core-ml

Name: core-ml
Author: rshankras

277installs46forks

How to install core-ml?

rshankras/claude-code-apple-skills/core-ml

$npx -y skills add rshankras/claude-code-apple-skills --skill core-ml

Installs into the current project.

Summary

Core ML, Create ML, Vision framework, Natural Language framework, on-device ML integration. Use when user wants image classification, text analysis, object detection, sound classification, model optimization, or custom model integration. Covers Core ML vs Foundation Models decisi

Files · 1

View on GitHub

SKILL.md

1	# Core ML Skills
2
3	Combined advisory, generator, and workflow skill for integrating machine learning into Apple platform apps. Covers Core ML model integration, Vision framework image analysis, NaturalLanguage framework text processing, Create ML training, and on-device model optimization.
4
5	## When This Skill Activates
6
7	Use this skill when the user:
8	- Wants to add ML capabilities to their app
9	- Needs to integrate a Core ML model (.mlmodel) into an Xcode project
10	- Wants to use the Vision framework for image analysis (faces, text recognition, body pose, object detection)
11	- Wants to use the NaturalLanguage framework for text processing (sentiment, entities, language detection)
12	- Needs to train a custom model with Create ML
13	- Wants to optimize a model for on-device use (quantization, pruning, palettization)
14	- Needs to choose between Core ML and Foundation Models (Apple Intelligence)
15	- Asks about image classification, object detection, sound classification, or tabular data prediction
16	- Wants real-time camera + ML processing
17
18	## Decision Guide: Core ML vs Foundation Models
19
20	Before generating code, determine which framework is appropriate.
21
22	### Use Foundation Models (Apple Intelligence) When:
23	- You need general-purpose text generation, summarization, or conversational AI
24	- Target is iOS 26+ / macOS 26+ (Foundation Models requires Apple Silicon + latest OS)
25	- The task is open-ended language understanding or generation
26	- You want `@Generable` structured output from natural language
27	- See `apple-intelligence/foundation-models/` skill for implementation
28
29	### Use Core ML When:
30	- You need specialized ML: image classification, object detection, sound classification, custom regression/classification
31	- You have a trained model (.mlmodel, .mlpackage) or plan to train one
32	- You need broad device support (iOS 14+ / macOS 11+)
33	- The task requires domain-specific predictions (medical imaging, product recognition, custom NLP)
34	- Performance-critical inference on Neural Engine or GPU
35
36	### Use Vision Framework When (No Custom Model Needed):
37	- Image classification using Apple's built-in models
38	- Face detection and facial landmark analysis
39	- Text recognition (OCR) with `VNRecognizeTextRequest`
40	- Body and hand pose detection
41	- Barcode and QR code scanning
42	- Image similarity and saliency detection
43	- Horizon detection, rectangle detection
44
45	### Use NaturalLanguage Framework When (No Custom Model Needed):
46	- Sentiment analysis on text
47	- Language identification
48	- Tokenization (word, sentence, paragraph boundaries)
49	- Named entity recognition (people, places, organizations)
50	- Word and sentence embeddings for similarity comparison
51	- Lemmatization and part-of-speech tagging
52
53	## Pre-Generation Checks
54
55	### 1. Project Context Detection
56	- [ ] Check deployment target (Core ML requires iOS 11+ / macOS 10.13+; Vision requires iOS 11+; NaturalLanguage requires iOS 12+)
57	- [ ] Check for existing ML code or models
58	- [ ] Identify project structure and source file locations
59	- [ ] Determine if SwiftUI or UIKit/AppKit
60
61	### 2. Conflict Detection
62	Search for existing ML integration:
63	```
64	Glob: */Model.swift, /Classifier.swift, /Predictor.swift, /.mlmodel, */.mlmodelc, */.mlpackage
65	Grep: "import CoreML" or "import Vision" or "import NaturalLanguage"
66	```
67
68	If found, ask user:
69	- Extend existing ML setup?
70	- Replace with new implementation?
71	- Add additional model/capability?
72
73	## Configuration Questions
74
75	Ask user via AskUserQuestion:
76
77	1. What ML capability do you need?
78	- Image classification (identify objects in photos)
79	- Object detection (locate objects with bounding boxes)
80	- Text analysis (sentiment, entities, language)
81	- Custom Core ML model integration
82	- Vision framework (OCR, faces, poses)
83	- Sound classification
84	- Tabular data prediction
85
86	2. Do you have a trained model, or need to train one?
87	- I have a .mlmodel / .mlpackage file
88	- I want to train with Create ML
89	- I want to use Apple's built-in models (Vision / NaturalLanguage)
90
91	3. Performance requirements?
92	- Real-time (camera feed, < 33ms per prediction)
93	- Interactive (user-initiated, < 500ms acceptable)
94	- Background processing (batch, latency not critical)
95
96	## Core ML Model Integration
97
98	### Adding a Model to Xcode
99	1. Drag `.mlmodel` or `.mlpackage` into Xcode project navigator
100	2. Xcode auto-generates a Swift class with the model name
101	3. The generated class provides type-safe input/output interfaces
102	4. Xcode compiles to `.mlmodelc` at build time (optimized for device)
103
104	### Loading Models

