Use when deploying ANY machine learning model on-device, converting models to CoreML, compressing models, or implementing speech-to-text. Covers CoreML conversion, MLTensor, model compression (quantization/palettization/pruning), stateful models, KV-cache, multi-function models, async prediction, SpeechAnalyzer, SpeechTranscriber.
You MUST use this skill for ANY on-device machine learning or speech-to-text work.
Use this router when:
Implementation patterns → /skill coreml
API reference → /skill coreml-ref
Diagnostics → /skill coreml-diag
Implementation patterns → /skill speech
| Thought | Reality |
|---|---|
| "CoreML is just load and predict" | CoreML has compression, stateful models, compute unit selection, and async prediction. coreml covers all. |
| "My model is small, no optimization needed" | Even small models benefit from compute unit selection and async prediction. coreml has the patterns. |
| "I'll just use SFSpeechRecognizer" | iOS 26 has SpeechAnalyzer with better accuracy and offline support. speech skill covers the modern API. |
coreml:
coreml-diag:
speech:
User: "How do I convert a PyTorch model to CoreML?"
→ Invoke: /skill coreml
User: "Compress my model to fit on iPhone"
→ Invoke: /skill coreml
User: "Implement KV-cache for my language model"
→ Invoke: /skill coreml
User: "Model loads slowly on first launch"
→ Invoke: /skill coreml-diag
User: "My compressed model has bad accuracy"
→ Invoke: /skill coreml-diag
User: "Add live transcription to my app"
→ Invoke: /skill speech
User: "Transcribe audio files with SpeechAnalyzer"
→ Invoke: /skill speech
User: "What's MLTensor and how do I use it?"
→ Invoke: /skill coreml-ref