Agent skill

UI Design Review

by MadAppGang in MadAppGang/claude-code

Prompting patterns and review templates for UI design analysis with Gemini multimodal capabilities.

MITAuto-check passedFrontend & Design

Install UI Design Review

skills CLI
$ npx skills add MadAppGang/claude-code --skill ui-design-review -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install MadAppGang/claude-code ui-design-review --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/MadAppGang/claude-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/dev/skills/design/ui-design-review .claude/skills/ui-design-review && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ui-design-review
GitHub stars
285
Token cost
~2k tokens
SKILL.md length
368 words
Files
1
Skills in repo
69
Repo updated
First seen
Licence
MIT

At a glance

Prompting patterns and review templates for UI design analysis with Gemini multimodal capabilities.

  • Works in 4 steps: Can users complete the primary task? → Are there any major accessibility… → Is the visual hierarchy clear? → …
  • Conducting design reviews
  • SKILL.md covers Overview, When to Use, Model Routing and Passing Images to Claudish, plus 5 more sections
  • Calls npx; needs GEMINI_API_KEY and OPENROUTER_API_KEY

What it does

UI Design Review is an agent skill from MadAppGang/claude-code. Prompting patterns and review templates for UI design analysis with Gemini multimodal capabilities. Use when conducting design reviews, accessibility audits, or design system validation.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Frontend & Design, covering UI design, Accessibility and Design review and critique. It works with Google Gemini and OpenRouter. The repository describes itself as: claude code plugins marketplace. The licence is MIT.

When your agent uses it

  • Conducting design reviews
  • Accessibility audits
  • Design system validation

Example prompts

  • “/ui-design-review”

Requirements

  • Node.js
  • A credential in GEMINI_API_KEY
  • A credential in OPENROUTER_API_KEY

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Can users complete the primary task?
  2. Are there any major accessibility barriers?
  3. Is the visual hierarchy clear?
  4. Are interactive elements obviously interactive?

What it can do on your machine

Read from SKILL.md and the folder at commit 6097ad4. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • npx

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GEMINI_API_KEY
    • OPENROUTER_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

UI Design Review loads about 2k tokens when it runs. Until then it costs about 51 tokens; SKILL.md has 368 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~51
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from MadAppGang/claude-code at commit 6097ad4, republished under its MIT licence (© MadAppGang). 368 words, ~2,032 tokens.

Download SKILL.mdSave it as .claude/skills/ui-design-review/SKILL.md (or your agent's skills folder).
name
ui-design-review
description
Prompting patterns and review templates for UI design analysis with Gemini multimodal capabilities. Use when conducting design reviews, accessibility audits, or design system validation.
version
1.0.0

UI Design Review Skill

Overview

This skill provides prompting patterns, checklists, and templates for conducting UI design reviews using Gemini's multimodal vision capabilities.

When to Use

  • Reviewing screenshots, wireframes, or mockups
  • Conducting accessibility audits
  • Validating design system consistency
  • Comparing implementation to design reference
  • Analyzing UI patterns and usability

Model Routing

Gemini API Key Detection
bash
# Check API key availability and select model
determine_gemini_model() {
  if [[ -n "$GEMINI_API_KEY" ]]; then
    echo "g/gemini-3-pro-preview"  # Direct Gemini API
  elif [[ -n "$OPENROUTER_API_KEY" ]]; then
    echo "google/gemini-3-pro-preview"  # OpenRouter
  else
    echo "ERROR: No API key available (need GEMINI_API_KEY or OPENROUTER_API_KEY)"
    return 1
  fi
}

GEMINI_MODEL=$(determine_gemini_model)
Why or/ Prefix for OpenRouter

The model ID google/gemini-3-pro-preview collides with Claudish's automatic routing:

Model IDRoutes ToRequires
google/gemini-*Gemini DirectGEMINI_API_KEY
google/gemini-*OpenRouterOPENROUTER_API_KEY
g/gemini-*Gemini Direct (explicit)GEMINI_API_KEY

Rule: Always use or/ prefix when routing Google models through OpenRouter.

