What problem does it solve? Manually clicking through a web app to find bugs is slow and easy to skip before shipping. This Skill systematically QA tests a web application like a real user, then fixes the bugs it finds in source code with atomic commits and re-verifies each fix. ## Core Features & Use Cases - Test → Fix → Verify loop: Explores pages, clicks every interactive element, checks console errors, then fixes found bugs with one commit per fix and re-tests. - Diff-aware mode: On a feature branch with no URL, it analyzes the branch diff, identifies affected pages/routes, and scopes testing to what changed. - Tiered severity: Quick (critical/high), Standard (+ medium), or Exhaustive (+ cosmetic) tiers control which issues get fixed, with before/after health scores and a ship-readiness report. - Test framework bootstrap: Detects missing test infrastructure, installs an appropriate framework, writes regression tests, and sets up CI. - Use Case: You just finished a feature branch and ask "qa this" — it detects your local dev server, tests the pages your branch touched, fixes a broken form validation, commits the fix, and produces a report with before/after screenshots. ## Quick Start Ask the AI to QA test the current feature branch and fix any bugs it finds, or provide a URL such as http://localhost:3000 to test a running app.