axiom-ios-ml

# iOS Machine Learning Router

**You MUST use this skill for ANY on-device machine learning or speech-to-text work.**

## When to Use

Use this router when:
- Converting PyTorch/TensorFlow models to CoreML
- Deploying ML models on-device
- Compressing models (quantization, palettization, pruning)
- Working with large language models (LLMs)
- Implementing KV-cache for transformers
- Using MLTensor for model stitching
- Building speech-to-text features
- Transcribing audio (live or recorded)

## Routing Logic

### CoreML Work

**Implementation patterns** → `/skill coreml`
- Model conversion workflow
- MLTensor for model stitching
- Stateful models with KV-cache
- Multi-function models (adapters/LoRA)
- Async prediction patterns
- Compute unit selection

**API reference** → `/skill coreml-ref`
- CoreML Tools Python API
- MLModel lifecycle
- MLTensor operations
- MLComputeDevice availability
- State management APIs
- Performance reports

**Diagnostics** → `/skill coreml-diag`
- Model won't load
- Slow inference
- Memory issues
- Compression accuracy loss
- Compute unit problems

### Speech Work

**Implementation patterns** → `/skill speech`
- SpeechAnalyzer setup (iOS 26+)
- SpeechTranscriber configuration
- Live transcription
- File transcription
- Volatile vs finalized results
- Model asset management

## Decision Tree

```
User asks about on-device ML or speech
  ├─ Machine learning?
  │   ├─ Implementing/converting? → coreml
  │   ├─ Need API reference? → coreml-ref
  │   └─ Debugging issues? → coreml-diag
  └─ Speech-to-text?
      └─ Any speech work → speech
```

## Critical Patterns

**coreml**:
- Model conversion (PyTorch → CoreML)
- Compression (palettization, quantization, pruning)
- Stateful KV-cache for LLMs
- Multi-function models for adapters
- MLTensor for pipeline stitching
- Async concurrent prediction

**coreml-diag**:
- Load failures and caching
- Inference performance issues
- Memory pressure from models
- Accuracy degradation from compression

**spe