Apple Foundation Models Skill

When to Use This Skill

• On-device AI: Building iOS/macOS apps with on-device language models
• SystemLanguageModel: Working with Apple's on-device LLM API
• Guided Generation: Generating structured Swift types from prompts
• Tool Calling: Extending model capabilities with custom tools
• Prompting: Crafting effective prompts for on-device models
• Safety: Implementing guardrails and handling sensitive content
• Localization: Supporting multilingual AI features

Description

Quick Reference

Core Components

Advanced

• Transcript

• Transcript.Entry

• Transcript.Response

• Transcript.ResponseFormat

• Transcript.Segment

• Transcript.StructuredSegment

Api Reference

• FoundationModels

• GenerationID

• SystemLanguageModel

• SystemLanguageModel.Adapter

• SystemLanguageModel.Guardrails

• SystemLanguageModel.UseCase

Getting Started

• SystemLanguageModel.Availability

Guided Generation

• DynamicGenerationSchema

• Generable

• GenerationGuide

• GenerationSchema

• Guide

Localization

• LanguageModelFeedback

Prompting

• Instructions

• InstructionsBuilder

• InstructionsRepresentable

• LanguageModelSession

• LanguageModelSession.GenerationError

• LanguageModelSession.ToolCallError

• Prompt

• PromptBuilder

• PromptRepresentable

• Transcript.Instructions

• Transcript.Prompt

Tool Calling

• Tool

Key Concepts

Platform Support

• iOS 26.0+
• iPadOS 26.0+
• macOS 26.0+
• Mac Catalyst 26.0+
• visionOS 26.0+

On-Device AI

Usage Guidelines

1. Check model availability before use
2. Define clear instructions for the model's behavior
3. Use guided generation for structured outputs
4. Implement tool calling for dynamic capabilities
5. Handle errors appropriately

Navigation

references/

• references/advanced.md

  - Advanced

• references/api_reference.md

  - Api Reference

• references/getting_started.md

  - Getting Started

• references/guided_generation.md

  - Guided Generation

• references/localization.md

  - Localization

• references/prompting.md

  - Prompting

• references/tool_calling.md

  - Tool Calling

Best Practices

• Prompting: Be specific and clear in your prompts
• Instructions: Define the model's behavior upfront
• Safety: Enable guardrails for sensitive content
• Localization: Check supported languages for your use case
• Performance: Use prewarm() for better response times
• Streaming: Use streamResponse() for real-time user feedback

Common Patterns

Basic Session

let model = SystemLanguageModel(useCase: .general)
let session = LanguageModelSession(model: model)
let response = try await session.respond(to: Prompt("Your question"))

Guided Generation

struct Recipe: Generable {
    let title: String
    let ingredients: [String]
}

let recipe = try await session.respond(
    generating: Recipe.self,
    prompt: Prompt("Create a pasta recipe")
)

Tool Calling

struct WeatherTool: Tool {
    func call(arguments: String) async throws -> String {
        // Fetch weather data
    }
}

let session = LanguageModelSession(
    model: model,
    tools: [WeatherTool()]
)

Reference Documentation

references/