Ios Ui Craft logo

Ios Ui Craft

Organization
Prisma-Labs-Dev
ios-ui-craft

Production-grade SwiftUI with Apple Design Award-quality aesthetics. Use when building visually striking iOS interfaces — screens, components, redesigns. Screenshot-driven visual iteration, Liquid Glass (iOS 26+), bold design direction. For design advice without code, use ios-design-consultant instead.

Overview

PublisherPrisma-Labs-Dev
Repositoryapple-skills
Skill nameios-ui-craft
Stars
348
Forks
21
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 Prisma-Labs-Dev on GitHub. Read the source before you install it.

Installation

Install the Ios Ui Craft 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.
    https://github.com/Prisma-Labs-Dev/apple-skills/tree/main/disabled-skills/ios-ui-craft
  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/Prisma-Labs-Dev/apple-skills.git /tmp/apple-skills
mkdir -p .claude/skills
cp -r /tmp/apple-skills/disabled-skills/ios-ui-craft .claude/skills/ios-ui-craft
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ios Ui Craft 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 Ios Ui Craft 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 Ios Ui Craft 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.

iOS UI Craft

Create distinctive, Apple Design Award-worthy iOS interfaces. This skill produces real, working SwiftUI code with exceptional attention to aesthetic details and creative choices that avoid generic AI-generated aesthetics.

The user provides iOS requirements: a screen, component, view, or interface to build. They may include context about the purpose, audience, or technical constraints.

Design Thinking

Before writing ANY code, understand the context and commit to a BOLD aesthetic direction:

  1. Purpose: What problem does this interface solve? Who uses it?
  2. Tone: Pick a direction: calm/serene, playful/energetic, premium/refined, utilitarian/focused, editorial/magazine, brutalist/raw, warm/organic, cold/technical. Commit fully.
  3. Inspiration: Which Apple apps set the bar? (Weather, Health, Fitness, Notes, Apple TV, Journal)
  4. Differentiation: What makes this UNFORGETTABLE? What's the one thing users will remember?
  5. Glass Philosophy: Is glass framing content or would it compete with it?

CRITICAL: Choose a clear conceptual direction and execute it with precision. Bold maximalism and refined minimalism both work—the key is intentionality, not intensity.

Then implement working SwiftUI code that is:

  • Production-grade and functional
  • Visually striking and memorable
  • Cohesive with a clear aesthetic point-of-view
  • Meticulously refined in every detail

Anti-Patterns: What to Avoid

These are hallmarks of generic AI-generated iOS design. NEVER do these:

Anti-PatternWhy It's BadInstead
Boring solid backgroundsNo depth or atmosphereGradients, subtle textures, or layered colors
System fonts everywhereNo typographic intentionIntentional hierarchy, consider display fonts
Cookie-cutter tab barsNo personalityCustom styling, meaningful icons
Purple/indigo gradientsQuintessential AI slopFind a distinctive, contextual palette
Flat, lifeless interactionsNo delightHaptics, spring animations, feedback
Glass on everythingDefeats the purposeGlass only for controls/navigation layer
Ignoring content layerGlass where it doesn't belongGlass frames content, never obscures
Generic card layoutsWhite rectangles with shadowsContext-specific, purposeful containers
Emojis as design elementsLazy, unprofessionalSF Symbols, custom assets
Evenly distributed colorsTimid, uncommittedDominant color with sharp accents

iOS Aesthetics Guidelines

Focus on:

  • Typography: Create clear hierarchy. Display fonts for impact, proper weight progression. Don't default to system everywhere—make intentional choices. Consider SF Pro Display for headers, custom fonts for brand identity.
  • Color & Theme: Commit to a cohesive aesthetic. Dominant colors with sharp accents outperform timid, evenly-distributed palettes. Dark mode often produces more distinctive results. Design dark first, then adapt to light.
  • Motion: Spring/bouncy animations are the new default. Morph between states, don't swap. Add haptics to every meaningful interaction. Use .bouncy not .easeInOut.
  • Spatial Composition: Intentional spacing (8pt grid). Breathing room where needed, density where appropriate. Concentric corners that match device hardware.
  • Backgrounds & Depth: Create atmosphere. Gradients, subtle layers, radial glows. Never flat white unless that's a deliberate minimal choice.

