skills/product/design-review/SKILL.md
Visual design and UI consistency review — design system adherence, spacing tokens, typography, color usage, component patterns, and responsive polish. Use when: "design critique", "polish the UI", "design system adherence", "responsive design", "visual polish", "review the design", "UI inconsistency"
npx skillsauth add mikeparcewski/wicked-garden 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.
Deep visual design and UI implementation review.
Visual Consistency:
Component Patterns:
Responsive Design:
Visual Polish:
Full review criteria: See Visual Consistency, Components & Responsive, and Accessibility & Scoring
# Scan for components
sh "${CLAUDE_PLUGIN_ROOT}/scripts/_python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/product/component-inventory.py" src/
# Find patterns
wicked-garden:search "className=" --type jsx
wicked-garden:search "styled\." --type ts
# Find hardcoded colors (violations)
wicked-garden:search "#[0-9a-fA-F]{3,6}" --type css
# Find magic number spacing
wicked-garden:search "[0-9]+px" --type css
| Category | Score | Notes | |----------|-------|-------| | Colors | {✓⚠✗} | {brief note} | | Typography | {✓⚠✗} | {brief note} | | Spacing | {✓⚠✗} | {brief note} | | Components | {✓⚠✗} | {brief note} | | Responsive | {✓⚠✗} | {brief note} |
Scoring guide: See refs/scoring-guide-methodology.md and refs/scoring-guide-examples.md
❌ Hardcoded colors: `color: #3b82f6` vs `color: var(--primary)`
❌ Magic numbers: `margin: 17px` vs `margin: var(--space-4)`
❌ Missing states: No `:hover` or `:focus` styles
❌ Non-responsive: Fixed widths without media queries
❌ Component duplication: Multiple similar button implementations
❌ Inaccessible contrast: Light gray on white
Fix examples: See Color Issues, Component Issues, Animation Issues
## Design Review
**Consistency**: {✓ Ship it | ⚠ Minor issues | ✗ Needs work}
### Component Inventory
- Buttons: {count}
- Inputs: {count}
- Cards: {count}
### Issues
#### Critical
- {Issue breaking design}
- Location: {file:line}
- Fix: {code change}
#### Major
- {Inconsistency}
- Location: {file:line}
- Recommendation: {improvement}
### Recommendations
1. {High-priority fix}
2. {Design system improvement}
Full report template: See refs/report-template-findings.md and refs/report-template-actions.md
If project has a design system:
If no design system:
Design system guide: See Tokens & Foundations, Components, Governance
Fast improvements with high impact:
Implementation guide: See Quick Wins 1-5, Quick Wins 6-10, and Workflow & Planning
Tools:
# Screenshots: Use the Read tool on a screenshot file, or capture via browser automation if available.
# Color contrast
sh "${CLAUDE_PLUGIN_ROOT}/scripts/_python.sh" "${CLAUDE_PLUGIN_ROOT}/scripts/product/contrast-check.py" "#666" "#fff"
# Track design debt via native TaskCreate
# TaskCreate(
# subject="UI: {issue}",
# metadata={
# "event_type": "task",
# "chain_id": "design-review.root",
# "source_agent": "design-review",
# "priority": "P2"
# }
# )
Collaboration:
Detailed guides in refs/:
development
--- name: large-scale-migration description: How to execute a LARGE MECHANICAL change across any codebase with LEVERAGE instead of an agent-grind or hand-edits — a cross-cutting migration, refactor, rename, dialect/framework/DB port, library adoption, or bulk transform. The map→transform→gate pattern: a deterministic transform driven by a source-of-truth map, proven by a differential-equivalence gate. Use when the work is "migrate all X to Y", "rename Z everywhere", "port to a new DB/dialect/fra
testing
v11 LLM-based work-shape classifier. Replaces the regex archetype detector with the model's own reasoning. Reads the user's prompt, picks the right archetype(s) from the catalog, identifies signals (blast_radius, novelty, reversibility, etc.), and persists to SessionState so subsequent turns steer correctly. Use when: the prompt_submit hook emitted a `<wg classify-due />` directive, OR explicitly invoked at session start, OR when re-classifying after the user changes scope mid-session.
tools
v11 work-shape archetype runner. When a prompt has been routed to one of the 9 archetypes (triage, explore, specify, decide, ship, review, incident, build, migrate), this skill is the entry point. It picks the right per-archetype playbook from refs/ and executes the phase shape declared in `.claude-plugin/archetypes.json`. Use when: a `<wg archetype="X">` or `<wg archetypes>` system-reminder tag appears, an explicit "let's run the X archetype" request, or when one of the per-archetype slash commands resolves to this skill.
development
Show or set the session intent variable. Intent gates how loud the framework is — simple-edit (silent), feature/research (synthesis directive), rigor (full crew context). Auto-detected on turn 1; this skill overrides explicitly. Sticky for the session. Use when: "set intent", "intent override", "/wicked-garden:intent", "make the framework quiet", "force rigor", "what's my intent".