Hig Platforms logo

Hig Platforms

Organization
raintree-technology
hig-platforms

Apple Human Interface Guidelines for platform-specific design. Use this skill when the user asks about "designing for iOS", "iPad app design", "macOS design", "tvOS", "visionOS", "watchOS", "Apple platform", "which platform", platform differences, platform-specific conventions, or multi-platform app design. Also use when the user says "should I design differently for iPad vs iPhone", "how does my app work on visionOS", "what's different about macOS apps", "porting my app to another platform", "universal app design", or "what input methods does this platform use". Cross-references: hig-foundations for shared design foundations, hig-patterns for interaction patterns, hig-components-layout for navigation structures, hig-components-content for content display.

Overview

Publisherraintree-technology
Repositoryhig-doctor
Skill namehig-platforms
Stars
148
Forks
10
Bundled files
7
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.

  • 7 bundled files

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

  • Open source

    Published by raintree-technology on GitHub. Read the source before you install it.

Installation

Install the Hig Platforms 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/raintree-technology/hig-doctor/tree/main/skills/hig-platforms
  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/raintree-technology/hig-doctor.git /tmp/hig-doctor
mkdir -p .claude/skills
cp -r /tmp/hig-doctor/skills/hig-platforms .claude/skills/hig-platforms
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hig Platforms 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 Hig Platforms 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 Hig Platforms 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 HIG: Platform Design

Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered.

Key Principles

  1. Each platform has a distinct identity. Do not port designs between platforms. Respect each platform's conventions, interaction models, and user expectations.

  2. iOS: touch-first. Direct manipulation on a handheld screen. Optimize for one-handed use. Navigation uses tab bars and push/pop stacks.

  3. iPadOS: expanded canvas. Support Split View, Slide Over, and Stage Manager. Use sidebars and multi-column layouts. Support pointer and keyboard alongside touch.

  4. macOS: pointer and keyboard. Dense information display is acceptable. Use menu bars, toolbars, and keyboard shortcuts extensively. Windows are resizable with precise control.

  5. tvOS: remote and focus. Viewed from a distance. Design for the Siri Remote with focus-based navigation. Large text, simple layouts, linear navigation.

  6. visionOS: spatial interaction. 3D environment using windows, volumes, and spaces. Eye tracking for targeting, indirect gestures for interaction. Respect ergonomic comfort zones.

  7. watchOS: glanceable and brief. Information consumable at a glance. Brief interactions. Digital Crown, haptics, and complications for timely content.

  8. Games: own paradigm. Free to define in-game interaction models, but still respect platform conventions for system interactions (notifications, accessibility, controllers).

Reference Index

ReferenceTopicKey content
designing-for-ios.mdiOSTouch, tab bars, navigation stacks, gestures, screen sizes, safe areas
designing-for-ipados.mdiPadOSMultitasking, sidebars, pointer, keyboard, Apple Pencil, Stage Manager
designing-for-macos.mdmacOSMenu bars, toolbars, window management, keyboard shortcuts, dense layouts, Dock
designing-for-tvos.mdtvOSFocus engine, Siri Remote, lean-back experience, content-forward, parallax
designing-for-visionos.mdvisionOSSpatial computing, windows/volumes/spaces, eye tracking, hand gestures, depth
designing-for-watchos.mdwatchOSGlanceable UI, Digital Crown, complications, notifications, haptics
designing-for-games.mdGamesControllers, immersive experiences, platform-specific conventions, accessibility

Decision Framework

  1. Identify the primary use context. On the go (iOS/watchOS), at a desk (macOS), on the couch (tvOS), spatial environment (visionOS)?

  2. Match input to interaction. Touch for direct manipulation, pointer for precision, gaze+gesture for spatial, Digital Crown for quick scrolling, remote for focus navigation.

  3. Adapt, don't replicate. A macOS sidebar becomes a tab bar on iPhone. A visionOS volume has no equivalent on watchOS. Translate intent, not implementation.

  4. Leverage platform strengths. Live Activities on iOS, Desktop Widgets on macOS, complications on watchOS, immersive spaces on visionOS.

  5. Maintain brand consistency while respecting each platform's visual language and interaction patterns.

Output Format

  1. Platform-specific recommendations citing relevant HIG sections.
  2. Platform differences table comparing navigation, input, layout, and conventions.
  3. Implementation notes per platform including recommended APIs and adaptation strategies.

Questions to Ask

  1. Which platforms are you targeting?
  2. New app or adapting an existing one? If existing, which platform is the base?
  3. SwiftUI or UIKit/AppKit?
  4. Need to support older OS versions?
  5. Primary use context? (On the go, desk, couch, spatial, glanceable?)

Related Skills

  • hig-foundations -- Shared principles (color, typography, accessibility, layout) across platforms
  • hig-patterns -- Interaction patterns that manifest differently per platform
  • hig-components-layout -- Navigation structures (tab bars, sidebars, split views) that vary by platform
  • hig-components-content -- Content display that adapts across platforms

Built by Raintree Technology · More developer tools

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 Hig Platforms AI skill do?

Apple Human Interface Guidelines for platform-specific design. Use this skill when the user asks about "designing for iOS", "iPad app design", "macOS design", "tvOS", "visionOS", "watchOS", "Apple platform", "which platform", platform differences, platform-specific conventions, or multi-platform app design. Also use when the user says "should I design differently for iPad vs iPhone", "how does my app work on visionOS", "what's different about macOS apps", "porting my app to another platform", "universal app design", or "what input methods does this platform use". Cross-references: hig-found...

Why use Hig Platforms on TypingMind?

Because you install it once and use it with any model. Hig Platforms 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 Hig Platforms in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/raintree-technology/hig-doctor/tree/main/skills/hig-platforms. 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 Hig Platforms?

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 Hig Platforms?

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

Is the Hig Platforms AI skill free?

Yes. It is published on GitHub by raintree-technology 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 👇