Apple Native Ui logo

Apple Native Ui

Community
kemiljk
apple-native-ui

Build or review native Apple interfaces, including platform controls, accessibility, state, navigation, and macOS window behavior.

Overview

Publisherkemiljk
Repositoryskills
Skill nameapple-native-ui
Stars
64
Forks
3
Bundled files
3
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.

  • 3 bundled files

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

  • Open source

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

Installation

Install the Apple Native Ui 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/kemiljk/skills/tree/main/skills/apple-native-ui
  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/kemiljk/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/apple-native-ui .claude/skills/apple-native-ui
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Apple Native Ui 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 Apple Native Ui 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 Apple Native Ui 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.

Apple Native UI

Build and review interfaces that feel native because they use the platform's interaction, accessibility, and adaptation contracts—not because they imitate a screenshot.

Start with the target

Identify the platforms, minimum OS versions, SwiftUI versus UIKit/AppKit boundary, supported input (touch, pointer, keyboard, VoiceOver, Digital Crown, remote, eye/hand), and primary form factors. Do not apply an iPhone convention to macOS, iPad multitasking, watchOS, tvOS, or visionOS without evidence that it transfers.

Prefer system controls, semantic colors, text styles, safe-area APIs, navigation containers, and presentation APIs before custom reconstructions. Custom UI must retain the equivalent accessibility, focus, state, and cancellation behaviour.

Fresh platform guidance

Before prescribing or implementing APIs, behaviour, design conventions, or verification that may vary by SDK or OS release, search current primary Apple sources: Apple Developer Documentation, Human Interface Guidelines, and relevant WWDC sessions. Check the project's deployment target before recommending a newer API, and distinguish current Apple guidance from repository-local compatibility constraints. The examples here express durable contracts; they are not a substitute for release-specific documentation.

macOS workflow

When macOS is an intended target, read references/macos-native-workflows.md before planning, building, porting, or reviewing a non-trivial interface. It adds a Mac-specific workflow for commands, windows and documents, selection and focus, pasteboard and drag/drop, undo, state restoration, configuration, Finder interoperability, and behaviour-led verification.

Treat a Mac version as a distinct workflow even when it shares models or views with iPadOS. A resizable iPad layout is not by itself a complete Mac app.

State and identity

Own state at the narrowest stable boundary. A child that only displays data receives a value; a child that edits parent state receives a binding. Keep side effects out of body and give lists stable identities.

swift
@Observable final class ProfileModel {
    var name = ""
    var isSaving = false
}

struct ProfileScreen: View {
    @State private var model = ProfileModel()

    var body: some View {
        Form {
            TextField("Name", text: $model.name)
            Button("Save") { save() }
                .disabled(model.name.isEmpty || model.isSaving)
        }
    }
}

Do not turn an injected value into @State, use positional indices as mutable list identity, or use onTapGesture where Button, NavigationLink, Toggle, or another native control expresses the task.

Platform contracts

  • Use NavigationStack/NavigationSplitView, sheets, alerts, confirmation dialogs, and toolbars according to the target platform. Verify back, dismiss, cancel, and focus-restoration paths.
  • Use semantic colors and Dynamic Type-aware typography. Test extra-large text before adding truncation, clipping, or fixed frames.
  • Treat safe areas, split view, window resizing, rotation, external keyboard, pointer, and layout direction as input to the layout—not exceptional breakpoints.
  • Prefer @Observable, @State, @Binding, and @Bindable where deployment targets permit; gate version-specific APIs and provide a real fallback.
  • Make animations value-driven and task-preserving under Reduce Motion. Wait for the observable end state before testing or reporting it.

Accessibility

Accessibility is expressed through the native accessibility tree, not ARIA. Check VoiceOver labels, values, hints, traits, grouping, reading order, adjustable actions, focus movement, and disabled controls. Hide decorative imagery; label meaningful images and ambiguous icons.

swift
Button(action: play) {
    Image(systemName: "play.fill")
}
.accessibilityLabel("Play preview")

Image(systemName: "sparkles")
    .accessibilityHidden(true)

Read references/apple-verification.md for simulator, device, XCUITest, accessibility, and form-factor evidence. Read it before making native verification claims.

Review output

Anchor findings to a source path or an observed target/device. State whether evidence is source-only or rendered. Name the affected platform and input method; an iOS finding is not automatically a macOS finding.

Prefer / reject

PreferReject
System control with intentional stylingClickable stacks or images standing in for controls
Semantic fonts, colors, and adaptive layoutFixed dimensions that break at larger text or smaller windows
Stable IDs and explicit state ownershipIndex identity and effects hidden in body
Platform-specific verificationTreating a simulator screenshot as proof for every target
Version gates with useful fallbacksUnconditional new APIs that silently drop supported users

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 Apple Native Ui AI skill do?

Build or review native Apple interfaces, including platform controls, accessibility, state, navigation, and macOS window behavior.

Why use Apple Native Ui on TypingMind?

Because you install it once and use it with any model. Apple Native Ui 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 Apple Native Ui in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kemiljk/skills/tree/main/skills/apple-native-ui. 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 Apple Native Ui?

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 Apple Native Ui?

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

Is the Apple Native Ui AI skill free?

Yes. It is published on GitHub by kemiljk 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 👇