Skip to content

borghei/Claude-Skills / engineering/design-auditor

design-auditor

Verified

Grade a UI (Design, AI-slop and Accessibility, A-F) and gate it in CI: batch WCAG contrast, token compliance, slop detection. Use when asked to audit, score or gate a UI; to fix one, use interface-refinement.

references/scoring-model.json

View on GitHub
{
  "_about": "Category weights and grade bands read by design_scorer.py. The 12 weights sum to 0.95; coherence adds the last 0.05.",
  "categories": {
    "visual_hierarchy": {
      "name": "Visual Hierarchy & Composition",
      "weight": 0.1
    },
    "typography": {
      "name": "Typography System",
      "weight": 0.08
    },
    "color_contrast": {
      "name": "Color & Contrast",
      "weight": 0.08
    },
    "spacing_layout": {
      "name": "Spacing & Layout Grid",
      "weight": 0.08
    },
    "interaction_states": {
      "name": "Interaction States",
      "weight": 0.1
    },
    "navigation_ia": {
      "name": "Navigation & Information Architecture",
      "weight": 0.08
    },
    "responsive": {
      "name": "Responsive Design",
      "weight": 0.08
    },
    "accessibility": {
      "name": "Accessibility (WCAG)",
      "weight": 0.12
    },
    "motion_animation": {
      "name": "Motion & Animation",
      "weight": 0.05
    },
    "content_microcopy": {
      "name": "Content & Microcopy",
      "weight": 0.05
    },
    "ai_slop": {
      "name": "AI Slop Indicators",
      "weight": 0.08
    },
    "performance_design": {
      "name": "Performance as Design",
      "weight": 0.05
    }
  },
  "coherence_weight": 0.05,
  "priority_order": [
    "critical",
    "high",
    "medium",
    "low",
    "cosmetic"
  ],
  "priority_labels": {
    "critical": "Critical — Breaks core UX",
    "high": "High — Degrades experience",
    "medium": "Medium — Inconsistency",
    "low": "Low — Polish",
    "cosmetic": "Cosmetic — Nice-to-have"
  },
  "grade_bands": {
    "design": [
      [
        95,
        "A+"
      ],
      [
        90,
        "A"
      ],
      [
        85,
        "B+"
      ],
      [
        80,
        "B"
      ],
      [
        75,
        "C+"
      ],
      [
        70,
        "C"
      ],
      [
        60,
        "D"
      ]
    ],
    "ai_slop": [
      [
        9,
        "A"
      ],
      [
        7,
        "B"
      ],
      [
        5,
        "C"
      ],
      [
        3,
        "D"
      ]
    ],
    "accessibility": [
      [
        9.5,
        "A+"
      ],
      [
        8.5,
        "A"
      ],
      [
        7,
        "B"
      ],
      [
        5,
        "C"
      ],
      [
        3,
        "D"
      ]
    ]
  },
  "grade_floor": "F"
}
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall