Pulls the actual article text from blog posts and news sites while stripping out all the navigation bars, ads, newsletter popups, and related content sidebars. Uses Mozilla's Readability or trafilatura under the hood, with a basic HTML parser as fallback if neither is installed. The skill handles title extraction and creates clean filenames automatically, which is nice when you're archiving a bunch of articles. Works best on standard blog formats and news sites, though it'll hit a wall on anything behind a paywall or heavy JavaScript rendering. Honestly most useful when you need to save reference material in a readable format or want to feed article content into another tool without the cruft.
npx skills add https://github.com/michalparkola/tapestry-skills-for-claude-code --skill article-extractor