What problem does it solve? Design reviews are often subjective and inconsistent, missing usability issues, AI-generated design tells, and accessibility failures. This Skill provides a structured, repeatable UX evaluation process that combines expert-style design review with deterministic automated detection. ## Core Features & Use Cases - Dual Independent Assessments: Runs an LLM design review and an automated detector (via npx impeccable) separately to avoid bias, then synthesizes findings into one report. - Quantitative Scoring: Scores all 10 Nielsen heuristics on a 0-4 scale with a total Design Health Score and P0-P3 severity tagging for each issue. - Persona-Based Testing: Walks the interface through relevant user archetypes (power user, first-timer, accessibility-dependent, stress tester, mobile user) to surface specific red flags. - Use Case: After building a new dashboard page, run a critique to get a heuristic score table, AI-slop verdict, cognitive load assessment, and a prioritized list of fixes mapped to follow-up commands like /polish or /layout. ## Quick Start Ask the AI to critique the design of a specific page or component, for example: "Critique the main dashboard page and give me a prioritized list of design fixes."