Passing Images to Claudish

bash
# Pass image file directly with --image flag
npx claudish --model "$GEMINI_MODEL" --image "$IMAGE_PATH" --quiet --auto-approve <<< "$ANALYSIS_PROMPT"

# Example
npx claudish --model "g/gemini-3-pro-preview" --image "screenshots/dashboard.png" --quiet --auto-approve <<< "Analyze this UI for usability issues."
Method 2: Base64 Encoded (For Inline Images)
bash
# Encode image to base64
IMAGE_B64=$(base64 -i "$IMAGE_PATH")

# Include in prompt with data URI
printf '%s' "[Image: data:image/png;base64,$IMAGE_B64]

Analyze this UI for usability issues." | npx claudish --stdin --model "$GEMINI_MODEL" --quiet --auto-approve
Method 3: URL Reference (For Remote Images)
bash
# Reference image by URL
printf '%s' "[Image: https://example.com/screenshot.png]

Analyze this UI for usability issues." | npx claudish --stdin --model "$GEMINI_MODEL" --quiet --auto-approve

Prompting Patterns

Pattern 1: General Usability Review
markdown
Analyze this UI screenshot for usability issues.

**Image**: [attached or path]

**Focus Areas**:
1. Visual hierarchy - Is the most important content prominent?
2. Affordances - Do interactive elements look clickable/tappable?
3. Feedback - Is system status clearly communicated?
4. Consistency - Do similar elements behave similarly?
5. Error prevention - Are destructive actions guarded?

**Output Format**:
For each issue found:
- **Location**: Where in the UI
- **Issue**: What the problem is
- **Principle**: Which design principle it violates
- **Severity**: CRITICAL/HIGH/MEDIUM/LOW
- **Recommendation**: Specific fix
Pattern 2: WCAG Accessibility Audit
markdown
Audit this UI for WCAG 2.1 AA compliance.

**Image**: [attached or path]

**Checklist**:
1. **Perceivable**
   - [ ] Text contrast >= 4.5:1 (WCAG 1.4.3)
   - [ ] Non-text contrast >= 3:1 (WCAG 1.4.11)
   - [ ] Information not conveyed by color alone (WCAG 1.4.1)
   - [ ] Text resizable to 200% (WCAG 1.4.4)

2. **Operable**
   - [ ] Keyboard accessible (WCAG 2.1.1)
   - [ ] No keyboard traps (WCAG 2.1.2)
   - [ ] Focus visible (WCAG 2.4.7)
   - [ ] Touch targets >= 44x44px (WCAG 2.5.5)

3. **Understandable**
   - [ ] Labels present for inputs (WCAG 3.3.2)
   - [ ] Error identification clear (WCAG 3.3.1)
   - [ ] Instructions available (WCAG 3.3.2)

4. **Robust**
   - [ ] Valid structure implied (headings, regions)

**Output Format**:
| Criterion | Status | Notes | Fix |
|-----------|--------|-------|-----|
| 1.4.3 | PASS/FAIL | Details | Recommendation |
Pattern 3: Design System Consistency Check
markdown
Compare this implementation against the design system.

**Implementation Image**: [attached or path]
**Design System Reference**: [tokens, components, patterns]

**Validation Points**:
1. **Colors**
   - Primary, secondary, accent colors
   - Semantic colors (success, warning, error)
   - Background and surface colors

2. **Typography**
   - Font family usage
   - Size scale adherence
   - Weight usage (regular, medium, bold)
   - Line height consistency

3. **Spacing**
   - Margin scale (4, 8, 16, 24, 32, 48...)
   - Padding consistency
   - Gap between elements

4. **Components**
   - Button variants (primary, secondary, ghost)
   - Input styles (default, focus, error, disabled)
   - Card patterns

5. **Elevation**
   - Shadow levels
   - Border usage
   - Layer hierarchy

**Output Format**:
| Element | Expected | Actual | Deviation |
|---------|----------|--------|-----------|
| Button BG | #2563EB | #3B82F6 | Wrong shade |
Pattern 4: Comparative Design Review
markdown
Compare the implementation screenshot to the original design.

