What problem does it solve? Design reviews are often subjective and inconsistent, missing AI-generated design tells, cognitive overload, and accessibility failures. This Skill provides a structured, repeatable UX evaluation combining expert design review with deterministic automated detection. ## Core Features & Use Cases - Dual Independent Assessments: Runs an LLM design review and a deterministic CLI/browser-based detector separately to avoid bias, then synthesizes findings into one report. - Quantitative Scoring: Scores all 10 Nielsen heuristics (0-4 each, 40 total) with rating bands, plus an 8-item cognitive load checklist and P0-P3 severity tagging for every issue. - Persona-Based Testing: Walks the primary user flow as 2-3 relevant personas (power user, first-timer, accessibility-dependent, stress tester, mobile user) and reports concrete red flags. - Use Case: After building a new dashboard page, run the critique to get a Design Health Score, a list of prioritized issues with suggested fix commands, and visual overlays highlighting problems directly in the browser. ## Quick Start Ask the AI to critique the current page or component, for example: review the checkout flow and give me a design critique with scores and prioritized fixes.
