What problem does it solve? Manual exploratory QA of web applications is slow and inconsistent, and bugs often go undocumented without screenshots, reproduction steps, or severity classification. This Skill systematizes browser-based testing so every issue is captured with evidence and reported in a consistent format. ## Core Features & Use Cases - Five-phase QA workflow: Plan, Explore, Collect Evidence, Categorize, and Report, using browser tools like navigate, snapshot, click, type, vision, and console inspection. - Structured issue taxonomy: Classifies findings by severity (Critical/High/Medium/Low) and category (Functional, Visual, Accessibility, Console, UX, Content) with deduplication. - Evidence-backed reporting: Generates a Markdown report with an executive summary, per-issue sections, screenshot references, console errors, and a summary table. - Use Case: Point it at a staging URL before a release; it navigates key flows, tests forms with valid and invalid inputs, captures JavaScript console errors, and produces a prioritized bug report. ## Quick Start Ask the agent to dogfood-test your web app at a given URL with a defined scope and save the bug report and screenshots to an output directory.
