Does this skill work with paywalled content?

The skill relies on public access to the URL; content behind logins or paywalls generally cannot be extracted unless the tool can bypass the gate or the content is already accessible in the DOM.

What tools need to be installed to use this skill?

The skill prefers 'reader-cli' (Mozilla Readability) or 'trafilatura', but it includes a built-in Python fallback method that works without external dependencies.

How does it handle file naming for saved articles?

It automatically extracts the article's title from the site metadata, sanitizes it by removing illegal characters, and saves it as a .txt file.

Can it extract images from the articles?

No, this specific skill is optimized for extracting and saving the clean text content, headings, and structure of an article rather than visual media.

Article Extractor

Name: Article Extractor
Author: kivilaid

bykivilaid

•

Web Scraping & Data Collection

Extracts clean, distraction-free text content from web URLs and saves it as readable text files.

About

The Article Extractor skill empowers Claude to convert cluttered web pages into clean, structured text files by stripping away ads, navigation menus, and non-essential scripts. Utilizing industry-standard tools like Mozilla's Readability algorithm and Trafilatura, it intelligently identifies the main content of blog posts, tutorials, and news articles. The skill automatically handles filesystem-friendly naming based on article titles and provides immediate content previews, making it an essential tool for research, archiving, and offline reading.

Key Features

Instant content preview and verification after extraction
6 GitHub stars
Automatic removal of ads, navigation menus, and newsletter popups
Multi-tool fallback system for maximum extraction reliability
Distraction-free content extraction using Readability and Trafilatura
Intelligent filesystem-friendly naming based on article titles

Use Cases

Archiving blog posts for offline reading or reference without clutter
Converting online tutorials into local documentation files for research
Preparing web content for further data processing or LLM analysis

About

Key Features

Instant content preview and verification after extraction
6 GitHub stars
Automatic removal of ads, navigation menus, and newsletter popups
Multi-tool fallback system for maximum extraction reliability
Distraction-free content extraction using Readability and Trafilatura
Intelligent filesystem-friendly naming based on article titles

Use Cases

Archiving blog posts for offline reading or reference without clutter
Converting online tutorials into local documentation files for research
Preparing web content for further data processing or LLM analysis