foundation-models — Claude Code skill: what it does, how to install
Gives Claude Code reference patterns for Apple's on-device Foundation Models framework: summarization, extraction, classification. Covers setting up a LanguageModelSession and typed output with @Generable.
MIT ★ 233 updated 2026-01-18
/plugin marketplace add johnrogers/claude-swift-engineering
/plugin install swift-engineering@claude-swift-engineeringWhat foundation-models does
The skill bundles reference files for Apple's Foundation Models framework, a 3B-parameter language model that runs locally without network calls. Separate reference files cover starting a LanguageModelSession, getting typed structured output through @Generable and @Guide, calling external tools via the Tool protocol, and streaming responses with AsyncSequence and partially generated types.
It lists recurring mistakes: calling the model on the main thread instead of wrapping it in Task {}, feeding it oversized documents that overflow context, and skipping the SystemLanguageModel.default.availability check before use. The model is meant for summarizing, extracting, or classifying a user's own text, not for answering factual or world-knowledge questions — the skill points to ChatGPT, Claude, or Gemini for those.
The framework needs iOS 26+, macOS 26+, iPadOS 26+, or visionOS 26+, an Apple Intelligence-capable device (iPhone 15 Pro or later, M1+ Mac or iPad), and Apple Intelligence turned on for the user.
What it helps with
- set up a LanguageModelSession and check model availability
- get typed structured output from the model with @Generable
- summarize or classify a user's text without a network call
- wire external data into the model through the Tool protocol
- avoid blocking the main thread or overflowing the context window
Example prompts for the agent
- Set up a LanguageModelSession to summarize the user's notes
- Add a @Generable struct to pull key fields out of a block of text
- Show how to check SystemLanguageModel.default.availability before running a session
How to install foundation-models
1Plugin marketplace
/plugin marketplace add johnrogers/claude-swift-engineering/plugin install swift-engineering@claude-swift-engineeringThis installs the whole swift-engineering plugin with all its skills
2Skills CLI (Vercel)
npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a claude-code3Manually: put the files in place
~/.claude/skills/foundation-models/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/foundation-models/
1Skills CLI (Vercel)
npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a codex2Manually: put the files in place
.agents/skills/foundation-models/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a cursor2Manually: put the files in place
.cursor/skills/foundation-models/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install johnrogers/claude-swift-engineering plugins/swift-engineering/skills/foundation-models2Manually: put the files in place
.github/skills/foundation-models/SKILL.md1Skills CLI (Vercel)
npx skills add johnrogers/claude-swift-engineering --skill foundation-models -a gemini-cli2Platform CLI
gemini skills install https://github.com/johnrogers/claude-swift-engineering --path plugins/swift-engineering/skills/foundation-modelsManually: put the files in place
.devin/skills/foundation-models/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about foundation-models
How do I install foundation-models in Claude Code?
Run /plugin marketplace add johnrogers/claude-swift-engineering, then /plugin install swift-engineering@claude-swift-engineering.
What does the foundation-models skill do?
It gives Claude Code reference material on Apple's Foundation Models framework: session setup, typed output via @Generable, tool calling, streaming, and a list of common mistakes when working with the on-device model.
What tasks is the Foundation Models framework good for, and what should it avoid?
It handles summarization, extraction, and classification of a user's own content well. It isn't built for world knowledge or complex reasoning, where the skill recommends ChatGPT, Claude, or Gemini instead.
Source text
SKILL.md · MIT
---
name: foundation-models
description: Use when implementing on-device AI with Apple's Foundation Models framework (iOS 26+), building summarization/extraction/classification features, or using @Generable for type-safe structured output.
---
# Foundation Models
Apple's on-device AI framework providing access to a 3B parameter language model for summarization, extraction, classification, and content generation. Runs entirely on-device with no network required.
## Overview
Foundation Models enable intelligent text processing directly on device without server round-trips, user data sharing, or network dependencies. The core principle: leverage on-device AI for specific, contained tasks (not for general knowledge).
## Reference Loading Guide
**ALWAYS load reference files if there is even a small chance the content may be required.** It's better to have the context than to miss a pattern or make a mistake.
| Reference | Load When |
|-----------|-----------|
| **[Getting Started](references/getting-started.md)** | Setting up LanguageModelSession, checking availability, basic prompts |
| **[Structured Output](references/structured-output.md)** | Using `@Generable` for type-safe responses, `@Guide` constraints |
| **[Tool Calling](references/tool-calling.md)** | Integrating external data (weather, contacts, MapKit) via Tool protocol |
| **[Streaming](references/streaming.md)** | AsyncSequence for progressive UI updates, PartiallyGenerated types |
| **[Troubleshooting](references/troubleshooting.md)** | Context overflow, guardrails, errors, anti-patterns |
## Core Workflow
1. Check availability with `SystemLanguageModel.default.availability`
2. Create `LanguageModelSession` with optional instructions
3. Choose output type: plain String or @Generable struct
4. Use streaming for long generations (>1 second)
5. Handle errors: context overflow, guardrails, unsupported language
## Model Capabilities
| Use Case | Foundation Models? | Alternative |
|----------|-------------------|-------------|
| Summarization | Yes | - |
| Extraction (key info) | Yes | - |
| Classification | Yes | - |
| Content tagging | Yes (built-in adapter) | - |
| World knowledge | No | ChatGPT, Claude, Gemini |
| Complex reasoning | No | Server LLMs |
## Platform Requirements
- iOS 26+, macOS 26+, iPadOS 26+, visionOS 26+
- Apple Intelligence-enabled device (iPhone 15 Pro+, M1+ iPad/Mac)
- User opted into Apple Intelligence
## Common Mistakes
1. **Using Foundation Models for world knowledge** — The 3B model is trained for on-device tasks only. It won't know current events, specific facts, or "who is X". Use ChatGPT/Claude for that. Keep prompts to: summarizing user's own content, extracting info, classifying text.
2. **Blocking the main thread** — LanguageModelSession calls must run on a background thread or async context. Blocking the main thread locks UI. Always use `Task { }` or background queue.
3. **Ignoring context overflow** — The model has finite context. If the user pastes a 50KB document, it will fail silently or truncate. Check input length and trim/truncate proactively.
4. **Forgetting to check availability** — Not all devices support Foundation Models. Check `SystemLanguageModel.default.availability` before using. Graceful degradation is required.
5. **Ignoring guardrails** — The model won't answer harmful queries. Instead of fighting it, design prompts that respect safety guidelines. Rephrasing requests usually works.
© John Rogers (@johnrogers) · MIT · johnrogers/claude-swift-engineering