core-ml

Integrate Core ML, Vision, and Natural Language into Apple platform apps.

4|1|Updated Apr 2, 2026

Search Tags:#vision #apple #inference #on-device #naturallanguage #createml #core-ml

Ready to run

npx skills add https://github.com/AutisticAF/claude-code-apple-dev-plugin --skill core-ml-autisticaf

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: core-ml
Source: https://github.com/AutisticAF/claude-code-apple-dev-plugin/tree/main/skills/core-ml
Command: npx skills add https://github.com/AutisticAF/claude-code-apple-dev-plugin --skill core-ml-autisticaf

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Integrates Core ML, Vision, and Natural Language into Apple platform apps to enable on-device ML features.

Core Features & Use Cases

Unified ML integration: Connects Core ML, Vision, and Natural Language workflows in a single, coherent pattern.
On-device inference & optimization: Supports running models locally with optional quantization and performance tuning.
Model training & deployment: Includes guidance for training with Create ML and deploying .mlmodel files in Xcode.
Decision guidance: Helps choose between Core ML and foundation models depending on use-case and OS constraints.

Quick Start

Train or obtain an ML model, add the .mlmodel to your Xcode project, and use the generated interface to run predictions.

Frequently Asked Questions about core-ml

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

FAQPage Schema

How do I run on-device inference with Core ML in my iOS app?▼

To run on-device inference with Core ML, add a trained .mlmodel file to your Xcode project and use the automatically generated Swift interface to execute predictions locally on the device.

Can I use Vision and Natural Language frameworks together for image and text analysis?▼

Yes, you can integrate Vision and Natural Language frameworks together to perform unified on-device image analysis and text processing within a single Apple platform application workflow.

What is the best way to train and deploy a machine learning model for macOS?▼

The best way to deploy a model for macOS is to train it using Create ML, export the resulting .mlmodel file, and add it directly to your Xcode project for on-device execution.

When should I choose Core ML over foundation models for on-device machine learning?▼

Choose Core ML over foundation models when you need optimized on-device inference across specific Apple platform constraints, as it provides dedicated quantization and performance tuning for local execution.

Does on-device inference with .mlmodel files work across watchOS and other Apple platforms?▼

Yes, on-device inference using .mlmodel files works across Apple platforms including iOS, macOS, and watchOS, enabling local machine learning features without requiring a network connection.