**Design Reference**: [Figma export or mockup]
**Implementation**: [Screenshot of built UI]

**Comparison Points**:
1. Layout and positioning accuracy
2. Color fidelity
3. Typography matching
4. Spacing precision
5. Component rendering
6. Responsive behavior (if multiple sizes)

**Output Format**:
## Match Analysis

**Overall Fidelity**: X/10

### Exact Matches
- [List elements that match perfectly]

### Deviations
| Element | Design | Implementation | Impact | Fix |
|---------|--------|----------------|--------|-----|
| CTA Button | #2563EB | #3B82F6 | Visual | Change to design color |

### Missing Elements
- [Elements in design but not in implementation]

### Extra Elements
- [Elements in implementation but not in design]

Review Templates

Quick Review (5 minutes)

Focus on critical issues only:

  1. Can users complete the primary task?
  2. Are there any major accessibility barriers?
  3. Is the visual hierarchy clear?
  4. Are interactive elements obviously interactive?
Standard Review (15 minutes)

Full heuristic evaluation:

  1. All Nielsen's 10 heuristics
  2. WCAG AA key criteria
  3. Visual design quality
  4. Interaction design
Comprehensive Review (30+ minutes)

Deep analysis including:

  1. Full heuristic evaluation
  2. Complete WCAG AA audit
  3. Design system consistency
  4. Competitive analysis context
  5. User flow mapping
Show full SKILL.md (136 more words)Show less

Severity Guidelines

SeverityUser ImpactExamplesAction
CRITICALBlocks task completionInvisible submit button, broken flowFix immediately
HIGHMajor barrierFails WCAG AA, confusing navigationFix before release
MEDIUMNoticeable frictionInconsistent spacing, unclear labelsFix in next sprint
LOWPolish opportunityMinor alignment, shade varianceBacklog

Integration with Multi-Model Validation

Use claudish CLI for multi-model design reviews:

bash
claudish --model google/gemini-3-pro-preview --stdin --quiet <<EOF > ${SESSION_PATH}/reviews/design-review/gemini.md
Review the dashboard screenshot at screenshots/dashboard.png

Focus on usability and accessibility.
EOF

This enables:

  • Running multiple design reviewers in parallel
  • Consensus analysis on design issues
  • Different model perspectives (Gemini vision, Claude reasoning)

Best Practices

DO
  • Always validate image inputs exist before analysis
  • Cite specific design principles for every issue
  • Provide actionable, specific recommendations
  • Prioritize by severity (CRITICAL first)
  • Use Gemini for visual analysis (not guessing)
DON'T
  • Give vague aesthetic opinions ("looks bad")
  • Overwhelm with LOW severity items
  • Forget accessibility considerations
  • Skip the principle citation
  • Assume implementation details without seeing

© MadAppGang, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in plugins/dev/skills/design/ui-design-review of MadAppGang/claude-code.

Open the folder on GitHubat commit 6097ad4

Compare with similar skills

UI Design Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

UI Design Review compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
UI Design Review this skillMadAppGang/claude-code285—~2kAutomated safety check: PassMIT
UI/UX Design System AdvisorGalaxy-Dawn/claude-scholar5.7k1 repos~1.1kAutomated safety check: PassMIT
Material Design 3 UI/UX Guideskydashnet/material-design-3-ui-skill138—~3kAutomated safety check: PassMIT
UI Component Spec Designerplugin87/ux-ui-agent-skills1.6k—~2.8kAutomated safety check: PassMIT
Typeui Fundamentalsbergside/typeui2k—~861Automated safety check: PassMIT
Better Designmarvkr/better-design254—~1.2kAutomated safety check: PassMIT

Similar skills

  • UI/UX Design System Advisor

    Galaxy-Dawn/claude-scholar

    Turns a vague UI request into a concrete design system with style, palette, typography and layout guidance from a search script, plus stack-specific implementation advice.

    5.7k GitHub starsUsed in 1 repo~1.1k tokens
    Frontend & DesignAuto-check passed
  • Material Design 3 UI/UX Guide

    skydashnet/material-design-3-ui-skill

    Guides designing, reviewing or implementing interfaces that follow Google's Material Design 3 system: semantic tokens, component states, adaptive layout and accessibility.

    138 GitHub stars~3k tokensUpdated 10 days ago
    Frontend & DesignAuto-check passed
  • UI Component Spec Designer

    plugin87/ux-ui-agent-skills

    Writes a complete UI component spec with anatomy, variants, sizes, eight interaction states, design-token mapping and accessibility notes before or alongside code.

    1.6k GitHub stars~2.8k tokensUpdated today
    Frontend & DesignAuto-check passed
  • Typeui Fundamentals

    bergside/typeui

    Universal UI/UX design principles covering visual hierarchy, interaction laws, typography foundations, and WCAG accessibility requirements.

