Agent skill · Audited from source

Design Auditor

skill · borghei/Claude-SkillsNOASSERTION licenceAudited 19 Oct 2026 · source 6e3fcbdbb5cf

★ 949pushed 12 days agoversion 2.2.0
!CAUTIONGrade B · 89/100 · 5 findings · 6e3fcbd
949repo stars · whole borghei/Claude-Skills

Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit 6e3fcbdbb5cf and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 5 findings, 0 critical or high. What it does: Audit UI/UX designs for quality, AI-generated slop, and accessibility. Use when reviewing designs, detecting slop patterns, validating WCAG compliance, checking design-token adherence, or reviewing responsive design…

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
Cite

Cite this page

ModelsAtlas. “Design Auditor (borghei/Claude-Skills)”. Retrieved 19 Oct 2026. https://modelsatlas.com/skills/borghei/design-auditor

Trust audit

Audit 0.4.1 · source read 19 Oct 2026

Trust score89/100!CAUTION B
0 critical0 high5 medium0 low0 info

CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.

What the source does

  • FilesystemNone observedNo reads or writes in the source
  • NetworkNone observedNo outbound calls in the source
  • ShellNone observedNo commands run in the source
  • DependenciesPinnedNothing floats
  • SecretsNone foundNo keys in source

Five audit layers

LayerWhat we checkResultFindings
L0 ProvenanceRepo owner, licence, archive status, activityWARN5
L1 Static sourceSecrets, path traversal, supply chain, hidden codePASS0
L2 InstructionsPrompt injection, authority framing, hidden directivesPASS0
L3 InventoryThe files and declarations match the sourcePASS0
L4 SandboxRun in isolation and watch behaviourSKIPPED why0

Gates applied: no behavioural pass.

Findings (5)

Audit 0.4.1 · source sha 6e3fcbdbb5cf · 19 Oct 2026Report an issue or request a re-scan

Provenance

Who published it, and what the verdict is pinned to

  • Publisherborghei GitHub userOwner of the repository this skill is read from
  • Source folderborghei/Claude-Skills/engineering/design-auditorThe exact folder we audited
  • LicenceNOASSERTIONAs the repository states it
  • Commit pinned for this verdict6e3fcbdbb5cfA new audit runs when the source changes
  • Repository statusNot archivedLast push 12 days ago
  • Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

What it tells the agent

Full source on GitHub ↗

Its description: Audit UI/UX designs for quality, AI-generated slop, and accessibility. Use when reviewing designs, detecting slop patterns, validating WCAG compliance, checking design-token adherence, or reviewing responsive design…

---
name: design-auditor
description: >
  Audit UI/UX designs for quality, AI-generated slop, and accessibility. Use when reviewing
  designs, detecting slop patterns, validating WCAG compliance, checking design-token
  adherence, or reviewing responsive design across breakpoints.
license: MIT + Commons Clause
metadata:
  version: 2.2.0
  author: borghei
  category: engineering
  domain: design-engineering
  updated: 2026-06-17
  tags: [design-audit, ai-slop, color-contrast, accessibility]
  python-tools: design_scorer.py, ai_slop_detector.py, color_contrast_checker.py, design_system_validator.py
  tech-stack: python, css, accessibility, wcag, design-systems
---
# Design Auditor

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).

## Core Capabilities

- **Full design audit** — score 12 weighted categories in five passes into a Design grade with prioritized recommendations and baseline comparison.
- **AI slop detection** — flag visual, copy, and structural slop in HTML/CSS with confidence scores and per-finding remediation.
- **Accessibility audit** — WCAG color-contrast checking (AA/AAA) with closest-compliant-color suggestions.
- **Design-system compliance** — detect hardcoded colors, spacing, fonts, radii, shadows, z-indices, and transitions that deviate from tokens; report compliance percentage.
- **Three independent grades** — Design (weighted aggregate), AI Slop (inverted), Accessibility (WCAG), each A–F.
- **Operating system** — 10 design principles, fix-session rules with a risk accumulator, and CI/CD gating.

## When to Use

- Reviewing a UI/UX design for quality, originality, and accessibility.
- Detecting AI-generated slop patterns in HTML/CSS.
- Validating WCAG color contrast or design-token adherence.
- Gating deployments or PRs on minimum compliance scores.

## Clarify First

Before running the audit, confirm these inputs. If any is unknown or vague, ASK — do not assume:

- [ ] **Audit type** — full design score, AI-slop detection, contrast check, or token compliance (selects `design_scorer.py` vs `ai_slop_detector.py` vs `color_contrast_checker.py` vs `design_system_validator.py`)
- [ ] **Input artifacts** — the findings JSON, HTML/CSS, color pairs, or design-token file (the input each tool requires)
- [ ] **Conformance level / threshold** — WCAG AA vs AAA, slop confidence threshold, and the minimum passing grade (sets `--level`, `--threshold`, and the gate)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

## Tools

| Tool | Purpose | Command |
|------|---------|---------|
| `design_scorer.py` | Score 12-category audit findings into three grades | `python scripts/design_scorer.py --input findings.json --output report.json --verbose` |
| `ai_slop_detector.py` | Detect AI-generated slop in HTML/CSS | `python scripts/ai_slop_detector.py --input page.html --css styles.css --threshold 0.6` |
| `color_contrast_checker.py` | Check WCAG color contrast (single/batch) | `python scripts/color_contrast_checker.py --input color-pairs.json --level AA --suggest-fixes` |
| `design_system_validator.py` | Validate CSS against design tokens | `python scripts/design_system_validator.py --tokens tokens.json --input src/styles/` |

All tools support `--format json|text` and `--output` for file writing.

