What problem does it solve? AI image generation for website design tends to collapse into repetitive defaults: a single tall page slice, left-text/right-image heroes, purple-blue gradients, and generic card grids. This Skill enforces disciplined art direction so generated images look like premium, codeable frontend design comps instead of AI slop. ## Core Features & Use Cases - One image per section: Generates a separate horizontal image for every page section (hero, features, pricing, CTA), never collapsing the page into one tall frame. - Combinatorial variation engine: Picks theme paradigm, typography character, hero architecture, section anchors, background modes, and CTA styles per section while keeping one consistent palette and brand world across all images. - Anti-slop and clarity rules: Bans generic copy, AI gradient clichés, and over-dense layouts, and runs a 21-point checklist so a developer or coding model can implement the design from the images. - Use Case: Ask for a landing page for a SaaS product and receive 6 labeled section images (hero, trust bar, features, showcase, testimonials, CTA) that share one design system and can be handed directly to a developer. ## Quick Start Generate a premium landing page design for a fintech SaaS product, one horizontal image per section.
