Ui Implement logo

Ui Implement

Organization
MadAppGang
ui-implement

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.

Overview

PublisherMadAppGang
Repositoryclaude-code
Skill nameui-implement
Stars
281
Forks
26
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by MadAppGang on GitHub. Read the source before you install it.

Installation

Install the Ui Implement AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/MadAppGang/claude-code.git /tmp/claude-code
mkdir -p .claude/skills
cp -r /tmp/claude-code/plugins/dev/skills/design/ui-implement .claude/skills/ui-implement
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ui Implement in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ui Implement on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ui Implement is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

UI Implementation Skill

Overview

This skill provides patterns for implementing UI improvements based on design analysis. It transforms review findings into code changes following Anti-AI design principles.

Relationship to Other Skills

SkillPurposeModifies Code?
dev:ui-analyseVisual analysis, issue detectionNo
dev:ui-implementApply improvements from analysisYes
dev:ui-style-formatStyle file specificationNo
dev:design-referencesReference image managementNo

Prerequisite

This skill assumes analysis has been completed using:

  • dev:ui-analyse skill
  • /dev:ui command output
  • External design review

Before implementing, ensure you have:

  1. A review document with identified issues
  2. Component path(s) to modify
  3. Understanding of the visual metaphor to apply

Implementation Workflow

Phase 1: Parse Review Document

Extract actionable items from the review document.

bash
# 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:

  • CRITICAL issues (fix immediately)
  • HIGH issues (fix before release)
  • Specific component locations
  • Recommended changes

Phase 2: Visual Context (Optional)

If Gemini available and screenshot provided, understand the current visual state.

bash
# 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:

bash
# 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

Phase 3: Apply Anti-AI Improvements

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.

Phase 4: Visual Verification (Optional)

If Gemini available after changes, verify improvements were applied correctly.

bash
# 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."

Anti-AI Design Rules

These rules transform generic, AI-generated looking UI into distinctive, human-crafted designs.

Rule 1: Break Symmetry

Rigid symmetric grids look AI-generated. Break them with asymmetric bento layouts.

tsx
// 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:

  • Use 12-column grids for flexibility
  • Vary column spans (7+5, not 6+6)
  • Use negative margins for overlap
  • Vary row heights
  • Break alignment intentionally

Rule 2: Add Texture

Flat solid colors look AI-generated. Add gradients, glass effects, and depth.

tsx
// 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:

  • Gradient backgrounds (subtle, directional)
  • Glassmorphism (backdrop-blur + semi-transparent)
  • Complex shadows with inset highlights
  • Border with alpha for subtle edges
  • Noise texture overlays

Rule 3: Dramatic Typography

Generic typography looks AI-generated. Create dramatic visual hierarchy.

tsx
// 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:

  • Fluid typography with clamp()
  • Extreme size contrasts (body 16px, hero 120px+)
  • Tight line-height for headlines (0.85-0.95)
  • Negative letter-spacing for large text
  • Gradient text with bg-clip-text
  • Mix serif/sans-serif for contrast

Rule 4: Micro-Interactions

Static elements look AI-generated. Add motion and feedback.

tsx
// 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:

  • Spring physics for natural feel
  • Subtle scale on hover (1.02-1.05)
  • Y-axis lift effect
  • Shadow glow expansion
  • Staggered animations for lists
  • Exit animations (not just enter)

Rule 5: Bespoke Colors

Default Tailwind colors look AI-generated. Create custom palettes.

tsx
// 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:

  • Custom hex colors (not Tailwind defaults)
  • Off-whites instead of pure white (#E8E4DD, #FAF9F6)
  • Rich blacks instead of pure black (#0D0D0D, #1a1a2e)
  • Color gradients across multiple stops
  • Consistent palette derived from style guide

Visual Metaphor Library

When implementing, select an appropriate visual metaphor to guide decisions.

MetaphorUse CaseKey Characteristics
Cyberpunk GlassDashboards, techNeon accents + glassmorphism + dark backgrounds
Swiss MinimalistProfessional, B2BStrict grid + high contrast + precise spacing
Neo-BrutalismCreative, boldThick borders + clashing colors + raw shapes
Organic LuxuryPremium, fashionWarm neutrals + serif typography + slow motion
Editorial MagazineMarketing, contentLarge display type + asymmetric images + whitespace

Applying a Metaphor:

  1. Choose based on brand/context
  2. Apply consistent characteristics across all changes
  3. Document choice in implementation log
  4. Verify consistency in visual check

Required Dependencies

Ensure these are installed before implementing micro-interactions:

bash
npm install framer-motion lucide-react
# or
bun add framer-motion lucide-react

Dependency Usage:

  • framer-motion: All animation and gesture handling
  • lucide-react: Icon library (consistent, customizable)

Implementation Log Format

When completing implementation, create a log documenting all changes.

markdown
## 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

Best Practices

DO

  • Read the full review document before starting
  • Apply changes systematically (one rule at a time)
  • Preserve existing accessibility features
  • Test responsive behavior after changes
  • Document all changes in implementation log
  • Use Gemini verification when available

DON'T

  • Apply all Anti-AI rules blindly (assess what's needed)
  • Break existing functionality for aesthetics
  • Ignore accessibility for visual appeal
  • Skip the implementation log
  • Forget to install required dependencies
  • Mix multiple visual metaphors inconsistently

Frequently asked questions

What does the Ui Implement AI skill do?

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.

Why use Ui Implement on TypingMind?

Because you install it once and use it with any model. Ui Implement is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ui Implement in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/MadAppGang/claude-code/tree/main/plugins/dev/skills/design/ui-implement. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ui Implement?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ui Implement?

As many as you like. As long as a model supports skills, you can use Ui Implement with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ui Implement AI skill free?

Yes. It is published on GitHub by MadAppGang under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