Design Auditor

The agent performs systematic 12-category UI/UX audits, detects AI-generated slop patterns, validates WCAG color contrast, and checks design system token compliance. Produces three independent grades: Design (A-F), AI Slop (A-F), and Accessibility (A-F).

Quick Start

# Score a full design audit (12 categories -> 3 grades)
python scripts/design_scorer.py --input findings.json --output report.json --verbose

# Detect AI-generated slop in HTML/CSS
python scripts/ai_slop_detector.py --input page.html --css styles.css --threshold 0.6

# Check color contrast (single pair or batch)
python scripts/color_contrast_checker.py --fg "#333" --bg "#fff" --level AA
python scripts/color_contrast_checker.py --input color-pairs.json --level AAA --suggest-fixes

# Validate design system token compliance
python scripts/design_system_validator.py --tokens tokens.json --input src/styles/

Tools Overview

design_scorer.py

ai_slop_detector.py

color_contrast_checker.py

design_system_validator.py

All tools support

--format json|text

--output

Workflow 1: Full Design Audit

The agent evaluates 12 weighted categories in five passes:

1. Visual Pass -- Visual Hierarchy (10%), Typography (8%), Color & Contrast (8%), Spacing & Layout (8%)
2. Interaction Pass -- Interaction States (10%), Navigation & IA (8%)
3. Platform Pass -- Responsive Design (8%), Accessibility/WCAG (12%)
4. Polish Pass -- Motion & Animation (5%), Content & Microcopy (5%)
5. Integrity Pass -- AI Slop Indicators (8%), Performance as Design (5%), Coherence Bonus (5%)

python scripts/design_scorer.py --input audit_findings.json --baseline last_sprint.json --format text --verbose

Three independent grades:

Validation checkpoint: Release gate requires minimum B Design grade and A Accessibility grade.

Workflow 2: AI Slop Detection

python scripts/ai_slop_detector.py --input index.html --css styles.css --threshold 0.6 --format json

The agent detects patterns across three categories:

Visual slop (confidence 0.4-0.9):

• Generic hero section (full-width, centered text, gradient)
• Stock gradients (trending purple-blue, pink-orange)
• 3-column feature grid (icon + heading + paragraph x3)
• Shadow/blur overuse on >60% of containers

Copy slop (confidence 0.5-1.0):

• Vague CTAs: "Get Started", "Learn More" without context
• Buzzword clustering: "Seamless", "Powerful", "Revolutionary"
• Lorem ipsum residue or uniform paragraph lengths

Structural slop (confidence 0.4-0.8):

• Template ordering: Hero > Features > Social Proof > Pricing > CTA > Footer
• Cookie-cutter pricing (3 tiers, middle highlighted)

Each finding includes a remediation suggestion for making the element more intentional.

Workflow 3: Accessibility & Design System Compliance

Color contrast audit:

python scripts/color_contrast_checker.py --input brand-colors.json --level AA --suggest-fixes --format text

Input format:

[
  {"foreground": "#666666", "background": "#ffffff", "label": "body text"},
  {"foreground": "#999999", "background": "#f5f5f5", "label": "muted text"}
]

The agent checks against WCAG thresholds (4.5:1 normal text, 3:1 large text) and suggests the closest compliant alternative for failing pairs.

Design system validation:

python scripts/design_system_validator.py --tokens design-tokens.json --input src/styles/ --glob "*.scss"

Token file format:

{
  "colors": {"primary": "#1a73e8", "secondary": "#5f6368", "error": "#d93025"},
  "spacing": [0, 4, 8, 12, 16, 24, 32, 48, 64],
  "typography": {"body": "16px", "h1": "32px", "h2": "24px"},
  "radii": [0, 4, 8, 16, 9999]
}

Detects hardcoded colors, spacing, fonts, radii, shadows, z-indices, and transitions that deviate from tokens. Reports compliance percentage and suggests nearest token for each violation.

Validation checkpoint: Token compliance >= 90%. Zero off-system colors in production CSS.

Design Principles (Audit Operating System)

These 10 principles drive every finding evaluation:

1. Specificity over vibes -- "Clean UI" is banned. Name the font, spacing scale, color system.
2. Empty states are features -- "No items found" is a bug. Guide users to first action.
3. Subtraction default -- every element must earn its place. When in doubt, remove it.
4. Edge cases are user experiences -- 47-character names, zero results, slow networks, stale state.
5. Four shadow paths -- happy path, nil input, empty input, error upstream. Blank screen = Critical.
6. Loading states earn trust -- skeleton screens > spinners > blank pages.
7. Consistency compounds -- one off-system color erodes the entire design language. Tokens are contracts.
8. Motion has meaning -- decorative animation without purpose is noise.
9. Accessibility is baseline -- WCAG AA is the floor. Accessibility findings are never "Low" priority.
10. Performance is perceived design -- 3-second load feels broken regardless of visual quality.

Fix Session Rules

• One issue = one question -- never batch multiple findings.
• AUTO-FIX: Cosmetic -- spacing token mismatches, off-system colors to nearest token.
• ASK: Structural -- layout changes, component swaps, navigation restructuring.
• Max 30 fixes per session. Hard stop, then generate report.
• Risk accumulator: component (+5), global style (+8), layout (+10), revert (+15). Stop at 20% of budget.
• Revert on regression -- if fix breaks visual tests or introduces Critical finding,

  git revert

  immediately.

CI/CD Integration

jobs:
  design-checks:
    steps:
      - run: python scripts/color_contrast_checker.py --input color-pairs.json --level AA
      - run: |
          python scripts/design_system_validator.py --tokens tokens.json --input src/styles/ --format json > compliance.json
          python -c "import json; exit(0 if json.load(open('compliance.json')).get('compliance_percentage',0)>=90 else 1)"
      - run: python scripts/ai_slop_detector.py --input dist/index.html --threshold 0.7 --format json

Anti-Patterns

1. Scoring categories too high relative to findings -- if there are 4 accessibility findings, the score should not be 8/10.
2. Ignoring interaction states -- every interactive element needs: default, hover, focus, active, disabled, loading, error, empty, success.
3. Color as sole information carrier -- information must not be conveyed by color alone.
4. Skipping edge cases -- test with long names, empty data, error states, not just the happy path.

Troubleshooting

design_scorer.py

categories

rgb()

hsl()

--threshold

--glob "*.scss"

References

references/design_audit_methodology.md

references/ai_slop_patterns.md

references/accessibility_checklist.md

Integration Points

senior-frontend

senior-qa

code-reviewer

senior-devops

product-team/ux-researcher

Last Updated: April 2026 Version: 2.1.0