Agent Claude Code
Use when reviewing native iOS 3D, AR, spatial UI, RealityKit, Model3D, ARKit, SceneKit migration, Metal shaders, particles, or Three.js-style product requests translated into Apple frameworks. Read-only; reports framework choice and implementation risks without editing code.
Agent Claude Code
Audits SwiftUI and UIKit code for VoiceOver, Dynamic Type, contrast, tap targets, and motion/transparency settings. Read-only — reports findings with file:line and the specific fix. Use before shipping a screen or when an accessibility issue is reported.
Agent Claude Code
Read-only App Intents reviewer. Use when exposing app actions to Siri, Shortcuts, Spotlight, Apple Intelligence, App Entities, schemas, View Annotations, semantic indexing, or App Intents testing. Reports findings and does not edit code.
Agent Claude Code
Read-only App Store reviewer. Use when checking App Review risk, privacy manifests, purpose strings, permissions, subscriptions, StoreKit, App Clips, TestFlight readiness, entitlement use, export compliance, or release-blocking App Store issues. Reports findings and does not edit code.
Agent Claude Code
Read-only Core AI reviewer. Use when working with custom .aimodel/.aimodelc assets, AIModel integration, model specialization, Core AI debugging, provider choice, availability gates, privacy boundaries, or Apple Silicon on-device inference. Reports guidance and does not edit code.
Agent Claude Code
Specialist for Apple's Foundation Models framework and Apple Intelligence — on-device and Private Cloud Compute language models, @Generable structured output, tool calling, Dynamic Profiles, and multimodal prompts. Use when building, reviewing, or debugging any on-device LLM feature. Enforces availability gating and…
Agent Claude Code
Writes and maintains documentation for this skill repository and for Swift codebases — new docs under docs/, DocC comments, README sections, CHANGELOG entries. Use when the deliverable is prose about code rather than code. Enforces the Context to Pattern to Anti-Patterns structure.
Agent Claude Code
Read-only codebase search for Swift/iOS projects. Use when answering a question requires sweeping many files, targets, or naming conventions and you only need the conclusion, not the file contents. Returns file:line citations. Safe to run several of these in parallel.
Agent Claude Code
Architecture and implementation planner for iOS/Swift work. Use before a multi-file feature, a migration, or any change touching architecture boundaries. Returns a step-by-step plan with file paths, ordering, and trade-offs. Read-only — it never edits code.
Agent Claude Code
Read-only Metal reviewer. Use when reviewing custom GPU rendering, MTKView, shaders, compute kernels, command buffers, pixel formats, AR camera texture interop, particles, or Metal performance risks. Reports findings and does not edit code.
Agent Claude Code
Read-only native iOS motion reviewer. Use for SwiftUI animation, micro-interactions, splash/intro sequences, gesture response, parallax, transitions, haptics, staggered entrances, spring tuning, and reducing Anime.js-style ideas into native SwiftUI/UIKit motion plans. Reports recommendations and does not edit code.
Agent Claude Code
Investigates iOS performance problems — scroll hitches, slow launch, memory growth, main-actor contention, over-invalidating SwiftUI views. Measures before concluding and never optimizes on suspicion. Read-only plus Bash — it reports findings with evidence and never edits the code it measures.
Agent Claude Code
Read-only RealityKit reviewer. Use when building or reviewing native 3D scenes, RealityView, Model3D, USDZ assets, ARKit + RealityKit integration, spatial interactions, physics, materials, lighting, or SceneKit migration. Reports recommendations and does not edit code.
Agent Claude Code
Read-only security reviewer. Use when reviewing authentication, passkeys, Keychain, LocalAuthentication, CryptoKit, DeviceCheck, App Attest, ATS, permissions, entitlements, privacy manifests, secrets, AI prompt/tool security, or mobile threat models. Reports findings and does not edit code.
Agent Claude Code
Root-cause analysis for Swift/iOS failures — compiler errors, test failures, crashes, data races, SwiftUI views that do not update. Use when something is broken and the cause is not obvious. Reproduces first, then fixes, then proves the fix with real output.
Agent Claude Code
Behavior-preserving Swift cleanups — extracting subviews, introducing protocol seams, replacing literals with design tokens, adding @MainActor isolation, removing duplication. Use for mechanical improvement with no behavior change. Proves behavior is unchanged by running the tests before and after.
Agent Claude Code
Independent verifier for Swift/iOS changes. Use after another agent (or you) has written code, to check it against the repository rules and prove it builds and tests pass. Runs builds and tests and returns their real output. Read-only — it holds no write tools, so it cannot fix what it should report, and it never…
Agent Claude Code
Read-only SwiftUI expert. Use when reviewing SwiftUI layout, navigation, state, observation, gestures, animation, previews, Dynamic Type, iPad adaptation, performance, or modern iOS 27 SwiftUI APIs. Reports recommendations and does not edit code.
Agent Claude Code
Migrates legacy SwiftUI and UIKit to current APIs — ObservableObject to @Observable, NavigationView to NavigationStack, completion handlers to async/await, AnyView removal, deprecated modifiers. Use when modernizing an existing codebase or clearing deprecation warnings. Behavior-preserving; requires a green test…
Agent Claude Code
Read-only testing reviewer. Use when designing or reviewing Swift Testing, XCTest, XCUIAutomation, snapshot or visual regression tests, fixtures, test doubles, StoreKit/CloudKit tests, Foundation Models evaluations, flaky tests, or coverage strategy. Reports recommendations and does not edit code.
Agent Claude Code
Read-only product UI reviewer for SwiftUI/UIKit screens. Use when asked to redesign a screen professionally, improve visual hierarchy, spacing, typography, navigation, loading/error/empty states, dark mode, or premium iOS polish. Reports concrete file:line recommendations and does not edit code.
Agent Claude Code
Read-only UIKit expert. Use when reviewing UIViewController lifecycle, UIKit layout, collection/table views, UIKit-SwiftUI interop, UIKit animation, accessibility, navigation controllers, sheets, or legacy UIKit modernization. Reports recommendations and does not edit code.
Agent Claude Code
Read-only WebKit reviewer. Use when deciding between WKWebView and native Apple UI, embedding web content, building a Swift-JavaScript bridge, using Anime.js/GSAP/Three.js/WebGL in a hybrid surface, or reviewing web content security. Reports guidance and does not edit code.
Agent Claude Code
Read-only Xcode tooling reviewer. Use when diagnosing Xcode projects, schemes, build settings, xcconfig, Swift Package Manager, Xcode Cloud, Instruments, previews, asset catalogs, string catalogs, Device Hub, Xcode 27 agents, or simulator/tooling workflows. Reports guidance and does not edit code.