People who liked this also viewed

6 picks

Type

core-ml

277installs46forks

View on GitHub

How to install core-ml?

rshankras/claude-code-apple-skills/core-ml

$npx -y skills add rshankras/claude-code-apple-skills --skill core-ml

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Core ML Skills
2
3	Combined advisory, generator, and workflow skill for integrating machine learning into Apple platform apps. Covers Core ML model integration, Vision framework image analysis, NaturalLanguage framework text processing, Create ML training, and on-device model optimization.
4
5	## When This Skill Activates
6
7	Use this skill when the user:
8	- Wants to add ML capabilities to their app
9	- Needs to integrate a Core ML model (.mlmodel) into an Xcode project
10	- Wants to use the Vision framework for image analysis (faces, text recognition, body pose, object detection)
11	- Wants to use the NaturalLanguage framework for text processing (sentiment, entities, language detection)
12	- Needs to train a custom model with Create ML
13	- Wants to optimize a model for on-device use (quantization, pruning, palettization)
14	- Needs to choose between Core ML and Foundation Models (Apple Intelligence)
15	- Asks about image classification, object detection, sound classification, or tabular data prediction
16	- Wants real-time camera + ML processing
17
18	## Decision Guide: Core ML vs Foundation Models
19
20	Before generating code, determine which framework is appropriate.
21
22	### Use Foundation Models (Apple Intelligence) When:
23	- You need general-purpose text generation, summarization, or conversational AI
24	- Target is iOS 26+ / macOS 26+ (Foundation Models requires Apple Silicon + latest OS)
25	- The task is open-ended language understanding or generation
26	- You want `@Generable` structured output from natural language
27	- See `apple-intelligence/foundation-models/` skill for implementation
28
29	### Use Core ML When:
30	- You need specialized ML: image classification, object detection, sound classification, custom regression/classification
31	- You have a trained model (.mlmodel, .mlpackage) or plan to train one
32	- You need broad device support (iOS 14+ / macOS 11+)
33	- The task requires domain-specific predictions (medical imaging, product recognition, custom NLP)
34	- Performance-critical inference on Neural Engine or GPU
35
36	### Use Vision Framework When (No Custom Model Needed):
37	- Image classification using Apple's built-in models
38	- Face detection and facial landmark analysis
39	- Text recognition (OCR) with `VNRecognizeTextRequest`
40	- Body and hand pose detection
41	- Barcode and QR code scanning
42	- Image similarity and saliency detection
43	- Horizon detection, rectangle detection
44
45	### Use NaturalLanguage Framework When (No Custom Model Needed):
46	- Sentiment analysis on text
47	- Language identification
48	- Tokenization (word, sentence, paragraph boundaries)
49	- Named entity recognition (people, places, organizations)
50	- Word and sentence embeddings for similarity comparison
51	- Lemmatization and part-of-speech tagging
52
53	## Pre-Generation Checks
54
55	### 1. Project Context Detection
56	- [ ] Check deployment target (Core ML requires iOS 11+ / macOS 10.13+; Vision requires iOS 11+; NaturalLanguage requires iOS 12+)
57	- [ ] Check for existing ML code or models
58	- [ ] Identify project structure and source file locations
59	- [ ] Determine if SwiftUI or UIKit/AppKit
60
61	### 2. Conflict Detection
62	Search for existing ML integration:
63	```
64	Glob: */Model.swift, /Classifier.swift, /Predictor.swift, /.mlmodel, */.mlmodelc, */.mlpackage
65	Grep: "import CoreML" or "import Vision" or "import NaturalLanguage"
66	```
67
68	If found, ask user:
69	- Extend existing ML setup?
70	- Replace with new implementation?
71	- Add additional model/capability?
72
73	## Configuration Questions
74
75	Ask user via AskUserQuestion:
76
77	1. What ML capability do you need?
78	- Image classification (identify objects in photos)
79	- Object detection (locate objects with bounding boxes)
80	- Text analysis (sentiment, entities, language)
81	- Custom Core ML model integration
82	- Vision framework (OCR, faces, poses)
83	- Sound classification
84	- Tabular data prediction
85
86	2. Do you have a trained model, or need to train one?
87	- I have a .mlmodel / .mlpackage file
88	- I want to train with Create ML
89	- I want to use Apple's built-in models (Vision / NaturalLanguage)
90
91	3. Performance requirements?
92	- Real-time (camera feed, < 33ms per prediction)
93	- Interactive (user-initiated, < 500ms acceptable)
94	- Background processing (batch, latency not critical)
95
96	## Core ML Model Integration
97
98	### Adding a Model to Xcode
99	1. Drag `.mlmodel` or `.mlpackage` into Xcode project navigator
100	2. Xcode auto-generates a Swift class with the model name
101	3. The generated class provides type-safe input/output interfaces
102	4. Xcode compiles to `.mlmodelc` at build time (optimized for device)
103
104	### Loading Models

People who liked this also viewed

6 picks

Type