A skill should state when to use it, what inputs it needs and how success is checked. A giant list of technologies cannot substitute for a procedure an agent can follow.

Trigger → Relevant context → Bounded procedure → Evidence
  1. 1Trigger
  2. 2Relevant context
  3. 3Bounded procedure
  4. 4Evidence

Work through the example

Keep the entry point short enough to route to focused references. Test discovery separately from whether the model follows the workflow.

Start with a disposable branch and synthetic data. Write the expected outcome before changing the implementation, then keep the first failing result. This prevents a later repair from quietly redefining the task. The procedure below is grounded in the repository reference; its examples must still be checked against your project and installed toolchain.

Implementation reference

The following focused section is adapted from the maintained project guide. It preserves the source’s examples and limitations.


name: ios-agent-skill description: Expert iOS/Swift developer behavior for AI coding agents. Use when writing, reviewing, or refactoring Swift, SwiftUI, UIKit, or SwiftData code; when designing iOS app architecture (MVVM, Clean Architecture, coordinators, routing); when building UI that must meet Apple's Human Interface Guidelines, contrast, dark-mode, and Dynamic Type standards; when working with any Apple framework (SwiftData, Core Data, CloudKit, StoreKit, HealthKit, WidgetKit, App Intents, CoreML, Vision, ARKit, RealityKit, SceneKit, Metal, and 30+ more); or when targeting iOS, macOS, watchOS, tvOS, or visionOS. Also use for Swift concurrency questions — actors, @MainActor isolation, Sendable, structured concurrency. version: "3.5.0" license: MIT allowed-tools: Read, Write, Edit, Glob, Grep, Bash metadata: author: Nagarjuna Reddy homepage: https://nagarjuna2997.github.io/ios-agent-skill/ languages: [swift] platforms: [ios, macos, watchos, tvos, visionos] entry: SKILL.md # Toolchain this skill is written against. swift-version: "6.4" xcode-version: "27" ios-sdk-version: "27" # Deployment floor the generated code must still support. minimum-swift: "5.9" minimum-ios: "17.0" supports: - Foundation Models - Apple Intelligence - Private Cloud Compute - Xcode Coding Agents - Device Hub - Liquid Glass - SwiftData - Swift 6 strict concurrency


Apple app engineering

Use the current project and the user's requested feature as the scope. Build working Swift implementations with explicit errors, injected dependencies, preview data and meaningful verification.

Acceptance and failure review

Checkpoint What to inspect If it does not match
Trigger Confirm the input and environment Preserve the failure and return to this step
Relevant context Inspect the intermediate artifact Preserve the failure and return to this step
Bounded procedure Run the focused check Preserve the failure and return to this step
Evidence Record the observed result Preserve the failure and return to this step

Ask the agent to explain the smallest change that resolves the observed mismatch. Keep unrelated refactors out of the repair. A change that makes a warning disappear is not enough if the behavior or ownership contract has changed. Re-run the same acceptance check so the before and after results are comparable.

Evidence and limits

Do not claim a skill improves quality without a controlled comparison.

This is an educational guide. Its presence in the series does not certify a completed client-specific lab. The series evidence record separates executed checks from exercises and blocked environments.

Inspect the source used in this lesson.

What to do next

Next: Building a Claude Code plugin from a skill