## References

Load the reference that matches the task — keep this file lean and pull detail on demand:

- **[references/audit-workflows-and-operations.md](references/audit-workflows-and-operations.md)** — quick-start commands, tools-overview table, the three workflows (full audit, slop detection, accessibility/token compliance), grade tables, the 10 design principles, fix-session rules, CI/CD integration, anti-patterns, and troubleshooting. Read when running an audit end to end.
- **[references/design_audit_methodology.md](references/design_audit_methodology.md)** — systematic audit approach, heuristic evaluation, Gestalt principles, critique frameworks, and anti-patterns. Read when designing the evaluation pass.
- **[references/ai_slop_patterns.md](references/ai_slop_patterns.md)** — comprehensive catalog of AI-generated UI patterns and remediation guidance. Read when judging originality.
- **[references/accessibility_checklist.md](references/accessibility_checklist.md)** — full WCAG 2.1 Level A/AA/AAA checklist organized by POUR with testing methodology and fixes. Read when auditing accessibility.

## Scope & Limitations

Covers static design quality, AI-slop, WCAG contrast, and design-token compliance auditing for web UI (HTML/CSS). Does not run live browsers, render-test layouts, or replace manual usability research. Accessibility findings are never "Low" priority; WCAG AA is the floor.

## Integration Points

| Skill | Integration |
|-------|-------------|
| `senior-frontend` | Design audit on component library after build |
| `senior-qa` | Accessibility and design regression in QA pipelines |
| `code-reviewer` | Attach audit findings to frontend PR reviews |
| `senior-devops` | Gate deployments on minimum compliance scores |
| `product-team/ux-researcher` | Feed findings into usability research prioritization |

---

**Last Updated:** June 2026
**Version:** 2.2.0

Excerpt, first 5,459 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.

Install

Pinned to the audited commit 6e3fcbd

Download folder ↗
git clone https://github.com/borghei/Claude-Skills
git -C Claude-Skills checkout 6e3fcbdbb5cf

The author documents no install command, so this uses the repository directly. Our verdict covers commit 6e3fcbdbb5cf only.

Works in which agents?

What its own text says, not a test

AgentStatusMore
CursorMentioned in its text, not testedSkills for Cursor · About Cursor
“Mentioned” means the skill’s text names the agent. We have not run it there.

Audit history

Every audit, every source change

  1. !CAUTION B 89 / 100

    first audit · source 6e3fcbdbb5cf

README badge

For maintainers · shows the latest audit

ModelsAtlas: CAUTION BMODELSATLASCAUTION · B
[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/borghei/design-auditor/badge.svg)](https://modelsatlas.com/skills/borghei/design-auditor/)

The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.

A11y Audit!CAUTION

borghei/Claude-Skills

This skill should be used when the user asks to "check accessibility", "audit WCAG compliance", "scan HTML for a11y issues", "check color contrast", or "find accessibility violations in web pages".

★ 949Grade B
Agent Designer!CAUTION

borghei/Claude-Skills

Designs multi-agent system architectures with orchestration patterns, tool schemas, and performance evaluation. Use when building AI agent systems, designing agent workflows, creating tool schemas, or evaluating agent…

★ 949Grade B
Agent Protocol!CAUTION

borghei/Claude-Skills

Design AI agent communication protocols: MCP tool schemas, A2A, function calling, and inter- agent messaging. Use when building multi-agent systems, defining tool interfaces, or implementing agent-to-agent communication.

★ 949Grade B
Agent Workflow Designer!CAUTION

borghei/Claude-Skills

Design multi-agent orchestration with workflow DAGs, routing, handoff protocols, and state management. Use when building pipelines of specialized agents, designing fan-out/fan-in patterns, or implementing fault-tolerant…

★ 949Grade B
Agenthub!CAUTION

borghei/Claude-Skills

Multi-agent DAG orchestration for workflows where AI agents collaborate via dependency graphs, covering agent spawning, output merging, and quality evaluation. Use when a task needs multiple specialized agents or to…

★ 949Grade B
Analytics Engineer!CAUTION

borghei/Claude-Skills

Analytics engineering across data modeling, dbt, transformation, and semantic layers. Use when building dbt models, designing star schemas, writing staging or mart SQL, configuring data tests, or optimizing warehouse…

★ 949Grade B

Add this badge to your README

[![ModelsAtlas: CAUTION B](https://modelsatlas.com/skills/borghei/design-auditor/badge.svg)](https://modelsatlas.com/skills/borghei/design-auditor/)

Questions about Design Auditor

What does the Design Auditor skill do?
385 AI skills, 77 expert agents, and 900 stdlib Python tools for every team: engineering, PM, marketing, C-level, compliance, business ops, research, and a LinkedIn toolkit. Installs on Claude Code, Cursor, Codex, Gemini, Copilot, and 6 other AI assistants.
Is Design Auditor safe to install?
With care. The audit graded it B (89/100) and found 5 things worth knowing before you trust this skill, listed below with the exact line each was found on.
What can Design Auditor access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Design Auditor work with?
Its documentation mentions cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (6e3fcbdbb5cf), read on 2026-10-19. The repository is watched, and a new audit runs when it changes — this is the first audit.

Sources

Spotted something wrong? Report a correction · Methodology

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.