ce-frontend-design

Builds frontend interfaces with design planning, context detection, and visual verification.

Updated Mar 17, 2026
One-click install
npx skills add https://github.com/Norfolk-Group/marcela-norfolk-ai --skill ce-frontend-design-norfolk-group
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ce-frontend-design
Source: https://github.com/Norfolk-Group/marcela-norfolk-ai/tree/main/skills/compound-engineering/skills/ce-frontend-design
Command: npx skills add https://github.com/Norfolk-Group/marcela-norfolk-ai --skill ce-frontend-design-norfolk-group

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI-generated frontend code often looks generic and ignores existing design systems. This Skill guides the creation of distinctive web interfaces by detecting existing design patterns, planning the visual direction before coding, and verifying results with screenshots. ## Core Features & Use Cases - Context Detection: Scans the codebase for design tokens, component libraries, CSS frameworks, and animation libraries to decide whether to follow existing patterns or apply fresh design guidance. - Structured Design Workflow: Covers pre-build planning (visual thesis, content plan, interaction plan), typography, color, composition, motion, accessibility, and copy rules across landing pages, dashboards, and components. - Visual Verification: Takes screenshots via Playwright, browser MCP tools, or agent-browser to confirm the output matches the intended design before declaring done. - Use Case: Ask for a new landing page for your product; the Skill plans a bold aesthetic direction, builds it with intentional typography and motion, then screenshots the result to catch layout or contrast issues. ## Quick Start Build a landing page for my product with a distinctive editorial design and verify it with a screenshot.

Frequently Asked Questions about ce-frontend-design

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

FAQPage Schema
How do I build a landing page that does not look like generic AI output?

Start with a visual thesis defining mood and typography, then follow a hero-support-detail-CTA section structure with one dominant visual. Commit to a distinctive font pairing and cohesive color palette, and verify the result with a screenshot before finishing.

How to add a new component that matches an existing design system?

Scan the codebase for design tokens, component libraries, and CSS frameworks first, then inherit the existing spacing scale, border radius, color tokens, and typography. Focus on interaction quality with clear hover, active, disabled, loading, and error states.

Does this frontend design approach work with Tailwind or shadcn/ui projects?

Yes. When Tailwind config, shadcn/ui, or similar component libraries are detected, the workflow defers to those established patterns for typography and color. Structural guidance on composition, copy, accessibility, and verification still applies.

Which animation library should I use for frontend motion design?

Use the animation library already present in the project. Otherwise the defaults are CSS animations as a baseline, Framer Motion for React, Vue Transition or Motion One for Vue, and Svelte transitions for Svelte.

How do I visually verify frontend code without browser tools installed?

Prefer existing project tooling like Playwright or Cypress, then browser MCP tools, then the agent-browser CLI. If none are available, apply the built-in litmus checks as a self-review and note that visual verification was skipped.