jrajasekera/claude-skills

Overview

This skill extracts clean article content from a webpage URL and saves it as a markdown file with frontmatter. It removes ads, navigation, and clutter so you get a reader-friendly version for offline reading, archiving, or publishing. The tool supports fallback extractors and Wayback Machine retrieval for dead or paywalled links.

How this skill works

Give the script a URL and it fetches the page, runs content-extraction tools, cleans HTML, and writes a markdown file with frontmatter. You must call the extraction script directly with the URL; the script handles fetching, extraction, and saving. It supports forcing a specific extractor, quiet mode, and an option to try the Wayback Machine when the original fails.

When to use it

• Save a blog post, news article, or tutorial for offline reading
• Archive a webpage or capture content before it changes
• Extract documentation or long-form content for notes or publication
• Grab content from pages behind mild paywalls using Wayback fallback
• Prepare clean markdown for static sites or content pipelines

Best practices

• Call the provided extraction script directly with the URL; do not prefetch the page with other tools
• Set an explicit output path (-o and -d) to keep files organized
• If extraction fails, try --wayback or change the extractor (-t) before troubleshooting networking
• Make the script executable (chmod +x) and install optional local tools for best reliability
• Use quiet mode (-q) in scripts or cron jobs to reduce logs

Example use cases

• Download a news article and save as my-article.md for research notes
• Archive an important tutorial before it’s updated or removed using --wayback
• Extract multiple blog posts into a content folder for reuse in a static site generator
• Clip long-form interviews or op-eds for offline reading on a mobile device
• Automate weekly saves of documentation pages for team knowledge backups