Catalog
affaan-m/design-system

affaan-m

design-system

Use this skill to generate or audit design systems, check visual consistency, and review PRs that touch styling.

global
origin:ECC
New~600
v1.2Saved Jul 14, 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

Safety

78

Quality

62

Clarity

75

Completeness

55

Summary

A design system generation and audit skill that analyzes codebases for visual consistency, extracts design tokens, and scores UI across 10 dimensions (color, typography, spacing, etc.). It supports three modes: generating design systems from scratch, auditing existing projects, and detecting AI-generated design patterns. The skill outputs structured reports (DESIGN.md, design-tokens.json) and generates an interactive preview page.

Detected Capabilities

file read (CSS/Tailwind/styled-components analysis)browser interaction (research competitor sites)code analysis (design token extraction)file write (DESIGN.md, design-tokens.json, design-preview.html generation)codebase scanningHTTP requests (localhost design preview)

Trigger Keywords

Phrases that MCP clients use to match this skill to user intent.

design system generationvisual consistency auditui design reviewcomponent style checkdesign token extractionai design pattern detection

Risk Signals

INFO

Browser-based research of competitor websites

Mode 1: Generate Design System, step 3
INFO

HTTP access to localhost design preview

Mode 2 and Mode 3: audit and slop-check examples
INFO

No credentials or sensitive data access documented

Entire skill

Referenced Domains

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

localhost

Use Cases

  • Starting a new project with no established design system
  • Auditing an existing codebase to identify visual consistency issues
  • Evaluating UI before a major redesign
  • Diagnosing why a UI looks visually off or unprofessional
  • Reviewing pull requests that modify styling or component design
  • Identifying and removing generic AI-generated design patterns from a project

Quality Notes

  • Clear three-mode structure (Generate, Audit, AI Slop Detection) makes purpose explicit
  • Audit dimension scoring (10 categories with 0-10 scale) is well-defined and practical
  • Examples provided for each mode show realistic command patterns
  • Output artifacts are well-specified (DESIGN.md, design-tokens.json, design-preview.html)
  • No implementation details for actual analysis logic—skill reads high-level only, missing specifics on: how CSS/Tailwind patterns are extracted, algorithm for token consolidation, methodology for competitor research
  • No error handling documented—what happens if codebase has no CSS? Missing files? Unreadable formats?
  • No scope boundaries stated—does this work on all projects or only specific frameworks/languages?
  • Interactive HTML preview is a nice UX touch but generation constraints not documented (size limits, dependency handling)
  • AI Slop Detection section is brief—pattern descriptions are spot-on but detection logic is vague
Model: claude-haiku-4-5-20251001Analyzed: Jul 14, 2026

Reviews

Add this skill to your library to leave a review.

No reviews yet

Be the first to share your experience.

Version History

v1.2

Content updated

2026-07-14

Latest
v1.1

Content updated

2026-04-20

v1.0

No changelog

2026-04-12

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

Command Palette

Search for a command to run...