imagegen-frontend-web

Generates one horizontal website design reference image per page section.

Updated Aug 26, 2026
One-click install
npx skills add https://github.com/danieliudi/trackforge-os --skill imagegen-frontend-web-danieliudi
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: imagegen-frontend-web
Source: https://github.com/danieliudi/trackforge-os/tree/main/.cursor/skills/imagegen-frontend-web
Command: npx skills add https://github.com/danieliudi/trackforge-os --skill imagegen-frontend-web-danieliudi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated website design references often collapse into repetitive defaults: a single tall image for the whole page, the same left-text/right-image hero, purple-blue gradients, and layouts no developer can actually build from. This Skill enforces disciplined art direction so every generated image is a premium, codeable frontend design comp. ## Core Features & Use Cases - One image per section: A landing page with 8 sections produces 8 separate horizontal images, never one collapsed tall slice. - Combinatorial variation engine: Picks theme paradigm, typography character, hero architecture, background mode, CTA style, and composition anchors per section while keeping one consistent palette and brand world across all frames. - Anti-AI-slop rules: Bans generic gradients, cloned card rows, fake dashboards, and filler copy so output reads as art-directed design. - Use Case: Ask for a landing page for a SaaS product and receive 6-8 labeled section images (hero, trust bar, features, showcase, testimonials, CTA) that a developer or coding model can directly implement. ## Quick Start Ask the AI to generate a landing page design for your product, specifying the number of sections and brand mood, and receive one horizontal reference 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 reference images with AI?

Describe the site type, brand mood, and section count, and the skill produces one horizontal image per section. A landing page with no count defaults to 6 sections and 6 images, each labeled by section name.

How many images does a landing page request produce?

One image per section, always. An 8-section landing page produces 8 separate horizontal images; ambiguous requests default high, with landing pages producing 6 and full websites producing 8.

Can developers implement designs from these generated images?

Yes. Each image is generated as a frontend reference that clearly communicates layout, hierarchy, spacing, typography scale, CTA priority, and component styling, so a developer or coding model can build from it directly.

How does it avoid generic AI-looking website designs?

It uses a combinatorial variation engine that picks distinct theme paradigms, typography characters, hero architectures, and background modes per section, plus explicit bans on purple-blue gradients, cloned card rows, fake dashboards, and filler copy.

Does it keep branding consistent across multiple section images?

Yes. All per-section frames share one palette, typography family, CTA identity, image treatment, and tonal voice. Only composition anchors, background modes, and section density vary between frames.

When should I not use this image generation approach?

Avoid it when you need actual production code rather than visual references, or when the request is for abstract mood art rather than website design comps. The skill defaults to implementation-friendly frontend references.