Automate AI tasks on Apple devices using Claude. Developers build on-device AI capabilities for iOS 26+ and macOS 26+ with Python. Integrates with Apple's Foundation Models framework.
git clone https://github.com/Eyadkelleh/apple_foundation_models_claude_skill.gitThis skill provides comprehensive documentation for integrating Apple's Foundation Models framework into iOS, iPadOS, macOS, and visionOS applications. It guides developers through implementing on-device language model inference using SystemLanguageModel, managing conversations with LanguageModelSession, and building advanced patterns including guided generation for structured outputs, tool calling for custom capabilities, and streaming responses. The skill covers critical implementation topics such as prompting strategies, safety guardrails, localization support, and performance optimization. Developers gain access to complete API reference documentation, code examples, and best practices for deploying privacy-first AI features that run entirely on-device without external API calls or data transmission.
Install the skill in Claude Code from the marketplace using `/plugin install apple-foundation-models@apple-foundation-models-marketplace`. Claude Code will automatically suggest this skill when working with Apple Foundation Models. Review the Getting Started guide and API Reference in the documentation for setup instructions and implementation patterns.
Building privacy-first text generation features in iOS apps with on-device inference
Implementing guided generation to extract structured data from user input
Creating tool-calling integrations that extend model capabilities with custom functions
Developing multilingual AI features with localization support
No install command available. Check the GitHub repository for manual installation instructions.
git clone https://github.com/Eyadkelleh/apple_foundation_models_claude_skillCopy the install command above and run it in your terminal.
Launch Claude Code, Cursor, or your preferred AI coding agent.
Use the prompt template or examples below to test the skill.
Adapt the skill to your specific use case and workflow.
I'm developing an iOS 26+ app for [COMPANY] in the [INDUSTRY] sector. I need to automate [SPECIFIC TASK] using Claude's capabilities through Apple's Foundation Models framework. Provide a Python code snippet that integrates Claude with my app, focusing on [KEY FEATURE] to ensure [DESIRED OUTCOME].
```python
# Import necessary libraries
from apple.foundation_models import FoundationModel
from apple.foundation_models.claude import Claude
# Initialize Claude model
claude_model = FoundationModel(
model_name="claude",
model_path="/path/to/claude/model"
)
# Define the task automation function
def automate_task(input_data):
# Process input data
processed_data = preprocess_data(input_data)
# Use Claude for task automation
result = claude_model.predict(
prompt=f"Automate {processed_data} for {company_name}"
)
# Return the result
return result
# Example usage
company_name = "TechSolutions Inc."
input_data = "customer support tickets"
automate_task(input_data)
```Shopify for Homebuilders
Automate your browser workflows effortlessly
PostgreSQL backend-as-a-service with real-time APIs
Enterprise workflow automation and service management platform
Automate your spreadsheet tasks with AI power
Agentic AI Workflow platform
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan