Swiftui Design Skill logo

Swiftui Design Skill

Community
Wholiver
swiftui-design-skill

SwiftUI frontend visual design skill. Creates beautiful, distinctive iOS/macOS interfaces that avoid generic AI slop patterns. Covers design direction, layout systems, typography, color, spacing, brand integration, and design review. Use when designing new SwiftUI views, reviewing UI quality, creating iOS prototypes, choosing visual styles, improving app aesthetics, or when the UI looks generic or AI-generated.

Overview

PublisherWholiver
Repositoryswiftui-design-skill
Skill nameswiftui-design-skill
Stars
209
Forks
10
Bundled files
9
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.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

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

Installation

Install the Swiftui Design Skill 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/Wholiver/swiftui-design-skill/tree/main
  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/Wholiver/swiftui-design-skill.git \
  .claude/skills/swiftui-design-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Swiftui Design Skill 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 Swiftui Design Skill 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 Swiftui Design Skill 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.

SwiftUI Design Skill

TL;DR: Design SwiftUI apps that look intentionally crafted, not AI-generated. Follow the 6 Anti-Slop Rules, use the Design Direction workflow when requirements are vague, and always pass the 5-Dimension Review before shipping.

When to Use

  • Designing new SwiftUI views or screens from scratch
  • Reviewing or improving existing UI quality
  • Creating iOS app prototypes or mockups
  • Choosing a visual style or design direction
  • Integrating brand assets into SwiftUI
  • When someone says "the UI looks generic" or "make it look better"
  • When building a new feature that needs visual design

When NOT to Use

  • Pure backend / API work with no UI
  • Fixing SwiftUI compilation errors (use swiftui-expert-skill instead)
  • Performance optimization of existing views (use swiftui-expert-skill)
  • Accessibility compliance only (use swiftui-expert-skill's accessibility topic)

Prerequisites

  • Xcode 16+ with iOS 18+ / macOS 15+ SDK
  • SwiftUI framework (not UIKit unless explicitly requested)
  • Familiarity with SwiftUI view hierarchy and modifiers

Core Design Philosophy

These 6 principles guide every design decision. They are distilled from real-world design practice and anti-patterns observed in AI-generated UI.

Principle 1: Start From Context, Never Blank

Before designing any screen, ask:

  • Is there an existing design system, UI kit, or Figma file?
  • Is there an existing codebase with established visual language?
  • Are there brand guidelines or a style guide?

If no context exists, create a brand-spec.md first (see Brand Asset Protocol below).

Principle 2: Junior Designer Mode — Hypothesize Early, Iterate Fast

Don't wait for the "perfect" design. Show hypotheses with placeholders early:

  • Gray boxes for images are better than bad AI-generated SVGs
  • System fonts with good spacing > custom fonts with bad spacing
  • A rough but honest layout > a polished but generic one

Principle 3: Offer Variations, Not Finals

Always present 2-3 distinct design directions, not one "final answer." Each variation should:

  • Represent a different design philosophy (e.g., editorial, functional, expressive)
  • Have a clear rationale for why it works
  • Be visually distinct — not just color swaps

Principle 4: Placeholder > Bad Implementation

If you cannot source a real asset (icon, image, illustration):

  • Use a clean gray placeholder with clear labeling
  • Never use AI-generated SVG clipart
  • Never use emoji as icon substitutes in production UI
  • For icons, prefer SF Symbols (Apple's built-in icon library)

Principle 5: System First, Don't Fill

Every element must earn its place. Before adding any UI element, ask:

  • Does this serve the user's goal?
  • Can this be combined with something else?
  • What happens if I remove it?

Whitespace is a feature, not emptiness.

Principle 6: Anti-AI-Slop

These patterns are banned in production UI. See references/anti-ai-slop.md for detailed rules.

Banned visual patterns:

  • ❌ Purple-to-blue gradient backgrounds
  • ❌ Emoji as functional icons
  • ❌ Rounded cards with left-border accent color
  • ❌ Generic "hero section" with centered text over gradient
  • ❌ Inter/Roboto as display fonts on Apple platforms
  • ❌ Neon-on-dark "cyber" aesthetic (#0D1117 base)
  • ❌ Symmetric 3-column feature grids
  • ❌ AI-drawn SVG illustrations or CSS silhouettes

What to do instead:

  • ✅ Single warm accent color on neutral background
  • ✅ SF Symbols for icons, or custom icon set
  • ✅ Serif display font (e.g., New York, Georgia) for headings
  • ✅ Restrained info density — let content breathe
  • ✅ One signature detail at 120% effort per screen
  • ✅ Real photography or clean placeholders

Brand Asset Protocol

When building UI for a specific brand, follow this 5-step hard flow:

  1. Ask — Request brand guidelines, logo files, color palette, typography
  2. Search — If not provided, search the web for "[brand name] brand guidelines"
  3. Download — Get actual asset files (PNG/SVG logos, font files)
  4. Verify — Confirm colors match official sources (check hex values)
  5. Write brand-spec.md — Document: primary/secondary colors, fonts, logo usage rules, spacing tokens

Quality threshold: 5 real brand colors, 10 verified design tokens, 2 font families, 8pt spacing grid.

If no brand exists, create a brand-spec.md with:

  • 1 primary accent color (warm, not purple-blue gradient)
  • 1 neutral palette (grays with warm undertone)
  • 1 display font + 1 body font (SF Pro default is fine)
  • 8pt spacing grid

Design Direction Workflow

When requirements are vague or the user asks "what style should we use?", follow this workflow:

Phase 1: Understand Context (5 min)

  1. Ask: What is the app? Who is the user? What platform (iOS/macOS/watchOS)?
  2. Ask: Any reference apps or websites they admire?
  3. Check: Existing design system or brand assets?

Phase 2: Recommend 3 Directions

Present 3 distinct design philosophies from different schools:

SchoolExample Directions
InformationClean data-first, chart-heavy, Bloomberg-style
EditorialMagazine layout, serif typography, generous whitespace
ExpressiveBold color, asymmetric layout, motion-forward
FunctionalDense utility, monospace accents, minimal decoration
Warm MinimalSoft neutrals, rounded shapes, subtle texture

Phase 3: Present Visual Anchors

For each direction, describe:

  • Color palette (3-5 colors with hex values)
  • Typography pairing (display + body)
  • Layout density (comfortable / compact / spacious)
  • Signature detail (one standout element per screen)

Phase 4: Let User Choose

Present options clearly. After choice, lock in the design system.


SwiftUI Design Workflow

Step 1: Define the Design System (Before Coding)

Create or confirm these design tokens:

swift
// Requires: references/swift-extensions.md (Color(hex:) extension)
// DesignTokens.swift
enum DesignTokens {
    // Colors
    static let accent = Color(hex: "E85D3A")      // Warm coral
    static let background = Color(hex: "FAFAF8")   // Warm white
    static let textPrimary = Color(hex: "1A1A1A")   // Near-black
    static let textSecondary = Color(hex: "6B6B6B") // Muted gray
    
    // Typography
    static let displayFont = "New York"  // Serif for headings
    static let bodyFont = "SF Pro"       // System default
    
    // Spacing (8pt grid)
    static let spaceXS: CGFloat = 4
    static let spaceS: CGFloat = 8
    static let spaceM: CGFloat = 16
    static let spaceL: CGFloat = 24
    static let spaceXL: CGFloat = 32
    static let spaceXXL: CGFloat = 48
    
    // Corner radius
    static let radiusS: CGFloat = 8
    static let radiusM: CGFloat = 12
    static let radiusL: CGFloat = 16
}

Step 2: Build the Layout Hierarchy

Follow the layout patterns in references/layout-patterns.md:

  • Start with the primary content container
  • Use VStack for vertical flow, HStack for horizontal
  • Use LazyVGrid / LazyHGrid for grid layouts
  • Use ScrollView with .scrollTargetBehavior(.paging) for paged content
  • Avoid GeometryReader — prefer containerRelativeFrame (iOS 17+)

Step 3: Apply Typography Hierarchy

Follow references/typography-color.md:

  • Display (screen titles): Serif font, 28-34pt, bold
  • Heading (section titles): Sans-serif, 20-24pt, semibold
  • Body (content text): Sans-serif, 15-17pt, regular
  • Caption (labels, metadata): Sans-serif, 12-13pt, secondary color

Step 4: Add the Signature Detail

Each screen should have ONE element that goes 120% — a custom animation, a unique layout choice, a distinctive color moment. This is what makes the design memorable.

Examples:

  • A custom pull-to-refresh with brand-colored animation
  • A card that expands with a spring animation on tap
  • A header that uses the brand's display font at an oversized scale
  • A subtle parallax effect on scroll

Step 5: Review Against Checklist

Before shipping, run the 5-Dimension Review (see references/design-review.md).


Common Mistakes to Avoid

MistakeFix
Using UIColor or NSColorUse Color (SwiftUI native)
UIScreen.main.bounds for sizingUse containerRelativeFrame or geometry-based modifiers
Default blue tint everywhereDefine a custom accent color in design tokens
No spacing system (random padding values)Use 8pt grid: 4, 8, 16, 24, 32, 48
Emoji as iconsUse SF Symbols or custom icon assets
Purple-blue gradient backgroundUse solid warm neutrals
All content in one giant VStackBreak into semantic sections with clear hierarchy
No visual hierarchy (everything same size)Use 3+ type scales (display, heading, body, caption)
Ignoring dark modeDefine semantic colors that adapt to appearance
Generic "Welcome!" hero sectionShow actual content immediately

Quick Reference: Topic Router

TopicReference File
Anti-AI-Slop Rules (detail)references/anti-ai-slop.md
Layout Patterns & Gridsreferences/layout-patterns.md
Typography & Color Systemsreferences/typography-color.md
5-Dimension Design Reviewreferences/design-review.md
Swift Extensions (required)references/swift-extensions.md
Brand Spec Templatetemplates/brand-spec.md

Validation Checklist

Before considering any SwiftUI design complete, verify:

  • Design tokens defined (colors, fonts, spacing)
  • No banned AI-slop patterns present
  • Typography has clear hierarchy (3+ scales)
  • Spacing follows 8pt grid
  • Dark mode colors defined and tested
  • One signature detail per screen
  • SF Symbols used for icons (not emoji)
  • Minimum 44×44pt tap targets
  • No GeometryReader or UIScreen.main.bounds
  • 5-Dimension Review score ≥ 7/10 on all dimensions

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Swiftui Design Skill AI skill do?

SwiftUI frontend visual design skill. Creates beautiful, distinctive iOS/macOS interfaces that avoid generic AI slop patterns. Covers design direction, layout systems, typography, color, spacing, brand integration, and design review. Use when designing new SwiftUI views, reviewing UI quality, creating iOS prototypes, choosing visual styles, improving app aesthetics, or when the UI looks generic or AI-generated.

Why use Swiftui Design Skill on TypingMind?

Because you install it once and use it with any model. Swiftui Design Skill 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 Swiftui Design Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Wholiver/swiftui-design-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Swiftui Design Skill?

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 Swiftui Design Skill?

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

Is the Swiftui Design Skill AI skill free?

Yes. It is published on GitHub by Wholiver 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 👇