What problem does it solve? AI-generated website design references often collapse into repetitive, generic layouts—default left-text/right-image heroes, purple-blue gradients, and cloned card sections. This Skill enforces disciplined art direction so generated frontend design images look premium, varied, and directly implementable by developers or coding models. ## Core Features & Use Cases - Per-Section Image Output: Generates one separate horizontal image for every page section (hero, trust bar, features, pricing, CTA), never collapsing multiple sections into a single frame. - Combinatorial Variation Engine: Selects theme paradigm, typography character, hero architecture, section anchors, background modes, and CTA styles to avoid repetitive AI-looking layouts. - Brand Consistency Enforcement: Maintains one palette, type scale, CTA family, and image treatment across all per-section frames so the full page reads as a single site. - Use Case: Ask for an 8-section SaaS landing page and receive 8 labeled horizontal design comps—hero through CTA—that a developer can directly recreate in code. ## Quick Start Generate an 8-section landing page design for a premium SaaS product, one horizontal image per section.