web-fetch
Fetch a URL, write the body to $TMPDIR/web-fetch-<runid>/, print the path. Pipe the path through rg / jq / awk to surgically extract what you need.
Why this skill exists
The built-in webfetch tool dumps the whole rendered page into the conversation. For anything bigger than a few KB that drowns the context window. The fix is dead simple: write the page to disk, then grep it.
That is all this skill does. One curl call, one Cloudflare-aware retry, HTML → Markdown v
[Description truncada. Veja o README completo no GitHub.]