What problem does it solve? Manually clicking through a web app to find bugs is slow and inconsistent, and bugs found often go unfixed or unverified. This Skill systematically QA tests a web application like a real user, fixes the bugs it finds in source code with atomic commits, and re-verifies each fix with before/after evidence. ## Core Features & Use Cases - Test → Fix → Verify Loop: Explores pages, clicks every interactive element, fills forms, checks console errors, then fixes confirmed bugs and re-tests them. - Three Severity Tiers: Quick (critical/high only), Standard (+ medium), and Exhaustive (+ low/cosmetic), with before/after health scores and a ship-readiness summary. - Diff-Aware Mode: On a feature branch with no URL, automatically scopes testing to pages and routes affected by the branch's changes. - Test Framework Bootstrap: Detects the project runtime, installs a test framework if missing, writes regression tests, and sets up CI. - Use Case: After shipping a new checkout flow on a feature branch, run /qa to have the branch's affected pages exercised end-to-end, bugs fixed with atomic commits, and a structured report with screenshots produced. ## Quick Start Ask the AI to QA test the current feature branch and fix any bugs it finds.