Axiom Design logo

Axiom Design

CommunityPopular
CharlesWiltgen
axiom-design

Use when making visual or interaction design decisions for an Apple app — HIG patterns, Liquid Glass, SF Symbols, typography, app entry-point and auth-flow structure.

Overview

PublisherCharlesWiltgen
RepositoryAxiom
Skill nameaxiom-design
Stars
1.2K
Forks
86
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 CharlesWiltgen on GitHub. Read the source before you install it.

Installation

Install the Axiom Design 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/CharlesWiltgen/Axiom/tree/main/axiom-codex/skills/axiom-design
  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/CharlesWiltgen/Axiom.git /tmp/Axiom
mkdir -p .claude/skills
cp -r /tmp/Axiom/axiom-codex/skills/axiom-design .claude/skills/axiom-design
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Axiom Design 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 Axiom Design 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 Axiom Design 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.

Design & HIG

You MUST use this skill for ANY visual design, HIG compliance, Liquid Glass, SF Symbols, typography, or app composition work.

Auditors are skills here. Where this router says "Launch some-auditor agent", invoke the matching Codex skill instead — same procedure, no Claude Code agent required.

Available: axiom-audit-liquid-glass.

The ones that shell out — builds, tests, simulators, crash symbolication — need shell access to run.

Quick Reference

Symptom / TaskReference
Design decisions, HIG compliance, colors, backgroundsSee skills/hig.md
Spacing, padding, margins, insets — what value to useSee skills/hig.md
Designing for iPhone Duo — poses, controls on the side, keeping UI out of the foldSee axiom-swiftui (skills/iphone-duo.md)
Section index / A–Z index strip / alphabet scrubber — should this list have oneSee skills/hig.md
Semantic colors, custom color patterns, material stylesSee skills/hig-ref.md
Liquid Glass effects, adoption, migration from blur effectsSee skills/liquid-glass.md
App-wide Liquid Glass adoption, platform differencesSee skills/liquid-glass-ref.md
Backward compatibility: the UIDesignRequiresCompatibility opt-out, and why the 27 SDK ignores it on OS 27See skills/liquid-glass.md (Backward Compatibility)
SF Symbols rendering modes, effects, animationsSee skills/sf-symbols.md
SF Symbols API signatures, UIKit equivalents, availabilitySee skills/sf-symbols-ref.md
Verify a symbol name exists / check one symbol's availability or supported modes (sfsymbols CLI)See skills/sf-symbols-ref.md (Part 11)
San Francisco fonts, text styles, Dynamic Type, trackingSee skills/typography-ref.md
App entry points, auth flows, root view switching, scene lifecycle, document-based appsSee skills/app-composition.md
Apple Pay button / Wallet pass design / Tap to Pay buttonSee axiom-payments suite, plus skills/hig.md for cross-cutting HIG context

Decision Tree

dot
digraph design {
    start [label="Design task" shape=ellipse];
    what [label="What do you need?" shape=diamond];

