What problem does it solve? Frontend interfaces often ship with bland visuals, weak hierarchy, accessibility gaps, and inconsistent design systems. This Skill gives an AI agent a structured design-director workflow to plan, build, evaluate, and refine UI so the result is intentional, on-brand, and production-quality. ## Core Features & Use Cases - Command-driven design workflow: 20+ commands such as shape, critique, audit, polish, bolder, quieter, animate, typeset, layout, harden, adapt, and optimize, each with a dedicated reference playbook. - Persistent design context: init captures product strategy in PRODUCT.md and document generates a DESIGN.md visual spec from existing code, keeping all later work on-brand. - Scored evaluation: critique runs dual independent assessments with Nielsen heuristic scoring and persona testing; audit produces a 0-20 technical health score across accessibility, performance, theming, responsive design, and implementation integrity. - Web and native coverage: dedicated references for iOS and Android platform conformance, plus live browser variant iteration via the live and generate commands. - Use Case: Ask the agent to audit a dashboard page; it scores accessibility, performance, theming, and responsiveness, lists P0-P3 issues, and recommends the exact follow-up commands to fix them. ## Quick Start Ask the agent to run the impeccable init command in your project to capture product context, then request a critique or audit of any page or component.