Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/billythekidz/apple-design-skillnpx agentmods add skills/billythekidz/apple-design-skill/apple-designWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/billythekidz/apple-design-skill/apple-design)<a href="https://agentmods.dev/skills/billythekidz/apple-design-skill/apple-design"><img src="https://agentmods.dev/badge/skills/billythekidz/apple-design-skill/apple-design/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/billythekidz/apple-design-skill/apple-design"><img src="https://agentmods.dev/badge/skills/billythekidz/apple-design-skill/apple-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.02729 |
| Opus 5 | $0.00028 | $0.01365 |
| Sonnet 5 | $0.00011 | $0.00546 |
| Haiku 4.5 | $0.00006 | $0.00273 |
Grade A, and why
apple-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
91% identical to apple-design — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apple Design System & Human Interface Guidelines (HIG)
This skill equips AI coding agents with the exact principles, visual specifications, component architectures, typography metrics, color tokens, motion curves, and automated compliance auditing defined by Apple's Human Interface Guidelines (HIG) across iOS, iPadOS, macOS, watchOS, visionOS, and modern Apple-grade Web UI.
🎯 Operational Modes
Mode 1 — Design & Build from Scratch
When tasked with creating new screens, apps, or web interfaces in Apple style:
- Choose the platform-native navigation paradigm (e.g. Bottom Tab Bar for iOS, Sidebar for macOS/iPad, Ornaments for visionOS).
- Establish the 8pt spatial grid and continuous squircle curvature (
G2 continuity). - Apply the SF Pro / New York typography scale with optical tracking rules.
- Implement semantic Dynamic Colors (Light & OLED Dark mode) and Liquid Frosted Glass materials.
- Apply Apple spring physics (
cubic-bezier(0.25, 1, 0.5, 1)) and tactile active feedback (scale(0.97)).
Mode 2 — Apple HIG Compliance Audit & Scoring
When reviewing an existing codebase, mockup, or component:
- Run the audit tool
node skills/apple-design/scripts/audit-apple-design.mjsto perform automated static scanning with a 0–100 Scoring Rubric. - Perform exact mathematical WCAG contrast checks and 44×44pt touch-target validations.
- Fill out the Apple HIG Audit Scorecard across the 5 core pillars.
- Deliver prioritized findings with Confidence Tagging:
- 🟢 Tool-verified: Statistically measured via CLI tool (e.g., contrast ratio, button dimension, static CSS rules).
- 🟡 Needs device test: Requires hardware interaction (e.g., Dynamic Type at 300%, Reduce Transparency toggle, VoiceOver speech hierarchy).
- 🔴 Assumed: Contextual design trade-off or subjective aesthetic evaluation.
🛠️ The Apple HIG Compliance CLI Engine
The built-in audit engine (skills/apple-design/scripts/audit-apple-design.mjs) provides four subcommands:
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/apple-components.css 7.3 KB
- assets/apple-tokens.css 5.1 KB
- assets/swiftui-cheat-sheet.md 4.5 KB
- assets/tailwind.preset.apple.js 2.8 KB runs code
- references/.hash-manifest.json 42 KB
- references/accessibility-and-haptics.md 2.8 KB
- references/accessibility.md 20 KB
- references/action-button.md 5.5 KB
- references/action-sheets.md 5.1 KB
- references/activity-rings.md 6.3 KB
- references/activity-views.md 7.4 KB
- references/airplay.md 8.1 KB
- references/alerts.md 11 KB
- references/always-on.md 4.2 KB
- references/animations-and-springs.md 3.6 KB
- references/app-clips.md 33 KB
- references/app-icons.md 15 KB
- references/app-shortcuts.md 10 KB
- references/apple-pay.md 30 KB
- references/apple-pencil-and-scribble.md 15 KB
- references/augmented-reality.md 24 KB
- references/boxes.md 2.3 KB
- references/branding.md 4.2 KB
- references/buttons.md 19 KB
- references/camera-control.md 5.7 KB
- references/carekit.md 20 KB
- references/carplay.md 8.6 KB
- references/charting-data.md 7.6 KB
- references/charts.md 22 KB
- references/collaboration-and-sharing.md 7.7 KB
- references/collections.md 2.7 KB
- references/color-palette-materials.md 4.7 KB
- references/color-wells.md 2.1 KB
- references/color.md 19 KB
- references/column-views.md 2.7 KB
- references/combo-boxes.md 2.1 KB
- references/complications.md 17 KB
- references/components-and-layouts.md 4.2 KB
- references/components.md 1.1 KB
- references/content.md 962 B
- references/context-menus.md 9.4 KB
- references/controls.md 7.8 KB
- references/dark-mode.md 8.6 KB
- references/design-principles.md 7.2 KB
- references/designing-for-games.md 14 KB
- references/designing-for-ios.md 4.4 KB
- references/designing-for-ipados.md 3.9 KB
- references/designing-for-macos.md 3.9 KB
- references/designing-for-tvos.md 3.5 KB
- references/designing-for-visionos.md 8.2 KB
- references/designing-for-watchos.md 5.2 KB
- references/digit-entry-views.md 1.3 KB
- references/digital-crown.md 5.2 KB
- references/disclosure-controls.md 3.9 KB
- references/dock-menus.md 2.4 KB
- references/drag-and-drop.md 15 KB
- references/edit-menus.md 6.8 KB
- references/entering-data.md 5.2 KB
- references/eyes.md 11 KB
- references/feedback.md 4.6 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 196 lines · 55 tokens per session scan A 0c3c12c931e3
apple-design is a skill published in the GitHub repository billythekidz/apple-design-skill (4 stars, last pushed 22d ago), licensed MIT. It adds 55 tokens to every session and 2,729 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 91% identical to apple-design, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
apple-hig-check
Audit code or design against Apple Human Interface Guidelines.
swift-expert
Expert-level Swift development for iOS, macOS with SwiftUI, Combine, and modern Swift 5.9+. Use when the user mentions iOS, macOS, SwiftUI, Combine, async await, or Apple platforms, or when the task involves Modern Swift Features, Basics and Optionals, Functions and Closures, or Structs and Classes.
swift-focusengine-pro
Reviews, writes, and fixes focus management code for all Apple platforms (tvOS, iOS/iPadOS, watchOS, visionOS, macOS), covering SwiftUI, UIKit, AppKit, and RealityKit. Use when reading, writing, or reviewing apps that handle focus, hover, key view loops, or Digital Crown navigation.
ios-hig-pro-max
Apple ecosystem experience architect skill for SwiftUI development. Invoke this skill whenever the user wants to build, design, review, or polish ANY iOS/iPadOS/macOS interface using SwiftUI — even if they just say "make a screen", "write a SwiftUI view", "help with my app UI", "build an iOS feature", or name any app…
apple-human-interface-guidelines
Use for any design, UI, or UX work on Apple-platform products, including visual design, interaction design, layout, navigation, accessibility, design review, and implementation decisions that should align with Apple Human Interface Guidelines.
iOS SwiftUI Accessibility
Enforces WCAG 2.2 accessible coding patterns when writing SwiftUI — labels, traits, Dynamic Type, contrast, touch targets, focus management, orientation, and more. Based on the ios-swiftui-accessibility-techniques project with 41 static analysis rules across 23 WCAG criteria.