    start -> what;
    what -> "skills/hig.md" [label="design decision,\nHIG compliance,\ncolor/background choice"];
    what -> "skills/hig.md" [label="spacing/padding/margin value"];
    what -> "skills/hig-ref.md" [label="semantic color API,\ncustom color code,\nmaterial style details"];
    what -> "skills/liquid-glass.md" [label="Liquid Glass effects,\nmigrate from blur,\nRegular vs Clear,\nopt-out key"];
    what -> "skills/liquid-glass-ref.md" [label="app-wide Liquid Glass plan,\nplatform differences"];
    what -> "skills/sf-symbols.md" [label="rendering mode choice,\nsymbol effects/animations,\ncustom symbols"];
    what -> "skills/sf-symbols-ref.md" [label="SF Symbols API syntax,\nUIKit equivalents,\navailability matrix"];
    what -> "skills/typography-ref.md" [label="font selection,\nDynamic Type,\ntext styles, tracking"];
    what -> "skills/app-composition.md" [label="@main entry point,\nauth flow, root view,\nscene lifecycle"];
}
  1. Design decision / HIG compliance / choosing colors or backgrounds? → skills/hig.md 1a. Need semantic color API, custom color code, or material style details? → skills/hig-ref.md
  2. Liquid Glass effects / migrating from blur / Regular vs Clear variant? → skills/liquid-glass.md 2a. Planning app-wide Liquid Glass adoption / platform differences? → skills/liquid-glass-ref.md 2b. Opting out of Liquid Glass / UIDesignRequiresCompatibility / backward compatibility? → skills/liquid-glass.md (Backward Compatibility)
  3. SF Symbols rendering mode / symbol effects / custom symbols? → skills/sf-symbols.md 3a. Need SF Symbols API syntax / UIKit equivalents / availability check? → skills/sf-symbols-ref.md
  4. Font selection / Dynamic Type / text styles / tracking / leading? → skills/typography-ref.md
  5. App entry point / auth flow / root view switching / scene lifecycle? → skills/app-composition.md
  6. SwiftUI view implementation? → /skill axiom-swiftui
  7. TextKit / rich text editing / Writing Tools? → /skill axiom-uikit
  8. Accessibility compliance (VoiceOver, contrast, touch targets)? → /skill axiom-accessibility
  9. Audit UI for Liquid Glass adoption? → liquid-glass-auditor (Agent — surfaces migration opportunities AND adoption-completeness gaps: variant discipline, nesting hygiene, unstyled pre-26 fallbacks, semantic toolbar placement, the UIDesignRequiresCompatibility opt-out, accessibility re-check; scores ADOPTED / PARTIAL / NOT ADOPTED)
  10. CarPlay app design, categories, driver-distraction rules? → /skill axiom-media (carplay-hig.md)
Platform-specific HIG
  • watchOS design (glanceable UI, watchOS 10 navigation) → See axiom-watchos (skills/design-for-watchos.md)

Conflict Resolution

design vs swiftui: When building UI:

  1. Use design FIRST — Decide what to build (colors, materials, typography, layout intent) before how to build it.
  2. Then use swiftui — Implement the design decision in SwiftUI code.

design vs accessibility: When choosing colors or typography:

  • Color contrast or Dynamic Type compliance? → use accessibility
  • Which semantic color or text style to pick? → use design

design (liquid-glass) vs swiftui: When implementing Liquid Glass:

  • What Liquid Glass is, when to use Regular vs Clear, migration strategy → use design (skills/liquid-glass.md)
  • SwiftUI code for .glassEffect() modifier → use design (skills/liquid-glass-ref.md), then swiftui for surrounding view code

design (app-composition) vs swiftui: When structuring app architecture:

  • @main entry, auth state machine, root view switching, scene lifecycle → use design (skills/app-composition.md)
  • NavigationStack, NavigationSplitView, tab structure → use swiftui

design vs media (CarPlay): When designing for CarPlay:

  • General iOS HIG principles (colors, typography, Liquid Glass) → use design
  • CarPlay-specific rules (app categories, entitlement review, template-only UI, driver distraction, per-category design rules) → invoke axiom-media (skills/carplay-hig.md)
  • CarPlay rules are stricter than iOS HIG and enforced at entitlement review, not just App Store review.

Critical Patterns

HIG Quick Decisions (skills/hig.md):

  • Background color decision tree (media-focused vs standard)
  • Typography selection (headline vs body vs caption)
  • Color usage guidelines and when to use semantic vs custom colors
  • Design review checklist for HIG compliance

HIG Comprehensive Reference (skills/hig-ref.md):

  • All semantic colors with platform availability
  • Custom color patterns with dark mode support
  • Background hierarchy and material styles
  • Code examples for every color and background pattern

Liquid Glass (skills/liquid-glass.md):

  • What Liquid Glass is and how it differs from blur effects
  • Regular vs Clear variant selection
  • Migration strategy from pre-iOS 26 materials
  • Tinting, legibility, and adaptive behavior troubleshooting
  • Expert review criteria for Liquid Glass implementations
  • The UIDesignRequiresCompatibility opt-out and its measured SDK × OS behavior

Liquid Glass Adoption (skills/liquid-glass-ref.md):

