Apple HIG Doctor Is Skills V2

The first version of Apple HIG Skills solved one problem: getting accurate Apple Human Interface Guidelines context into AI coding assistants.

Apple HIG Doctor takes that foundation and turns it into a full workflow. Think of it as skills v2: guidance plus execution.

Instead of only asking your agent for HIG advice, you can now run an Apple HIG audit CLI to score a codebase, detect violations, export reports, and enforce checks in CI.

What changed from v1 to v2 for Apple HIG tooling

Version 1 was mostly knowledge delivery:

• 14 skills
• Progressive disclosure loading
• Apple HIG references on demand

HIG Doctor keeps that architecture and adds runtime tooling:

• A universal audit CLI that scans projects for HIG patterns
• A skill validator that checks skill package quality and consistency
• CI integration through GitHub Actions

That shift is the key idea behind skills v2: from “tell me what to do” to “verify what I built.”

The core Apple HIG Doctor stack

From the current repository:

• 14 skills across foundations, platforms, components, patterns, inputs, technologies, and project context
• 156 reference documents loaded only when needed
• 349 detection patterns in the audit engine
• 12 framework families supported for scanning

The project still uses progressive disclosure, so agents don’t load everything at once. But now those same categories also power audits and reports.

Two products in one Apple HIG Doctor repo

HIG Doctor combines two complementary tools.

1. Apple HIG skills layer

Install the skills into your coding agent:

npx skills add raintree-technology/apple-hig-skills

This gives the agent scoped HIG reasoning for:

• Foundations (color, typography, accessibility, dark mode)
• Platform guidance (iOS, iPadOS, macOS, tvOS, watchOS, visionOS)
• Components (layout, controls, dialogs, menus, content, search, status, system surfaces)
• Patterns, inputs, and Apple technologies

If your team uses Claude Code, you can also install it from the plugin marketplace path documented in the repo.

2. Apple HIG audit CLI + doctor tooling

Run the audit CLI against a real codebase:

cd packages/hig-doctor/src-termcast
bun install
bun run audit <directory>

Key output modes:

• --export writes hig-audit.md
• --stdout streams markdown for piping into an AI reviewer
• --json returns structured output for CI automation

Then validate the skill repository itself:

npm --prefix packages/hig-doctor install
node packages/hig-doctor/src/cli.js . --verbose

So the same project can both audit apps and quality-check the skill system behind the guidance.

After publishing, you can run the packaged validator directly:

npx -y hig-doctor@latest . --verbose

Why this matters for teams

Most AI design guidance fails at handoff.

• The model gives good advice.
• Code ships.
• Nobody verifies that implementation still matches HIG.

HIG Doctor closes that loop:

1. Agent gives contextual HIG guidance.
2. Developer implements in SwiftUI, React, Flutter, or another supported stack.
3. Audit runs and scores actual code.
4. CI enforces quality thresholds before merge.

That is the practical jump from “assistant” to “workflow.”

CI automation for Apple HIG compliance

You can run the project as a GitHub Action:

- uses: actions/checkout@v4
- uses: raintree-technology/apple-hig-skills@main
  with:
    directory: .
    verbose: "true"
    strict: "true"

For teams, this means HIG compliance stops being an informal code review comment and becomes a repeatable check.

Skills v2 in one sentence

Apple HIG Doctor is skills v2 because it combines domain-specific agent context with executable verification.

You still get the intelligence layer. Now you also get the enforcement layer.

If you already used Apple HIG Skills, this is the natural next step.

• GitHub
• Documentation