frontend-design

jwynia/agent-skills · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/jwynia/agent-skills --skill frontend-design
0 commentsdiscussion
summary

Analyze existing designs and generate production-grade design systems with intentional aesthetics.

  • Three operational modes: analyze CSS for patterns and tokens, specify design requirements in JSON, and generate color palettes, typography systems, design tokens, and framework components
  • Supports React, Vue, Svelte, and vanilla HTML with multiple styling approaches (Tailwind, CSS modules, styled-components, scoped CSS)
  • Includes accessibility auditing (contrast ratios, focus states, tou
skill.md

Frontend Design

Create distinctive, production-grade frontend interfaces that avoid generic "AI slop" aesthetics. This skill combines design philosophy guidance with practical TypeScript tooling for analyzing existing designs and generating design system artifacts.

Core Principle: Choose a clear aesthetic direction and execute it with precision. Bold maximalism and refined minimalism both work - the key is intentionality, not intensity.

When to Use This Skill

Use when:

  • Building web components, pages, or applications
  • Auditing existing CSS for design inconsistencies
  • Extracting design tokens from legacy codebases
  • Generating color palettes and typography systems
  • Creating component templates across frameworks
  • Checking accessibility compliance for design elements

Don't use when:

  • Simple text content changes
  • Backend-only work
  • Non-visual functionality

Prerequisites

  • Deno runtime (for script execution)
  • Optional: Existing CSS/design files for analysis
  • Optional: Design tokens file for reference

Quick Start

This skill operates in three modes:

1. Analyze Mode

Audit existing styles, extract tokens, check accessibility.

# Audit CSS for design patterns and inconsistencies
deno run --allow-read scripts/analyze-styles.ts styles.css

# Extract design tokens from existing CSS
deno run --allow-read scripts/extract-tokens.ts ./src --format css

# Check accessibility (contrast, focus states)
deno run --allow-read scripts/analyze-accessibility.ts component.tsx

2. Specify Mode

Create JSON specifications defining what to generate. See assets/ for schema examples.

3. Generate Mode

Create palettes, typography systems, tokens, and components.

# Generate a color palette
deno run --allow-read --allow-write scripts/generate-palette.ts --seed "#2563eb" --theme warm

# Generate typography system
deno run --allow-read --allow-write scripts/generate-typography.ts --display "Playfair Display" --body "Source Sans Pro"

# Generate design tokens file
deno run --allow-read --allow-write scripts/generate-tokens.ts tokens-spec.json ./output/

# Generate a component
deno run --allow-read --allow-write scripts/generate-component.ts --name Button --framework react --styling tailwind

Instructions

Phase 1: Analysis (Optional but Recommended)

Before creating new designs, audit existing code to understand current patterns.

1a. Style Analysis

Analyze CSS files to identify colors, typography, spacing, and inconsistencies:

deno run --allow-read scripts/analyze-styles.ts <input> [options]

Options:
  --tokens <file>    Compare against existing design tokens
  --pretty           Pretty-print JSON output
  --format <type>    Output format: json (default), summary

Output includes:

  • Color usage inventory with hex normalization
  • Typography patterns (fonts, sizes, weights)
  • Spacing value distribution
  • Inconsistencies and recommendations

1b. Token Extraction

Extract design tokens from CSS files into standardized formats:

deno run --allow-read scripts/extract-tokens.ts <input> [options]

Options:
  --format <type>    Output: css, scss, tailwind, style-dictionary, tokens-studio
  --output-css       Also output CSS variables file

1c. Accessibility Audit

Check design-related accessibility issues:

deno run --allow-read scripts/analyze-accessibility.ts <input> [options]

Options:
  --format <type>    Output: json, summary
  --level <AA|AAA>   WCAG conformance level (default: AA)

Checks include:

  • Color contrast ratios
  • Focus indicator presence
  • Touch target sizes
  • Motion preference respect

Phase 2: Generation

2a. Color Palette Generation

Generate cohesive color palettes from seed colors or themes:

deno run --allow-read --allow-write scripts/generate-palette.ts [options] <output>

Options:
  --seed <color>     Primary seed color (hex)
  --theme <type>     warm, cool, neutral, vibrant, muted, dark, light
  --style <type>     minimalist, bold, organic, corporate, playful
  --shades           Generate 50-950 shade scale
  --semantic         Generate success/warning/error colors
  --contrast <lvl>   Target contrast: AA (default), AAA
  --format <type>    css, scss, tailwind, tokens, json

Example specification (palette-spec.json):

{
  "seedColors": {
    "primary": "#2563eb",
    "accent": "#f59e0b"
  },
  "theme": "cool",
  "generateShades": true,
  "generateSemantics": true,
  "contrastTarget": "AA",
  "outputFormat": "css"
}

2b. Typography System Generation

Generate typography systems with font stacks and scales:

deno run --allow-read --allow-write scripts/generate-typography.ts [options] <output>

Options:
  --display <font>   Display/heading font family
  --body <font>      Body text font family
  --mono <font>      Monospace font family
  --scale <type>     minor-second, major-second, minor-third, major-third, perfect-fourth, golden-ratio
  --base <px>        Base font size (default: 16)
  --line-height      tight, normal, relaxed
  --responsive       Generate responsive breakpoints
  --format <type>    css, scss, tailwind, tokens

Type scales:

Scale Ratio Character
minor-second 1.067 Subtle, conservative
major-second 1.125 Balanced, professional
minor-third 1.200 Clear hierarchy
major-third 1.250 Strong presence
perfect-fourth 1.333 Bold, impactful
golden-ratio 1.618 Dramatic, artistic

