Pulls a URL's raw content into a local file so Claude reads the authoritative source instead of WebFetch's summary. Use when the user wants docs, a page, or an API reference grounded in what the source actually says — not what a small-model pass thinks the page says. Works on any http/https URL; optional HTML→markdown conversion.
$npx -y skills add jtsternberg/claude-plugins --skill fetch-docsInstalls into the current project.
Run `npx skills use "https://github.com/jtsternberg/claude-plugins" --skill "jtsternberg/claude-plugins/fetch-docs"` 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/jtsternberg/claude-plugins" that are relevant to the current task. Run `npx skills add "https://github.com/jtsternberg/claude-plugins"` and select the relevant skills, then follow their instructions.