What problem does it solve? Verifying that a web application actually works after shipping code requires tedious manual clicking, form filling, and console checking. This Skill automates report-only QA testing: it drives a real browser through your app, captures screenshots and console errors, and produces a structured report with a health score and repro steps — while never modifying any code. ## Core Features & Use Cases - Diff-aware testing: On a feature branch with no URL given, it analyzes the git diff, identifies affected pages and routes, detects the running local app, and tests exactly what changed. - Multiple modes: Full systematic exploration, 30-second quick smoke tests, and regression mode that diffs results against a saved baseline.json. - Evidence-based reporting: Every issue gets annotated screenshots, repro steps, severity classification, and a weighted health score across console, links, visual, functional, UX, performance, content, and accessibility categories. - Use Case: You just pushed a branch changing the checkout flow. Run the skill and it finds your local dev server, walks the checkout end-to-end, screenshots a broken submit button, and hands you a report — without touching your code. ## Quick Start Ask the AI to run report-only QA on your current feature branch or a specific URL such as http://localhost:3000 and produce a bug report without fixing anything.