2c. Design Token Generation

Generate comprehensive design token files in multiple formats:

deno run --allow-read --allow-write scripts/generate-tokens.ts <spec> <output-dir>

Specification structure:

{
  "name": "my-design-system",
  "tokens": {
    "color": { "primary": "#2563eb", "secondary": "#64748b" },
    "spacing": { "xs": "0.25rem", "sm": "0.5rem", "md": "1rem" },
    "typography": {
      "fontFamilies": { "display": "Playfair Display", "body": "Inter" },
      "fontSizes": { "sm": "0.875rem", "base": "1rem", "lg": "1.125rem" }
    },
    "shadow": { "sm": "0 1px 2px rgba(0,0,0,0.05)" },
    "border": { "radius": { "sm": "0.25rem", "md": "0.5rem" } },
    "animation": { "duration": { "fast": "150ms", "normal": "300ms" } }
  },
  "outputFormats": ["css", "scss", "tailwind", "ts"]
}

2d. Component Generation

Generate component templates with design-focused styling:

deno run --allow-read --allow-write scripts/generate-component.ts [options] <output-dir>

Options:
  --name <name>      Component name (required)
  --type <type>      button, card, input, modal, navigation, hero, custom
  --framework <fw>   react, vue, svelte, html
  --styling <type>   css, tailwind, css-modules, styled-components, emotion
  --aesthetic <type> minimal, bold, organic, brutalist, glassmorphism, neumorphism
  --animation <lvl>  none, subtle, expressive
  --dark-mode        Include dark mode support
  --tokens <file>    Use design tokens file

Framework output examples:

React with Tailwind:

export function Button({ variant = 'primary', children }: ButtonProps) {
  return (
    <button className="px-4 py-2 rounded-lg font-medium transition-all">
how to use frontend-design

How to use frontend-design on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add frontend-design
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/jwynia/agent-skills --skill frontend-design

The skills CLI fetches frontend-design from GitHub repository jwynia/agent-skills and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/frontend-design

Reload or restart Cursor to activate frontend-design. Access the skill through slash commands (e.g., /frontend-design) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

Task Automation & Efficiency

Automate repetitive workflows and reduce manual effort

Example

Generate reports, summarize documents, draft communications

Save 3-5 hours per week on routine tasks

Knowledge Enhancement

Learn new skills, understand complex topics, get expert guidance

Example

Explain concepts, provide examples, suggest learning resources

Accelerate learning and skill development by 2x

Quality Improvement

Enhance output quality through reviews, suggestions, and refinements

Example

Review drafts, suggest improvements, catch errors

Improve work quality by 30-40% with less effort

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client with skill support
  • Clear understanding of task or problem to solve
  • Willingness to iterate and refine outputs

Time Estimate

15-45 minutes depending on use case complexity

Installation Steps

  1. 1.Install skill using provided installation command
  2. 2.Test with simple use case relevant to your work
  3. 3.Evaluate output quality and relevance
  4. 4.Iterate on prompts to improve results
  5. 5.Integrate into regular workflow if valuable

Common Pitfalls

  • Expecting perfect results without iteration
  • Not providing enough context in prompts
  • Using skill for tasks outside its intended scope
  • Accepting outputs without review and validation

Best Practices

✓ Do

  • +Start with clear, specific prompts
  • +Provide relevant context and constraints
  • +Review and refine all outputs before using
  • +Iterate to improve output quality
  • +Document successful prompt patterns

✗ Don't

  • Don't use without understanding skill limitations
  • Don't skip validation of outputs
  • Don't share sensitive information in prompts
  • Don't expect skill to replace human judgment

💡 Pro Tips

  • Be specific about desired format and style
  • Ask for multiple options to choose from
  • Request explanations to understand reasoning
  • Combine AI efficiency with human expertise

When to Use This

✓ Use When

Use when skill capabilities match your task, clear ROI on time saved, and you can validate outputs. Best for repetitive tasks, learning, and quality improvement.

✗ Avoid When

Avoid when task requires deep expertise you can't validate, involves sensitive decisions, or when learning process is more valuable than speed of completion.

Learning Path

  1. 1Familiarize yourself with skill capabilities and limitations
  2. 2Start with low-risk, non-critical tasks
  3. 3Progress to more complex and valuable use cases
  4. 4Build expertise through regular use and experimentation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.635 reviews
  • James Khanna· Dec 24, 2024

    Solid pick for teams standardizing on skills: frontend-design is focused, and the summary matches what you get after install.

  • Shikha Mishra· Dec 12, 2024

    Registry listing for frontend-design matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Ganesh Mohane· Dec 8, 2024

    frontend-design has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Harper Johnson· Dec 4, 2024

    frontend-design reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Daniel Ramirez· Nov 23, 2024

    Registry listing for frontend-design matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Kiara Martin· Nov 19, 2024

    Useful defaults in frontend-design — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Harper Smith· Nov 15, 2024

    frontend-design is among the better-maintained entries we tried; worth keeping pinned for repeat workflows.

  • Yash Thakker· Nov 3, 2024

    frontend-design reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Dhruvi Jain· Oct 22, 2024

    I recommend frontend-design for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Olivia Bansal· Oct 14, 2024

    Keeps context tight: frontend-design is the kind of skill you can hand to a new teammate without a long onboarding doc.

showing 1-10 of 35

1 / 4