What problem does it solve? Manually clicking through a web app to find bugs is slow and easy to skip before shipping. This Skill automates end-to-end QA: it browses your app like a real user, catalogs every issue by severity, fixes the bugs in source code with atomic commits, and re-verifies each fix with before/after evidence. ## Core Features & Use Cases - Automated exploratory testing: Visits pages, clicks every interactive element, fills and submits forms, checks console errors, links, visual layout, performance, and accessibility. - Test-fix-verify loop: Fixes bugs directly in source code with one atomic commit per fix, then re-tests to confirm the fix works, with screenshot evidence. - Tiered depth and reporting: Quick (critical/high), Standard (+ medium), or Exhaustive (+ cosmetic) tiers, producing a structured report with health scores, ship-readiness summary, and regression comparison against baselines. - Use Case: You just finished a feature branch and ask "does this work?" The Skill enters diff-aware mode, tests only what changed, fixes two broken form validations, and hands you a report showing the health score went from 72 to 96. ## Quick Start Ask the assistant to QA test your running app at localhost:3000 and fix any bugs it finds.
