plugins/designer/skills/ui-design-review/SKILL.md
Prompting patterns and review templates for UI design analysis with Gemini multimodal capabilities. Use when conducting design reviews, accessibility audits, or design system validation.
npx skillsauth add madappgang/magus ui-design-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
This skill provides prompting patterns, checklists, and templates for conducting UI design reviews using Gemini's multimodal vision capabilities.
Read shared/model-aliases.json → roles.designer_review.modelId for the design review model.
If the file doesn't exist, tell the user to run /update-models.
# GEMINI_MODEL: read from shared/model-aliases.json → roles.designer_review.modelId
# Pass image file directly with --image flag
npx claudish --model "$GEMINI_MODEL" --image "$IMAGE_PATH" --quiet --auto-approve <<< "$ANALYSIS_PROMPT"
# Example
npx claudish --model "$GEMINI_MODEL" --image "screenshots/dashboard.png" --quiet --auto-approve <<< "Analyze this UI for usability issues."
# 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
# 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
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
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 |
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 |
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]
Focus on critical issues only:
Full heuristic evaluation:
Deep analysis including:
| Severity | User Impact | Examples | Action | |----------|-------------|----------|--------| | CRITICAL | Blocks task completion | Invisible submit button, broken flow | Fix immediately | | HIGH | Major barrier | Fails WCAG AA, confusing navigation | Fix before release | | MEDIUM | Noticeable friction | Inconsistent spacing, unclear labels | Fix in next sprint | | LOW | Polish opportunity | Minor alignment, shade variance | Backlog |
Use claudish CLI for multi-model design reviews:
claudish --model "$GEMINI_MODEL" --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:
testing
A test skill for validation testing. Use when testing skill parsing and validation logic.
tools
--- name: bad-skill description: This skill has invalid YAML in frontmatter allowed-tools: [invalid, array, syntax prerequisites: not-an-array --- # Bad Skill This skill has malformed frontmatter that should fail parsing. The YAML has: - Unclosed array bracket - Wrong type for prerequisites (should be array, not string)
development
Sync model aliases from the curated Firebase database. Fetches default model assignments, short aliases, team compositions, and known model metadata from the claudish API. Run this to get fresh model recommendations.
tools
Release one or more Magus plugins to the distribution repos (magus, magus-alpha, magus-marketing). Handles version inference from git history, marketplace.json updates, tagging, and force-push to lean dist repos. Use whenever the user says "release kanban", "release the dev plugin", "cut a new version of gtd", "bump kanban to 1.7", or hands you a batch like "release kanban and gtd". Also use for multi-plugin releases and for checking what a release would contain before committing.