article-extractor

Extract main article text from URLs and save as .txt files.

8|3|Updated Feb 8, 2026

Search Tags:#readability #article #text-extraction #web-content #title-extraction #content-scraping #offline-archiving

Ready to run

npx skills add https://github.com/haberlah/dotfiles-claude --skill article-extractor-haberlah

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: article-extractor
Source: https://github.com/haberlah/dotfiles-claude/tree/main/skills/article-extractor
Command: npx skills add https://github.com/haberlah/dotfiles-claude --skill article-extractor-haberlah

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill extracts the main article content from URLs, removing ads, navigation, and clutter to produce readable text you can save or share.

Core Features & Use Cases

Content extraction: pull the article body from URLs using a preferred backend (reader, trafilatura, or a lightweight curl-based fallback).
Title-based file naming: derive a suitable filename from the article title for easy organization.
Save and preview: store clean text to a .txt file and provide a quick preview for verification.
Use Case: download and archive long-form posts for offline reading or research without distractions.

Quick Start

Use this skill by providing an article URL and asking to extract the clean text for saving.

Frequently Asked Questions about article-extractor

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

FAQPage Schema

How do I extract the main article text from a URL and remove ads or navigation?▼

To extract article text from a URL, the skill processes the link using a prioritized toolkit to remove ads and navigation, producing clean, readable text saved as a .txt file. It also generates a title-based filename and a text preview for verification.

What is the best way to save web content for offline reading without clutter?▼

The best way to save web content for offline reading is extracting the main article body and removing clutter. This skill pulls the readable text from URLs and stores it as a clean .txt file, making it suitable for archiving long-form posts or research without distractions.

Can I extract text from any type of web page or does it only work on news articles?▼

Text extraction works on blog posts, tutorials, and news URLs where removing clutter and navigation is necessary. It processes these web pages by applying a prioritized toolkit, including reader, trafilatura, or a curl-based fallback, to isolate the main article content.

How does the title-based file naming work when saving extracted web content?▼

Title-based file naming works by deriving a suitable filename directly from the extracted article title. This ensures your saved .txt files are organized logically, making it easier to manage and retrieve archived web content for later reading or research.

What happens if the primary text extraction backend fails to parse a web page?▼

If the primary text extraction backend fails, the skill applies a lightweight curl-based fallback to parse the web page. This prioritized toolkit approach ensures you still get a preview and saved text file even when standard content scraping methods encounter issues.

Do I need to install any dependencies to extract clean text from web articles?▼

No dependencies are required to start extracting clean text from web articles. The skill handles the content scraping internally by utilizing its built-in prioritized toolkit, allowing you to simply provide an article URL and request the text extraction.