  • App-wide adoption planning (icons, controls, navigation, menus)
  • Platform-specific behavior (iOS, iPadOS, macOS, tvOS, watchOS)
  • Accessibility compliance with Liquid Glass interfaces

SF Symbols (skills/sf-symbols.md):

  • Rendering mode selection (Monochrome, Hierarchical, Palette, Multicolor)
  • Symbol effect selection (Bounce, Pulse, Scale, Wiggle, Rotate, Breathe, Draw)
  • Custom symbol creation workflow
  • Troubleshooting effects not playing, weight mismatches

SF Symbols API (skills/sf-symbols-ref.md):

  • Exact API signatures for rendering modes and effects
  • UIKit/AppKit equivalents for every SwiftUI symbol API
  • Platform availability matrix
  • Configuration options (weight, scale, variable values)

Typography (skills/typography-ref.md):

  • San Francisco font system (Pro, Compact, Mono, New York)
  • Text styles with Dynamic Type scaling
  • Tracking and leading values
  • Internationalization considerations

App Composition (skills/app-composition.md):

  • @main entry point and root view patterns
  • Authentication state machine (login, onboarding, main)
  • Flicker-free root view switching
  • scenePhase lifecycle handling and state restoration
  • Document-based apps: the OS27 @Observable document model (ReadableDocument/WritableDocument) + DocumentGroup

Anti-Rationalization

ThoughtReality
"I'll just pick colors that look good"Semantic colors adapt to dark mode, accessibility settings, and platform automatically. Custom colors need all of that manually. skills/hig.md has the decision tree.
"Liquid Glass is just a blur effect"Liquid Glass is a distinct material system with lensing, tinting, and adaptive behavior. Using .blur() instead creates a visually wrong result. skills/liquid-glass.md explains the difference.
"I know which SF Symbol rendering mode to use"The right mode depends on context (monochrome for toolbars, hierarchical for depth, palette for brand colors). skills/sf-symbols.md has the decision tree.
"I'll hardcode font sizes"Hardcoded sizes break Dynamic Type, violate HIG, and fail accessibility review. skills/typography-ref.md shows the text style system.
"I'll handle auth state with a boolean"A boolean can't represent login, onboarding, and main states without race conditions. skills/app-composition.md has the state machine pattern.
"Liquid Glass adoption means rewriting my whole UI"Most standard SwiftUI/UIKit components adopt automatically. Start by building with latest Xcode, then review. skills/liquid-glass-ref.md has the incremental strategy.
"I'll add the SF Symbol animation later"Symbol effects are the primary way users perceive interactive feedback. Shipping without them feels broken. skills/sf-symbols.md covers selection.
"I'll skip the design review, the code works"HIG compliance affects App Store review. Reviewers reject apps that feel wrong even if they function correctly. skills/hig.md has the review checklist.

Example Invocations

User: "Should I use a dark or light background?" -> Read: skills/hig.md

User: "What semantic color should I use for secondary text?" -> Read: skills/hig-ref.md

User: "How do I implement Liquid Glass in my app?" -> Read: skills/liquid-glass.md

User: "I need to plan Liquid Glass adoption across my whole app" -> Read: skills/liquid-glass-ref.md

User: "My SF Symbol is flat, I want it to have depth" -> Read: skills/sf-symbols.md

User: "What's the SwiftUI API for symbol effects?" -> Read: skills/sf-symbols-ref.md

User: "Which font should I use for body text?" -> Read: skills/typography-ref.md

User: "How do I switch between login and main screens?" -> Read: skills/app-composition.md

User: "Check my app's UI for HIG compliance" -> Read: skills/hig.md, then /skill axiom-accessibility for contrast/Dynamic Type

User: "I want my download button icon to animate" -> Read: skills/sf-symbols.md

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 Axiom Design AI skill do?

Use when making visual or interaction design decisions for an Apple app — HIG patterns, Liquid Glass, SF Symbols, typography, app entry-point and auth-flow structure.

Why use Axiom Design on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/CharlesWiltgen/Axiom/tree/main/axiom-codex/skills/axiom-design. 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 Axiom Design?

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 Axiom Design?

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

Is the Axiom Design AI skill free?

Yes. It is published on GitHub by CharlesWiltgen 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 👇