The Three Principles

PrincipleDescription
HierarchyControls float above content. Glass frames, never obscures. Content is king.
HarmonySoftware design aligns with hardware. Concentric corners. Fluid gestures.
ConsistencyAdapt fluidly across iPhone, iPad, Mac. Same identity, contextual expression.

Required Reading

Before implementing, read the shared Liquid Glass reference for API patterns:

skills/ios-liquid-glass/ - Core Liquid Glass API, code patterns, navigation patterns, animation philosophy, haptics

This reference contains the technical implementation details. This skill provides the aesthetic vision; the reference provides the code patterns.

Typography That Speaks

Don't default to system fonts for everything. Create typographic hierarchy:

swift
// Display fonts for headers
Text("Dashboard")
    .font(.largeTitle.bold())
    .foregroundStyle(.primary)

// Secondary information
Text("Last updated 5 min ago")
    .font(.subheadline)
    .foregroundStyle(.secondary)

// Consider custom fonts for brand identity
Text("Premium")
    .font(.custom("PlayfairDisplay-Bold", size: 32))

Font Recommendations

Use CaseOptions
DisplaySF Pro Display, New York, custom serif
BodySF Pro Text (system), custom sans
TechnicalSF Mono, custom monospace
EditorialNew York, custom serif with character

Color with Intention

Dominant + Accent

Don't distribute color evenly. Choose:

  • One dominant that defines the brand/mood
  • Sharp accents for actions and highlights
  • Neutral base for content readability

Dark Mode First

Dark mode often produces more distinctive results. Design dark, then adapt to light.

swift
// Semantic colors that adapt
.foregroundStyle(.primary)
.foregroundStyle(.secondary)
.background(.background)

// Accent with purpose
.tint(.accentColor)

Development Loop: Screenshot-Driven Iteration

Never submit UI work without visually verifying it. Use the screenshot script to iterate until the screen is both functional and beautiful.

bash
# Screenshot simulator
xcrun simctl io booted screenshot /tmp/screenshot.png && sips --resampleHeightWidthMax 1800 /tmp/screenshot.png

The loop:

  1. Implement your changes
  2. Screenshot the simulator
  3. Evaluate critically — is this share-worthy?
  4. Iterate if not — fix and screenshot again

Keep iterating until:

  • You'd proudly screenshot it to show a friend
  • It could appear in an App Store feature
  • It feels like it belongs on Apple's marketing materials

This is the quality bar: share-worthy, award-worthy.

Quality Checklist

Before considering UI complete:

  • Committed to a clear aesthetic direction (not generic)
  • Glass applied only to navigation layer (not content)
  • Haptics on all meaningful interactions
  • Spring/bouncy animations (not linear)
  • SF Symbols (not emojis or random icons)
  • Dark mode tested and polished
  • Typography hierarchy clear and intentional
  • Colors are purposeful, not default blue
  • Morphing transitions where applicable
  • Loading states animated
  • Empty states designed
  • Error states helpful and styled
  • Accessibility settings respected
  • Screenshot taken and visually verified
  • Would I screenshot this to show someone? (If no, iterate)

The Mandate

Remember: Claude is capable of extraordinary creative work. Don't settle for "working." Push for memorable.

Every interface should have:

  1. A point of view - A clear aesthetic direction
  2. Intentional details - Nothing accidental
  3. Emotional resonance - Users feel something
  4. Technical excellence - Smooth, performant, accessible

The goal is an app worthy of an Apple Design Award—an app that feels genuinely designed, not generated.

Related Skills

  • /ios-dev - Start here for any iOS task — coordinates guides, correctness checks, and API references
  • /ios-design-consultant - For design questions before coding

Frequently asked questions

What does the Ios Ui Craft AI skill do?

Production-grade SwiftUI with Apple Design Award-quality aesthetics. Use when building visually striking iOS interfaces — screens, components, redesigns. Screenshot-driven visual iteration, Liquid Glass (iOS 26+), bold design direction. For design advice without code, use ios-design-consultant instead.

Why use Ios Ui Craft on TypingMind?

Because you install it once and use it with any model. Ios Ui Craft 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 Ios Ui Craft in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Prisma-Labs-Dev/apple-skills/tree/main/disabled-skills/ios-ui-craft. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ios Ui Craft?

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 Ios Ui Craft?

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

Is the Ios Ui Craft AI skill free?

Yes. It is published on GitHub by Prisma-Labs-Dev 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 👇