Accessibility Generator logo

Accessibility Generator

Community
rshankras
accessibility-generator

Generate accessibility infrastructure for VoiceOver, Dynamic Type, and accessibility features. Use when improving app accessibility, adding accessibility labels and hints, or auditing compliance.

Overview

Publisherrshankras
Repositoryclaude-code-apple-skills
Skill nameaccessibility-generator
Stars
744
Forks
70
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Accessibility Generator 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/rshankras/claude-code-apple-skills.git /tmp/claude-code-apple-skills
mkdir -p .claude/skills
cp -r /tmp/claude-code-apple-skills/skills/generators/accessibility-generator .claude/skills/accessibility-generator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Accessibility Generator 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 Accessibility Generator 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 Accessibility Generator 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.

Accessibility Generator

Generate accessibility infrastructure for VoiceOver, Dynamic Type, and accessibility features.

When This Skill Activates

  • User wants to improve app accessibility
  • User mentions VoiceOver, Dynamic Type, or accessibility
  • User needs to add accessibility labels and hints
  • User wants to audit accessibility compliance

Pre-Generation Checks

bash
# Check existing accessibility usage
grep -r "accessibilityLabel\|accessibilityHint\|AccessibilityFocused" --include="*.swift" | head -5

Key Features

Accessibility Labels

swift
Image(systemName: "heart.fill")
    .accessibilityLabel("Favorite")
    .accessibilityHint("Double tap to remove from favorites")

Dynamic Type Support

swift
Text("Title")
    .font(.title)  // Scales automatically
    .dynamicTypeSize(...DynamicTypeSize.accessibility3)  // Limit max size

Reduce Motion

swift
@Environment(\.accessibilityReduceMotion) private var reduceMotion

withAnimation(reduceMotion ? nil : .spring()) {
    // Animation
}

VoiceOver Groups

swift
VStack {
    Text("Item Name")
    Text("$9.99")
}
.accessibilityElement(children: .combine)

Visual Accessibility: Numbers and APIs (WWDC20)

SettingThreshold / APIWhat to do
Contrast4.5:1 minimum ("generally the lowest acceptable ratio"); ~7.5:1 for comfort on dark backgroundsCheck text and glyphs against their actual backgrounds
Differentiate Without ColorUIAccessibility.shouldDifferentiateWithoutColorAdd shapes/symbols wherever color is the only signal (red/green states)
Button ShapesUIAccessibility.buttonShapesEnabled + its change notificationShow borders/underlines on plain-text buttons when on
Increase ContrastSystem colors adapt for free; custom colors need a "High Contrast" variant in the asset catalogNever ship a single hex for both modes
Dynamic TypepreferredContentSizeCategoryNever truncate — set line count to 0 so text wraps; reflow layout at accessibility sizes
Bold TextUIAccessibility.isBoldTextEnabledFree with system text styles; custom fonts must swap weights manually
Reduce MotionisReduceMotionEnabled, prefersCrossFadeTransitionsGate animations, parallax, and video autoplay; prefer cross-fades over sliding transitions
Smart Invert.accessibilityIgnoresInvertColors()Apply to photos, videos, and full-color icons so they don't invert
Reduce TransparencyUIAccessibility.isReduceTransparencyEnabledRender blur/vibrancy backgrounds as opaque

SwiftUI mirrors most of these as environment values (\.accessibilityReduceMotion above, plus \.accessibilityDifferentiateWithoutColor, \.legibilityWeight, \.accessibilityReduceTransparency).

Deep Patterns (accessibility-patterns.md)

The full recipes live in accessibility-patterns.md:

  • Label-writing rules — context ladder, no control types, succinctness, localize (WWDC19 254)
  • Custom actions doctrine — clutter/speed rationale, hide replaced buttons, widget intents (WWDC19 250, WWDC24 10073)
  • Custom rotors, UIKit and SwiftUI (WWDC20 10116, WWDC21 10119)
  • Data-rich rows via the More Content rotor / AXCustomContent (WWDC21 10121)
  • Announcements with priorities, .isToggle, zoom, direct touch, block-based setters (WWDC23 10036)
  • Custom-control technique selection: adjustable vs passthrough vs custom actions vs direct touch (WWDC26 220)
  • Switch Control grouping and timeout rules (WWDC20 10019); Full Keyboard Access (WWDC21 10120)
  • Reading-app text navigation, page turns, UITextInput adoption (WWDC26 219)

Inclusive Design Principles (WWDC25)

  • About 1 in 7 people has a disability — accessibility features are mainstream features.
  • Provide information through multiple senses: captions for audio, audible/haptic paths for visual cues.
  • Support multiple input methods — touch, keyboard, voice, switch — for every action.
  • Larger Text scales text up to ~3x — layouts must reflow, not clip or overlap.
  • Inclusion is iterative, not one-time — re-audit each release, not just before launch.

Generated Files

Sources/Accessibility/
├── AccessibilityModifiers.swift   # Custom view modifiers
├── AccessibilityHelpers.swift     # Label builders
└── AccessibilityStrings.swift     # Localized labels

Audit Checklist

  • All interactive elements have labels
  • Images have descriptions or are hidden decoratively
  • Color is not the only indicator
  • Touch targets are at least 44×44 points
  • Dynamic Type is supported
  • Reduce Motion is respected
  • VoiceOver order is logical
  • Custom controls expose purpose, value, actions, and feedback (WWDC26 220)
  • Automated audit + Nutrition Label evaluation — see ios/accessibility-audit

References

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 Accessibility Generator AI skill do?

Generate accessibility infrastructure for VoiceOver, Dynamic Type, and accessibility features. Use when improving app accessibility, adding accessibility labels and hints, or auditing compliance.

Why use Accessibility Generator on TypingMind?

Because you install it once and use it with any model. Accessibility Generator 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 Accessibility Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/rshankras/claude-code-apple-skills/tree/main/skills/generators/accessibility-generator. 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 Accessibility Generator?

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 Accessibility Generator?

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

Is the Accessibility Generator AI skill free?

Yes. It is published on GitHub by rshankras 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 👇