Skip to main content
ClaudeWave
Skill1.1k repo starsupdated 1mo ago

app-intents

The app-intents Skill provides implementation guidance for exposing iOS app functionality to Siri, Shortcuts, Spotlight, widgets, Control Center, and Apple Intelligence through App Intents framework. Use this resource when building custom integrations that allow system features and external tools to discover and execute app actions or query app data.

Install in Claude Code
Copy
git clone --depth 1 https://github.com/dpearson2699/swift-ios-skills /tmp/app-intents && cp -r /tmp/app-intents/skills/app-intents ~/.claude/skills/app-intents
Then start a new Claude Code session; the skill loads automatically.

SKILL.md

# App Intents (iOS 26+)

Implement, review, and extend App Intents to expose app functionality to Siri,
Shortcuts, Spotlight, widgets, Control Center, and Apple Intelligence.

## Contents

- [Triage Workflow](#triage-workflow)
- [AppIntent Protocol](#appintent-protocol)
- [`@Parameter`](#parameter)
- [AppEntity](#appentity)
- [EntityQuery (4 Variants)](#entityquery-4-variants)
- [AppEnum](#appenum)
- [AppShortcutsProvider](#appshortcutsprovider)
- [System Surface Integration](#system-surface-integration)
- [iOS 26 Additions](#ios-26-additions)
- [Common Mistakes](#common-mistakes)
- [Review Checklist](#review-checklist)
- [References](#references)

## Triage Workflow

### Step 1: Choose the action, boundary, and surface

Start from 1-3 valuable actions people want outside the app, not from its screen hierarchy. Record one design row per action: user goal; inline result or app destination; shared domain operation; parameters and entity query; confirmation/authentication; target surface and protocol. Use one explicit runtime route for app handoff instead of scattering navigation side effects through intents.

Then choose the system feature and protocol that fit that action:

| Surface | Protocol | Since |
|---|---|---|
| Siri / Shortcuts | `AppIntent` | iOS 16 |
| Configurable widget | `WidgetConfigurationIntent` | iOS 17 |
| Control Center | `ControlConfigurationIntent` | iOS 18 |
| Spotlight search | `IndexedEntity` | iOS 18 |
| Apple Intelligence | `@AppIntent(schema:)` | iOS 18 |
| Interactive snippets | `SnippetIntent` | iOS 26 |
| Visual Intelligence | `IntentValueQuery` | iOS 26 |

### Step 2: Define the data model

- Prefer `AppEntity` shadow models for app data exposed to the system.
- Create `AppEnum` types for fixed parameter choices.
- Choose the right `EntityQuery` variant for resolution.
- Mark searchable entities with `IndexedEntity` and `indexingKey` metadata.

### Step 3: Implement the intent

- Conform to `AppIntent` (or a specialized sub-protocol).
- Declare `@Parameter` properties for all user-facing inputs.
- Implement `perform() async throws -> some IntentResult`.
- Add `parameterSummary` for Shortcuts UI.
- Register phrases via `AppShortcutsProvider`.

### Step 4: Verify

- Build and run in the target system surface to confirm discovery, parameter resolution, cancellation, confirmation, authentication, result rendering, and app handoff.
- If a step fails, reset the fixture, fix the smallest intent/entity/query boundary, and rerun the same action from the same surface before adding another action.
- Test Siri phrases with the intent preview in Xcode.
- Confirm `IndexedEntity` instances are indexed in a named Spotlight index.
- Check widget configuration for `WidgetConfigurationIntent` intents.

## AppIntent Protocol

The system instantiates the struct via `init()`, sets parameters, then calls
`perform()`. Declare a `title` and `parameterSummary` for Shortcuts UI.

```swift
struct OrderSoupIntent: AppIntent {
    static var title: LocalizedStringResource = "Order Soup"
    static var description = IntentDescription("Place a soup order.")

    @Parameter(title: "Soup") var soup: SoupEntity
    @Parameter(title: "Quantity", default: 1) var quantity: Int

    static var parameterSummary: some ParameterSummary {
        Summary("Order \(\.$soup)") { \.$quantity }
    }

    func perform() async throws -> some IntentResult {
        try await OrderService.shared.place(soup: soup.id, quantity: quantity)
        return .result(dialog: "Ordered \(quantity) \(soup.name).")
    }
}
```

Optional members: `description` (`IntentDescription`), `openAppWhenRun` (`Bool`),
`isDiscoverable` (`Bool`), `authenticationPolicy` (`IntentAuthenticationPolicy`).

## `@Parameter`

Declare each user-facing input with `@Parameter`. Non-optional parameters are
required; the system requests values when needed. Defaults pre-fill a useful
value. Optional parameters are not requested automatically, so ask for them in
`perform()` when the intent cannot continue without a value.

```swift
// Required; the system asks for a value when needed
@Parameter(title: "Count")
var count: Int

// Required and pre-filled
@Parameter(title: "Count", default: 1)
var count: Int

// Optional; request it yourself if it becomes necessary
@Parameter(title: "Count")
var count: Int?
```

### Supported value types

Primitives: `Bool`, `Int`, `Double`, `String`, `Duration`, `Date`, `Decimal`,
`Measurement`, and `URL`. Collections: `Array` and `Set` of supported element
types. Framework: `IntentPerson`, `IntentFile`. Custom: any `AppEntity` or
`AppEnum`.