    2k GitHub stars~861 tokensUpdated 3 mo ago
    Frontend & DesignAuto-check passed
  • Better Design

    marvkr/better-design

    Build, improve, and review production interfaces with the Better Design MCP.

    254 GitHub stars~1.2k tokensUpdated 18 days ago
    Frontend & DesignAuto-check passed
  • UI Design System

    try-works/role-model

    React UI component systems with TailwindCSS + Radix + shadcn/ui.

    117 GitHub stars~5k tokensUpdated today
    Frontend & DesignAuto-check passed

More from MadAppGang/claude-code

All 69 skills in this repo
  • Content Brief

    MadAppGang/claude-code

    Content brief template and creation methodology for SEO-optimized content.

    285 GitHub starsUsed in 1 repo~959 tokens
    Auto-check passed
  • Context Detection

    MadAppGang/claude-code

    A skill your agent uses when detecting project technology stack from files/configs/directory structure, auto-loading framework-specific skills, or analyzing multi-stack fullstack projects (e.g…

    285 GitHub stars~5.4k tokensUpdated 7 mo ago
    Auto-check passed
  • Content Optimizer

    MadAppGang/claude-code

    On-page SEO optimization techniques including keyword density, meta tags, heading structure, and readability.

    285 GitHub starsUsed in 1 repo~694 tokens
    Auto-check passed
  • Keyword Cluster Builder

    MadAppGang/claude-code

    Techniques for expanding seed keywords and clustering by topic and intent.

    285 GitHub starsUsed in 1 repo~674 tokens
    Auto-check passed
  • Serp Analysis

    MadAppGang/claude-code

    SERP analysis techniques for intent classification, feature identification, and competitive intelligence.

    285 GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed
  • Agent Coordination Discipline

    MadAppGang/claude-code

    A skill your agent uses when deciding whether to launch an agent, selecting which agent to use, or coordinating multiple agents.

    285 GitHub stars~3.8k tokensUpdated 7 mo ago
    Auto-check passed

Questions about UI Design Review

What does UI Design Review do?

Prompting patterns and review templates for UI design analysis with Gemini multimodal capabilities. UI Design Review is an agent skill from MadAppGang/claude-code. Prompting patterns and review templates for UI design analysis with Gemini multimodal capabilities.

When should I use UI Design Review?

UI Design Review fits situations like: conducting design reviews; accessibility audits; design system validation.

How do I install UI Design Review in Claude Code?

Run `npx skills add MadAppGang/claude-code --skill ui-design-review -a claude-code`. Or copy the skill folder (plugins/dev/skills/design/ui-design-review in MadAppGang/claude-code) into .claude/skills/ui-design-review in your project. Claude Code loads it when a task matches its description.

How do I install UI Design Review in Codex?

Run `npx skills add MadAppGang/claude-code --skill ui-design-review -a codex`. Or copy the skill folder (plugins/dev/skills/design/ui-design-review in MadAppGang/claude-code) into .agents/skills/ui-design-review in your project. Codex loads it when a task matches its description.

Can I use UI Design Review in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add MadAppGang/claude-code --skill ui-design-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ui-design-review, .gemini/skills/ui-design-review, .github/skills/ui-design-review and .opencode/skills/ui-design-review in your project.

What does UI Design Review need to run?

Going by SKILL.md and its folder, UI Design Review needs the command-line tools its instructions call (npx) and credentials named GEMINI_API_KEY and OPENROUTER_API_KEY. Our summary lists: Node.js; A credential in GEMINI_API_KEY; A credential in OPENROUTER_API_KEY.

Does UI Design Review access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is UI Design Review safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does UI Design Review use?

UI Design Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does UI Design Review use?

About 2k tokens (SKILL.md is roughly 8.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to UI Design Review?

Skills that share tags, products or a category with UI Design Review: UI/UX Design System Advisor (Galaxy-Dawn/claude-scholar, 5.7k stars), Material Design 3 UI/UX Guide (skydashnet/material-design-3-ui-skill, 138 stars), UI Component Spec Designer (plugin87/ux-ui-agent-skills, 1.6k stars) and Typeui Fundamentals (bergside/typeui, 2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains UI Design Review?

MadAppGang (a GitHub organization) maintains it in MadAppGang/claude-code, which has 285 GitHub stars. The repository holds 69 skills in this directory. The repository was last updated on March 15, 2026.

Source: MadAppGang/claude-code on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.