axiom-foundation-models-ref
Reference — Complete Foundation Models framework guide covering LanguageModelSession, @Generable, @Guide, Tool protocol, streaming, dynamic schemas, built-in use cases, and all WWDC 2025 code examples
npx skills add majiayu000/claude-skill-registry --skill axiom-foundation-models-ref --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Provides a reference guide for Foundation Models framework, covering core API (LanguageModelSession), structured output (@Generable and @Guide), tool protocol for external data, streaming via PartiallyGenerated, and usage patterns with WWDC 2025 code examples.
How it works
Describes how to create a LanguageModelSession (with optional instructions, tools, and model/use case), how respond(to:) and respond(to:generating:) produce outputs (including typed results via @Generable), and how streaming works through streamResponse with Itinerary as an example. Explains multi-turn context by appending to transcript, and shows isResponding to gate concurrent requests. Documents the @Generable macro usage for structs and enums, constrained decoding, and how property declaration order affects streaming. Details the Tool protocol, including an example GetWeatherTool and how tools are attached to a session to fetch external data, with a step-by-step flow of tool invocation and transcript augmentation.
When to use it
Use when implementing Foundation Models features, understanding API capabilities, looking up code examples, planning architecture, migrating from prototype to production, or debugging implementation issues.
What it can touch
Tools: GetWeatherTool and integration examples are provided to extend session capabilities by fetching external data via tools. The session can be initialized with tools and can call multiple tools per request, potentially in parallel.
Caveats
No explicit licensing statements beyond file-level metadata; reference-based guidance, with WWDC-derived patterns and example code. Limitations and safety considerations are described (e.g., structured output via @Generable, constrained decoding, and context usage).
# Foundation Models Framework — Complete API Reference ## Overview The Foundation Models framework provides access to Apple's on-device Large Language Model (3 billion parameters, 2-bit quantized) with a Swift API. This reference covers every API, all WWDC 2025 code examples, and comprehensive implementation patterns. ### Model Specifications **Technical Details**: - **Parameters**: 3 billion (3B) - **Quantization**: 2-bit - **Context Window**: 4096 tokens (combined input + output) - **Supported Languages**: English + additional languages via `SystemLanguageModel.default.supportedLanguages` - **Platforms**: iOS 26+, macOS 26+, iPadOS 26+, axiom-visionOS 26+ **Optimized For**: - Text summarization - Information extraction - Content classification - Content generation - Tag generation - Entity detection **NOT Optimized For**: - World knowledge queries - Complex multi-step reasoning - Mathematical computation - Translation (use dedicated translation models) **Privacy & Performance**: - Runs entirely on-device - No network required (works offline) - Data never leaves device - No per-request costs - Integrated into OS (doesn't increase app size) --- ## When to Use This Reference Use thi
- Overview
- Model Specifications
- When to Use This Reference
- LanguageModelSession
- Creating a Session
- Instructions vs Prompts
- respond(to:) Method
- respond(to:generating:) Method
- Generation Options
- Multi-Turn Interactions
- Retaining Context
- Transcript Property
- isResponding Property
- @Generable Macro
What does the axiom-foundation-models-ref skill do?
Reference — Complete Foundation Models framework guide covering LanguageModelSession, @Generable, @Guide, Tool protocol, streaming, dynamic schemas, built-in use cases, and all WWDC 2025 code examples
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill axiom-foundation-models-ref --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.