frontend-design

Guides creation of distinctive web UI designs with deliberate typography, color, and layout choices.

Updated Mar 4, 2026
One-click install
npx skills add https://github.com/gmolike/Claude-Template --skill frontend-design-gmolike
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: frontend-design
Source: https://github.com/gmolike/Claude-Template/tree/main/.agents/skills/frontend-design
Command: npx skills add https://github.com/gmolike/Claude-Template --skill frontend-design-gmolike

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve? AI-generated web designs tend to cluster around generic, templated looks that lack a distinctive visual identity. This Skill provides structured design guidance so new or reshaped UI feels intentional, subject-specific, and memorable rather than like a default template. ## Core Features & Use Cases - Design Direction Process: Brainstorm a compact token system covering color, typography, layout, and a signature element, then critique it against the brief before writing code. - In-Depth Reference Guides: Six reference documents cover color and contrast (OKLCH, WCAG), typography (pairing, fluid type, OpenType), motion design (durations, easing, reduced motion), interaction design (states, focus, modals), responsive design (breakpoints, safe areas), spatial design (spacing, hierarchy), and UX writing (buttons, errors, empty states). - Use Case: When asked to build a landing page for a new product, use this Skill to define a bespoke palette and type pairing grounded in the product's subject, plan a signature hero moment, and implement it with accessible, responsive CSS. ## Quick Start Ask the AI to design a landing page for your product using the frontend-design skill, providing a short brief about the subject and audience.

Frequently Asked Questions about frontend-design

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

FAQPage Schema
How do I make AI-generated web designs look less generic?

Ground every choice in the subject's own world: define a named color palette in OKLCH, pair a characterful display face with a complementary body face, and commit to one signature element. Critique the plan against common defaults before writing any code.

What is the process this design guidance follows?

It works in two passes: first brainstorm a compact token system covering color, type, layout, and a signature element, then review that plan against the brief for generic choices. Only after revising does implementation begin, deriving every color and type decision from the plan.

Does the guidance cover accessibility requirements like contrast and reduced motion?

Yes. The references specify WCAG contrast ratios (4.5:1 for body text, 3:1 for large text and UI components), visible focus rings via :focus-visible, and prefers-reduced-motion alternatives for animations. It also warns against pure black, pure gray, and color-only information encoding.

Which CSS color space does it recommend and why?

It recommends OKLCH over HSL because OKLCH is perceptually uniform, so equal lightness steps look equal across hues. It also advises reducing chroma at extreme lightness and tinting neutrals slightly with the brand hue for cohesion.

What are the limitations of this design guidance?

It provides principles and reference material rather than executable code or component libraries, so results depend on the implementing model's judgment. It also explicitly defers to the user's brief whenever the brief pins down a visual direction, including directions it otherwise flags as defaults.