### Common initializer patterns

```swift
// Basic
@Parameter(title: "Name")
var name: String

// With default
@Parameter(title: "Count", default: 5)
var count: Int

// Numeric slider
@Parameter(title: "Volume", controlStyle: .slider, inclusiveRange: (0, 100))
var volume: Int

// Options provider (dynamic list)
@Parameter(title: "Category", optionsProvider: CategoryOptionsProvider())
var category: Category

// File with content types
@Parameter(title: "Document", supportedContentTypes: [.pdf, .plainText])
var document: IntentFile

// Measurement with unit
@Parameter(title: "Distance", defaultUnit: .miles, supportsNegativeNumbers: false)
var distance: Measurement<UnitLength>
```

See [references/appintents-advanced.md](references/appintents-advanced.md) for all initializer variants.

## AppEntity

Prefer shadow models that mirror app data and expose only system-facing fields.
Direct model conformance is allowed when the model is lightweight, stable, and
appropriate for App Intents lifecycles.

```swift
struct SoupEntity: AppEntity {
    static let defaultQuery = SoupEntityQuery()
    static var typeDisplayRepresentation: TypeDisplayRepresentation = "Soup"
    var id: String

    @Property(title: "Name") var name: String
    @Property(title: "Price") var price: Double

    var displayRepresentation: DisplayRepresentation {
        DisplayRepresentation(title: "\(name)", subtitl
accessorysetupkitSkill

Discover and configure Bluetooth and Wi-Fi accessories using AccessorySetupKit. Use when presenting a privacy-preserving accessory picker, defining discovery descriptors for BLE or Wi-Fi devices, handling accessory session events, migrating from CoreBluetooth permission-based scanning, or setting up accessories without requiring broad Bluetooth permissions.

activitykitSkill

Implement, review, or improve Live Activities and Dynamic Island experiences in iOS apps using ActivityKit. Use when building real-time updating widgets for the Lock Screen and Dynamic Island — delivery tracking, sports scores, ride-sharing status, workout timers, media playback, or any time-sensitive information that updates in real time. Also use when working with ActivityKit, ActivityAttributes, Activity lifecycle (request/update/end), Dynamic Island layouts (compact/minimal/expanded), push-to-update Live Activities, or Lock Screen live widgets.

adattributionkitSkill

Measure ad effectiveness with privacy-preserving attribution using AdAttributionKit. Use when registering ad impressions, handling attribution postbacks, updating conversion values, implementing re-engagement attribution, configuring publisher or advertiser apps, or replacing SKAdNetwork with AdAttributionKit for ad measurement.

alarmkitSkill

Implement AlarmKit alarms and countdown timers for iOS and iPadOS with Lock Screen, Dynamic Island, StandBy, and paired Apple Watch system UI. Covers AlarmManager scheduling, AlarmAttributes and AlarmPresentation, system Stop and AlarmButton secondary actions, authorization, state observation, countdown widget-extension handoff, and Live Activity integration. Use when building wake-up alarms, countdown timers, or alarm-style alerts that need Apple's system alarm experience.

app-clipsSkill

Build iOS App Clips with invocation URLs, App Clip Codes, NFC, QR codes, Safari banners, Maps, Messages, target setup, App Store Connect experiences, size/capability constraints, NSUserActivity routing, SKOverlay promotion, App Group/keychain handoff, ephemeral notifications, location confirmation, and full-app migration. Use when creating App Clips or wiring App Clip invocation, experience configuration, or full-app handoff.

app-store-optimizationSkill

Optimize App Store product pages for search visibility and conversion. Use for App Store Optimization (ASO), keyword research, app name/subtitle/keyword-field strategy, conversion-focused descriptions and promotional text, screenshot captions and ordering, Custom Product Pages with assigned search keywords, In-App Events, Product Page Optimization tests, localized metadata, ratings/review strategy, and in-app review prompt timing with RequestReviewAction or AppStore.requestReview. Also use when routing ASO vs App Store review, privacy/ATT, or StoreKit implementation boundaries.

app-store-reviewSkill

Audits App Store submission readiness and rejection risk across current review guidelines, PrivacyInfo.xcprivacy and required-reason APIs, privacy labels, ATT, StoreKit payments, metadata, entitlements, widgets, and Live Activities. Use when preparing a submission, responding to rejection, reconciling privacy evidence, or separating upload blockers from cleanup.

apple-on-device-aiSkill

Build private, on-device AI features on iPhone, iPad, and Mac with Foundation Models, Core ML, MLX Swift, or llama.cpp. Use when choosing an Apple-local model runtime, building an Apple Intelligence chatbot or tool-calling feature, running an LLM on Apple Silicon, converting or compressing a Python model for Core ML, or comparing on-device inference backends. For Swift Core ML loading and prediction code, use the coreml skill.