design-taste-frontend

Generates anti-generic frontend code for landing pages, portfolios, and redesigns using configurable design dials.

Updated Jul 10, 2026
One-click install
npx skills add https://github.com/AvaTar-ArTs/.Agent-skills --skill design-taste-frontend-avatar-arts
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: design-taste-frontend
Source: https://github.com/AvaTar-ArTs/.Agent-skills/tree/main/skills/taste-skill
Command: npx skills add https://github.com/AvaTar-ArTs/.Agent-skills --skill design-taste-frontend-avatar-arts

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes assets (resource) components.

What problem does it solve? AI coding agents default to templated, generic-looking interfaces: purple gradients, centered heroes, three equal feature cards, and Inter font everywhere. This Skill forces the agent to read the brief first, infer the right design direction, and ship frontend code that does not look machine-generated. ## Core Features & Use Cases - Brief Inference and Design Read: Analyzes page kind, vibe words, references, and audience before writing code, then declares a one-line design direction. - Three Configuration Dials: DESIGN_VARIANCE, MOTION_INTENSITY, and VISUAL_DENSITY control layout experimentation, animation depth, and information density per project. - Design System Mapping: Routes briefs to real design systems (Fluent, Material, Carbon, shadcn/ui, Tailwind v4) instead of hand-rolled imitations, with strict anti-pattern bans on AI clichés. - Use Case: Ask your coding agent to build a SaaS landing page; the Skill produces an asymmetric hero, a locked single-accent palette, real imagery, and a pre-flight audit covering eyebrow restraint, CTA contrast, and layout repetition. ## Quick Start Ask your coding agent to build a landing page for your product and tell it to follow the design-taste-frontend skill rules before writing any code.

Frequently Asked Questions about design-taste-frontend

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

FAQPage Schema
How do I stop AI coding agents from generating generic-looking landing pages?

Load this Skill into your agent so it reads the brief first, declares a design direction, and applies explicit bans on AI defaults like purple gradients, centered heroes, and three equal feature cards. Three dials control variance, motion, and density per project.

How do the DESIGN_VARIANCE, MOTION_INTENSITY, and VISUAL_DENSITY dials work?

Each dial is a 1-10 scale set after the brief inference step. Variance controls layout experimentation, motion controls animation depth, and density controls information per viewport. The baseline is 8/6/4, with lookup tables mapping brief signals like minimalist or playful to specific values.

Does this frontend skill work with React, Vue, and Svelte?

Yes. The rules target design intent rather than a single framework API, though the default stack is React or Next.js with Tailwind v4 and Motion for animation. Real design systems like Fluent, Carbon, or shadcn/ui are used when the brief calls for them.

Can I use this skill to redesign an existing project instead of a new page?

Yes. Redesign briefs trigger an audit-first workflow that treats existing brand assets as starting material. Preserve mode matches current variance and density, while overhaul mode raises both dials by two.

Why does the skill ban Inter font and purple gradients?

Inter and AI-purple gradients are the most common LLM defaults, making outputs instantly recognizable as machine-generated. The skill bans them as defaults but allows them when the brief explicitly requests that aesthetic, executed with intent.

What happens when no image generation tool is available for page assets?

The skill falls back to real photography sources like picsum.photos with descriptive seeds, or leaves clearly labeled placeholder slots and tells the user exactly which images to provide. Hand-rolled SVG illustrations and fake screenshot divs are discouraged.