Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page.
$npx -y skills add lvndry/jazz --skill defuddleInstalls into the current project.
Run `npx skills use "https://github.com/lvndry/jazz" --skill "lvndry/jazz/defuddle"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/lvndry/jazz" that are relevant to the current task. Run `npx skills add "https://github.com/lvndry/jazz"` and select the relevant skills, then follow their instructions.