What problem does it solve? Design reviews are often subjective, inconsistent, or miss systematic issues like AI-generated visual clichés and usability heuristic violations. This Skill provides a structured, repeatable design critique process that combines independent expert-style assessment with deterministic automated detection, producing scored, prioritized, and actionable feedback. ## Core Features & Use Cases - Dual Independent Assessments: Runs an LLM design review (visual hierarchy, cognitive load, emotional journey, AI slop detection) alongside a deterministic detector that flags 25 anti-patterns via CLI scan or browser overlay. - Quantitative Scoring: Scores all 10 Nielsen usability heuristics (0-4 each, 40 total) with rating bands, plus P0-P3 severity tagging for every issue found. - Persona-Based Testing: Walks the interface through 2-3 relevant user archetypes (power user, first-timer, accessibility-dependent, stress tester, mobile user) to expose specific failure modes. - Actionable Follow-Up: Ends with targeted clarifying questions and a prioritized action plan mapping each issue to a specific fix command. - Use Case: After building a new landing page, run a critique to get a heuristic scorecard, detect AI-generated design tells, identify persona-specific red flags, and receive a ranked list of fixes. ## Quick Start Ask the assistant to critique the design of a specific page or component, for example: critique the checkout page for usability and visual quality.
