to ensure files are lightweight and distraction-free.

How are the saved files named?

The skill automatically fetches the article title from the website's metadata and sanitizes it into a filesystem-friendly filename.

Is it possible to extract multiple articles at once?

Yes, you can provide multiple URLs to Claude, and it will use this skill to process and save each article individually.

Which extraction tools does this skill support?

It prioritizes 'reader-cli' (Mozilla Readability) and 'trafilatura' for high-quality extraction, but also includes a native Python fallback if those aren't available.

Can this skill bypass paywalls or login screens?

No, the skill relies on tools that access publicly available HTML. It cannot bypass authentication or subscription-based paywalls.

Article Extractor

Name: Article Extractor
Author: Krosebrook

byKrosebrook

•

Web Scraping & Data Collection

Extracts clean, clutter-free content from web articles and blog posts for readable text storage.

About

The Article Extractor skill empowers Claude to convert cluttered web pages into clean, readable text files. By utilizing industry-standard tools like Mozilla's Readability algorithm and Trafilatura, it intelligently strips away ads, navigation bars, and newsletter popups to focus solely on the primary content. This tool is essential for developers, researchers, and content creators who need to archive tutorials, documentation, or blog posts in a structured, text-only format for local reading, knowledge bases, or further AI-assisted processing.

Key Features

Multi-engine extraction using Mozilla Readability or Trafilatura
Preservation of article structure and headings for maximum readability
Smart filename generation based on sanitized article titles
Automated removal of ads, sidebars, and promotional clutter
Robust Python-based fallback for environments without specialized CLI tools
1 GitHub stars

Use Cases

Archiving technical tutorials and documentation for offline reference
Converting web articles into clean text for AI analysis or summarization
Building a local knowledge base from online blog posts without distraction

About

Key Features

Multi-engine extraction using Mozilla Readability or Trafilatura
Preservation of article structure and headings for maximum readability
Smart filename generation based on sanitized article titles
Automated removal of ads, sidebars, and promotional clutter
Robust Python-based fallback for environments without specialized CLI tools
1 GitHub stars

Use Cases

Archiving technical tutorials and documentation for offline reference
Converting web articles into clean text for AI analysis or summarization
Building a local knowledge base from online blog posts without distraction