agentleFS
bastosbastos/skills/review-ios-ui-apple-hig/SKILL.md

review-ios-ui-apple-hig

Skill7 starsChanged 10 months agoMITView on GitHub

Review iOS app UI against Apple Human Interface Guidelines and iOS platform conventions. Use when asked for an Apple HIG-based iOS UI, UX, SwiftUI, UIKit, screenshot, simulator, accessibility, Dynamic Type, navigation, layout, controls, color, typography, or platform-conventions review, especially when the user wants critique or prioritized findings grounded in Apple's interface guidance instead of project-specific design docs.

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to review an iOS interface against Apple Human Interface Guidelines, iOS conventions, and observable product behavior.

    line 10
  2. Distinctive:

    Default to review-only. Do not edit files unless the user explicitly asks for fixes.

    line 12
  3. Very specific:

    Read references/apple-hig-review.md before making guideline claims, then read the page-specific reference files it routes to.

    line 18
  4. Distinctive:

    Do not rely on project-specific design documents unless the user explicitly asks for that comparison.

    line 25
  5. Distinctive:

    When reviewing code, cite file paths and line numbers for the UI surface that creates the issue.

    line 26
  6. Distinctive:

    When reviewing screenshots or simulator output, describe the visible region precisely enough that the user can locate it.

    line 27
  7. Distinctive:

    When behavior depends on runtime state, Dynamic Type, appearance mode, localization, or device size, say whether it was verified.

    line 28
  8. Distinctive:

    Use the Browser plugin or another rendered browser only when Apple HIG imagery/examples or web-rendered reference pages need visual …

    line 29
  9. Distinctive:

    Start with findings, ordered by severity:

    line 33
  10. Distinctive:

    Keep the response concise.

    line 48

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Review iOS UI Against Apple HIG

Purpose

Use this skill to review an iOS interface against Apple Human Interface Guidelines, iOS conventions, and observable product behavior.

Default to review-only. Do not edit files unless the user explicitly asks for fixes.

Workflow

  1. Define the review surface: identify the app screens, screenshots, SwiftUI/UIKit files, simulator state, and target devices or size classes involved.
  2. Gather evidence from the actual artifact. Prefer screenshots, simulator runs, UI previews, or concrete SwiftUI/UIKit code over generic assumptions.
  3. Read references/apple-hig-review.md before making guideline claims, then read the page-specific reference files it routes to. If the user asks for the current or exact Apple rule, verify the linked Apple page live.
  4. Review by category: platform fit, layout, navigation, controls and input, typography, color and materials, accessibility, feedback states, destructive actions, and iPad/adaptive behavior when relevant.
  5. Rank findings by user impact and confidence. Prioritize issues that affect comprehension, task completion, accessibility, safety, or platform expectation.
  6. Report findings with evidence and a concrete recommendation. Avoid broad redesign advice unless it follows directly from an observed issue.

Evidence Rules

  • Do not rely on project-specific design documents unless the user explicitly asks for that comparison.
  • When reviewing code, cite file paths and line numbers for the UI surface that creates the issue.
  • When reviewing screenshots or simulator output, describe the visible region precisely enough that the user can locate it.
  • When behavior depends on runtime state, Dynamic Type, appearance mode, localization, or device size, say whether it was verified.
  • Use the Browser plugin or another rendered browser only when Apple HIG imagery/examples or web-rendered reference pages need visual inspection.

Output Shape

Start with findings, ordered by severity:

High: <issue title>
Evidence: <file:line, screenshot area, or runtime observation>
Apple guideline basis: <short paraphrase plus HIG page name/link when useful>
Recommendation: <specific UI change or validation step>

Then include:

  • Open questions only when missing context changes the recommendation.
  • Verification gaps when the review did not include device, simulator, Dynamic Type, dark mode, VoiceOver, or localization checks that matter.
  • No guideline-level issues found when the inspected surface appears aligned and only subjective style preferences remain.

Keep the response concise. Do not include a generic HIG checklist in the final answer unless the user asks for one.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.