imagegen-frontend-web

Generates per-section horizontal website design reference images with consistent art direction.

Updated Jun 11, 2026
One-click install
npx skills add https://github.com/dylinmat/design-skills-plugin --skill imagegen-frontend-web-dylinmat
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: imagegen-frontend-web
Source: https://github.com/dylinmat/design-skills-plugin/tree/main/plugins/design/skills/imagegen-frontend-web
Command: npx skills add https://github.com/dylinmat/design-skills-plugin --skill imagegen-frontend-web-dylinmat

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated website design references often collapse into repetitive defaults like left-text/right-image heroes, purple-blue gradients, and single tall page slices that developers cannot accurately implement. This Skill enforces disciplined art direction so every generated image is a buildable, premium frontend design comp. ## Core Features & Use Cases - One Image Per Section: Generates a separate horizontal image for every page section (hero, features, pricing, CTA), never collapsing multiple sections into one frame. - Combinatorial Variation Engine: Selects theme paradigm, typography character, hero architecture, section anchors, and background modes to avoid generic AI-looking layouts. - Multi-Image Consistency: Enforces one palette, type scale, CTA family, and image treatment across all section frames so they read as a single brand. - Use Case: Ask for a landing page for a premium SaaS product and receive 6-8 labeled horizontal section images (hero, trust bar, features, showcase, testimonials, pricing, CTA) that a developer or coding model can directly recreate. ## Quick Start Generate a landing page design for a minimalist fintech product with one horizontal image per section.

Frequently Asked Questions about imagegen-frontend-web

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate website design references with AI image generation?

Describe the site type, brand mood, and section count in your prompt. The skill produces one horizontal image per section with controlled typography, palette, and layout so each frame can be directly implemented as frontend code.

How many images are generated for a landing page?

One image per section, always. A landing page request defaults to 6 sections producing 6 images, a full website defaults to 8, and explicit section counts are matched exactly, with each image labeled by section name.

Can the generated design images be converted to code?

Yes. Each image is generated as an implementation-clear frontend reference showing layout, hierarchy, spacing, typography scale, and component styling, so a developer or coding model can accurately recreate the design.

How does it avoid generic AI-looking website designs?

It uses a combinatorial variation engine that picks distinct theme paradigms, hero architectures, section anchors, and background modes, while banning patterns like purple-blue gradients, cloned card rows, and default left-text/right-image heroes.

Does it keep branding consistent across multiple section images?

Yes. All per-section frames share one palette, typography family, CTA identity, border radius language, and image treatment, so the full set reads as a single cohesive brand when viewed together.