plugins/dev/skills/design/ui-implement/SKILL.md
Patterns for implementing UI improvements based on design analysis. Works with review documents from dev:ui-analyse or /dev:ui command. Includes Anti-AI design rules and visual verification.
npx skillsauth add madappgang/claude-code ui-implementInstall 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 patterns for implementing UI improvements based on design analysis. It transforms review findings into code changes following Anti-AI design principles.
| Skill | Purpose | Modifies Code? | |-------|---------|----------------| | dev:ui-analyse | Visual analysis, issue detection | No | | dev:ui-implement | Apply improvements from analysis | Yes | | dev:ui-style-format | Style file specification | No | | dev:design-references | Reference image management | No |
This skill assumes analysis has been completed using:
dev:ui-analyse skill/dev:ui command outputBefore implementing, ensure you have:
Extract actionable items from the review document.
# Extract actionable items from review
parse_review() {
local review_path="$1"
# Extract CRITICAL and HIGH issues
grep -A 2 "^\[CRITICAL\]" "$review_path"
grep -A 2 "^\[HIGH\]" "$review_path"
}
What to Look For:
If Gemini available and screenshot provided, understand the current visual state.
# Understand current visual state
npx claudish --model "$GEMINI_MODEL" --image "$CURRENT_SCREENSHOT" --quiet --auto-approve <<< "
Describe the current UI implementation:
1. Layout structure
2. Color scheme
3. Typography
4. Animation presence
5. Areas needing improvement
Output as structured data for implementation."
Provider Detection:
# Check providers in priority order
if [[ -n "$GEMINI_API_KEY" ]]; then
GEMINI_MODEL="g/gemini-3-pro-preview"
elif [[ -n "$OPENROUTER_API_KEY" ]]; then
GEMINI_MODEL="or/google/gemini-3-pro-preview"
elif [[ -n "$GOOGLE_APPLICATION_CREDENTIALS" ]]; then
GEMINI_MODEL="vertex/gemini-3-pro-preview"
else
GEMINI_MODEL="" # Text-only mode
fi
Apply the five core Anti-AI design rules to transform generic UI into distinctive design.
See Anti-AI Design Rules section below for detailed patterns.
If Gemini available after changes, verify improvements were applied correctly.
# Verify improvements
npx claudish --model "$GEMINI_MODEL" --image "$NEW_SCREENSHOT" --quiet --auto-approve <<< "
Verify these improvements were applied:
1. Asymmetric layout: {expected}
2. Texture/depth: {expected}
3. Typography drama: {expected}
4. Micro-interactions: {expected}
5. Bespoke colors: {expected}
Score 1-10 and note any remaining issues."
These rules transform generic, AI-generated looking UI into distinctive, human-crafted designs.
Rigid symmetric grids look AI-generated. Break them with asymmetric bento layouts.
// BEFORE: Symmetric grid
<div className="grid grid-cols-3 gap-4">
// AFTER: Asymmetric bento
<div className="grid grid-cols-12 gap-6">
<div className="col-span-7 row-span-2" />
<div className="col-span-5" />
<div className="col-span-3" />
<div className="col-span-2 -mt-8" />
</div>
Key Techniques:
Flat solid colors look AI-generated. Add gradients, glass effects, and depth.
// BEFORE: Flat
<div className="bg-white rounded-lg">
// AFTER: Textured
<div className="
bg-gradient-to-br from-white/80 to-white/40
backdrop-blur-xl
border border-white/20
shadow-[0_8px_32px_rgba(0,0,0,0.08),inset_0_1px_0_rgba(255,255,255,0.6)]
">
Key Techniques:
Generic typography looks AI-generated. Create dramatic visual hierarchy.
// BEFORE: Generic
<h1 className="text-2xl font-bold">Welcome</h1>
// AFTER: Dramatic
<h1 className="
text-[clamp(4rem,15vw,12rem)]
font-serif font-thin tracking-[-0.04em]
leading-[0.85]
bg-gradient-to-r from-zinc-900 via-zinc-600 to-zinc-900
bg-clip-text text-transparent
">
Welcome
</h1>
Key Techniques:
Static elements look AI-generated. Add motion and feedback.
// BEFORE: Static
<button className="bg-blue-500 hover:bg-blue-600">
// AFTER: Reactive
<motion.button
whileHover={{ scale: 1.02, y: -2 }}
whileTap={{ scale: 0.98 }}
transition={{ type: "spring", stiffness: 400, damping: 17 }}
className="
bg-gradient-to-r from-violet-600 to-indigo-600
hover:shadow-[0_0_40px_rgba(139,92,246,0.4)]
transition-shadow duration-300
"
>
Key Techniques:
Default Tailwind colors look AI-generated. Create custom palettes.
// BEFORE: Default palette
<div className="bg-blue-500 text-white">
// AFTER: Bespoke palette
<div className="
bg-[#0D0D0D]
text-[#E8E4DD]
bg-gradient-to-br
from-[#1a1a2e] via-[#16213e] to-[#0f3460]
">
Key Techniques:
When implementing, select an appropriate visual metaphor to guide decisions.
| Metaphor | Use Case | Key Characteristics | |----------|----------|---------------------| | Cyberpunk Glass | Dashboards, tech | Neon accents + glassmorphism + dark backgrounds | | Swiss Minimalist | Professional, B2B | Strict grid + high contrast + precise spacing | | Neo-Brutalism | Creative, bold | Thick borders + clashing colors + raw shapes | | Organic Luxury | Premium, fashion | Warm neutrals + serif typography + slow motion | | Editorial Magazine | Marketing, content | Large display type + asymmetric images + whitespace |
Applying a Metaphor:
Ensure these are installed before implementing micro-interactions:
npm install framer-motion lucide-react
# or
bun add framer-motion lucide-react
Dependency Usage:
framer-motion: All animation and gesture handlinglucide-react: Icon library (consistent, customizable)When completing implementation, create a log documenting all changes.
## Implementation Log
**Component**: {component_path}
**Session**: {session_id}
**Date**: {timestamp}
### Changes Applied
1. **{Issue from Review}**
- Before: {description}
- After: {description}
- Code: {file:line}
2. **{Issue from Review}**
- Before: {description}
- After: {description}
- Code: {file:line}
### Visual Metaphor
{metaphor_name}: {brief explanation of why chosen and how applied}
### Anti-AI Rules Applied
- [x] Rule 1: Break Symmetry - {how applied}
- [x] Rule 2: Add Texture - {how applied}
- [x] Rule 3: Dramatic Typography - {how applied}
- [ ] Rule 4: Micro-Interactions - {not applicable or how applied}
- [x] Rule 5: Bespoke Colors - {how applied}
### Dependencies Added
{list if any, or "None"}
### Verification Status
- [ ] Visual verified with Gemini
- [ ] Manual testing recommended
- [ ] Responsive breakpoints checked
- [ ] Accessibility preserved
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)
tools
Plugin release process for MAG Claude Plugins marketplace. Covers version bumping, marketplace.json updates, git tagging, and common mistakes. Use when releasing new plugin versions or troubleshooting update issues.
testing
Fetch trending programming models from OpenRouter rankings. Use when selecting models for multi-model review, updating model recommendations, or researching current AI coding trends. Provides model IDs, context windows, pricing, and usage statistics from the most recent week.