What problem does it solve? Building AI features that respect user privacy and work offline is hard when relying on cloud LLM APIs. This Skill provides ready-to-apply patterns for Apple's FoundationModels framework so you can run text generation, structured output, and tool calling entirely on-device. ## Core Features & Use Cases - Availability Checks & Sessions: Verify SystemLanguageModel availability and create single-turn or multi-turn LanguageModelSession instances with custom instructions. - Guided Generation: Use @Generable and @Guide macros to produce strongly-typed Swift structs instead of parsing raw strings, with constraints like ranges and counts. - Tool Calling & Streaming: Define custom Tool implementations the model can invoke, and stream structured responses as PartiallyGenerated snapshots for real-time SwiftUI updates. - Use Case: Build a recipe assistant that extracts structured ingredients from natural language, calls a custom recipe search tool, and streams results into a SwiftUI list — all without any network request. ## Quick Start Ask the assistant to create a SwiftUI view that uses LanguageModelSession with @Generable structured output and handles all model availability states.
