Catalog
affaan-m/design-system

affaan-m

design-system

Generate a design system from an existing codebase or audit one for visual consistency: extract tokens (colors, typography, spacing, shadows) into design-tokens.json and CSS custom properties with DESIGN.md rationale and an interactive HTML preview, score the UI across 10 dimensions, and flag AI-slop patterns. Use when starting a design system, auditing visual consistency before a redesign, or reviewing a PR that touches styling.

NewUpdated Sep 27, 2026

Design System — Generate & Audit Visual Systems

When to Use

  • Starting a new project that needs a design system
  • Auditing an existing codebase for visual consistency
  • Before a redesign — understand what you have
  • When the UI looks "off" but you can't pinpoint why
  • Reviewing PRs that touch styling

How It Works

Mode 1: Generate Design System

Analyzes your codebase and generates a cohesive design system:

1. Scan CSS/Tailwind/styled-components for existing patterns
2. Extract: colors, typography, spacing, border-radius, shadows, breakpoints
3. Research 3 competitor sites for inspiration (via browser MCP)
4. Propose a design token set (JSON + CSS custom properties)
5. Generate DESIGN.md with rationale for each decision
6. Create an interactive HTML preview page (self-contained, no deps)

Output: DESIGN.md + design-tokens.json + design-preview.html

Mode 2: Visual Audit

Scores your UI across 10 dimensions (0-10 each):

1. Color consistency — are you using your palette or random hex values?
2. Typography hierarchy — clear h1 > h2 > h3 > body > caption?
3. Spacing rhythm — consistent scale (4px/8px/16px) or arbitrary?
4. Component consistency — do similar elements look similar?
5. Responsive behavior — fluid or broken at breakpoints?
6. Dark mode — complete or half-done?
7. Animation — purposeful or gratuitous?
8. Accessibility — contrast ratios, focus states, touch targets
9. Information density — cluttered or clean?
10. Polish — hover states, transitions, loading states, empty states

Each dimension gets a score, specific examples, and a fix with exact file:line.

Mode 3: AI Slop Detection

Identifies generic AI-generated design patterns:

- Gratuitous gradients on everything
- Purple-to-blue defaults
- "Glass morphism" cards with no purpose
- Rounded corners on things that shouldn't be rounded
- Excessive animations on scroll
- Generic hero with centered text over stock gradient
- Sans-serif font stack with no personality

Examples

Generate for a SaaS app:

/design-system generate --style minimal --palette earth-tones

Audit existing UI:

/design-system audit --url http://localhost:3000 --pages / /pricing /docs

Check for AI slop:

/design-system slop-check
Files1
1 files · 1.0 KB

Select a file to preview

Overall Score

68/100

Grade

C

Adequate

Grades are signals, not a certification. Always review a skill yourself before use.

Safety

72

Quality

62

Clarity

78

Completeness

58

Summary

This skill guides agents to generate design systems from existing codebases, audit visual consistency, and detect AI-generated design patterns. It extracts design tokens (colors, typography, spacing) into JSON and CSS custom properties, generates documentation with rationale, creates interactive previews, and scores UIs across 10 dimensions with specific improvement recommendations.

Detected Capabilities

file read (CSS, styled-components, Tailwind config)HTML file generation (preview)JSON file generation (design-tokens)Markdown file generation (DESIGN.md)local browser access (localhost)codebase analysis (patterns, tokens)

Trigger Keywords

Phrases that agents use to match this skill to user intent.

design system generationvisual consistency auditextract design tokensai design patternsui inventory

Risk Signals

INFO

Skill references browser MCP and localhost for inspecting UI

Mode 1, step 2-3
WARNING

No file write scope restrictions documented — could write to any project directory

Output section
INFO

Skill performs analysis only; no destructive operations, credential access, or privilege escalation

Overall content

Referenced Domains

External domains referenced in skill content, detected by static analysis.

localhost

Use Cases

  • Starting a new project that needs a design system from scratch
  • Auditing an existing codebase for visual consistency violations
  • Understanding current design patterns before undertaking a redesign
  • Reviewing style-related PRs for consistency with established tokens
  • Detecting common AI-generated design anti-patterns in a codebase

Quality Notes

  • Skill provides three distinct, well-separated modes with clear intent for each
  • Examples are concrete and actionable with plausible CLI syntax
  • Audit scoring matrix (10 dimensions with 0-10 scale) is detailed and measurable
  • AI slop detection patterns are specific and recognizable (gradient abuse, purple-blue defaults, etc.)
  • Missing: implementation details for how tokens are extracted from different CSS formats (vanilla CSS vs Tailwind vs styled-components require different parsing)
  • Missing: how the skill handles ambiguous token values or conflict resolution when multiple values exist
  • Missing: sample output showing what DESIGN.md, design-tokens.json, and design-preview.html actually look like
  • Missing: error handling guidance (e.g., what if codebase has no CSS, or CSS is heavily obfuscated?)
  • Missing: scope boundaries for file writes — should limit to /design-system/, .github/, or project root only
  • Missing: guidance on what constitutes 'acceptable' scores per dimension or how to prioritize fixes
Model: claude-haiku-4-5-20251001Analyzed: Sep 27, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

  1. v3.0

    Contract changed: description

    ✦ AIScope narrowed from general design-system work to token extraction and UI scoring with specific artifact outputs and detection of AI-generated patterns.

    triggering2026-09-27

    LATEST
  2. v2.0

    Contract changed: description

    ✦ AISkill activation description expanded to clarify use cases (design system generation, visual consistency, styling PRs).

    triggering2026-09-09

    View This Version
  3. v1.2

    Content updated

    ✦ AINo behavioral changes detected.

    2026-07-14

    View This Version
  4. v1.1

    Content updated

    ✦ AIAdds LICENSE file.

    2026-04-20

    View This Version
  5. v1.0

    2026-04-12

    View This VersionInitial version

Use affaan-m/design-system in your dev environment

Command Palette

Search for a command to run...