Article Extractor

Pulls clean article text from URLs by stripping out ads, navigation, and clutter. Works with reader-cli (Mozilla's Readability), trafilatura, or falls back to basic curl parsing if neither is installed. Feed it a blog post or tutorial URL and it saves readable text with the article title as filename. Handles the typical edge cases like special characters in titles and different site structures. Honestly most useful when you want to read or reference web content without the noise, or feed articles into other tools that need clean text input. The fallback method is less reliable but means it works out of the box.

Install to Claude Code

npx -y skills add dedalus-erp-pas/foundation-skills --skill article-extractor --agent claude-code