toolkit

SuperAudit · Playbook

Remote audit (SuperAudit) — high-level pointers (local fallback)

superaudit-client renders what the remote engine says. The detailed, current standards for using it — when a remote second opinion is worth the call, how to reconcile a SuperAudit finding against a native skill’s own verdict, and when --all (the vertical/CRO categories) is actually appropriate — live in the team wiki (set OUTLINE + OUTLINE_API_URL and the report links them directly). This file is the minimal high-level fallback for when the wiki isn’t configured: direction only, deliberately not step-by-step, so there’s no detailed content to drift out of sync with the wiki.

  • The verdict is the engine’s — treat a FAIL/REVIEW here as a lead to investigate, not an automatic action; the toolkit’s native skills remain the source of truth for their own checks.
  • Neutral by default — keep --all for an actual medical-vertical client; a generic site graded on medical/CRO categories produces noise, not signal.
  • Overlap with native skills — where SuperAudit and a native skill (orbeetle, porygon, axew) cover the same ground, prefer the native skill’s self-contained result; use SuperAudit as a cross-check, not a replacement.
  • Quick wins are optional — treat a missing quick-wins response as expected (it may be gated), not a configuration error.
  • PageSpeed — leave --pagespeed off unless specifically comparing against rapidash; the two measure the same thing from different vantage points and duplicating them wastes a call.
  • Fallback vantage — reach for this client specifically when a local fetch is blocked and a remote-origin request might succeed.

Full playbook → the team wiki’s remote-audit usage standards.