apple-foundation-models

Generate structured on-device language output with Apple Foundation Models.

3|Updated Jan 25, 2026
One-click install
npx skills add https://github.com/ai-enhanced-engineer/aiee-skills --skill apple-foundation-models-ai-enhanced-engineer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: apple-foundation-models
Source: https://github.com/ai-enhanced-engineer/aiee-skills/tree/main/skills/apple-foundation-models
Command: npx skills add https://github.com/ai-enhanced-engineer/aiee-skills --skill apple-foundation-models-ai-enhanced-engineer

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires FoundationModels, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill addresses the challenge of generating personalized coaching content on-device, providing structured output from language models, and managing token limits for offline AI functionality.

Core Features & Use Cases

  • Personalized Coaching Content: Generate on-device coaching content tailored to individual needs.
  • Structured Output: Obtain structured, typed responses from on-device language models.
  • Token Management: Handle the 4096-token context limit for long conversations.
  • Offline AI: Create AI features that operate without cloud dependency.
  • Use Case: Develop a breathing coach app that provides personalized breathing exercises and feedback based on biometric data, leveraging the Foundation Models for on-device AI processing.

Quick Start

Use the apple-foundation-models skill to generate a breathing exercise recommendation based on the user's current heart rate and session length.

Frequently Asked Questions about apple-foundation-models

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run on-device AI generation for personalized iOS apps?

You can run on-device AI generation by utilizing Apple Foundation Models, which support personalized experiences and offline AI functionality without cloud dependency on iOS 26+ devices.

How do I get structured output from on-device language models?

Apple Foundation Models provide structured output capabilities, allowing you to obtain typed responses from on-device language models for consistent data parsing in your application.

Do I need iOS 26 to use Apple Foundation Models for offline AI?

Yes, you need iOS 26+ devices to use Apple Foundation Models for offline AI, as the framework requires the FoundationModels dependency and system-level integrations available only in that version.

How do I manage token limits for long conversations on-device?

You manage token limits by handling the 4096-token context limit inherent to on-device language models, ensuring long conversations are processed efficiently within the FoundationModels framework.

What are the limitations of offline AI with FoundationModels?

Limitations of offline AI with FoundationModels include a 4096-token context limit for conversations and strict hardware requirements, meaning processing relies entirely on local device capabilities without cloud support.