axiom-ios-ml
npx skills add https://github.com/charleswiltgen/axiom --skill axiom-ios-ml
Agent 安装分布
Skill 文档
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 â /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 â /skill coreml-ref
- CoreML Tools Python API
- MLModel lifecycle
- MLTensor operations
- MLComputeDevice availability
- State management APIs
- Performance reports
Diagnostics â /skill coreml-diag
- Model won’t load
- Slow inference
- Memory issues
- Compression accuracy loss
- Compute unit problems
Speech Work
Implementation patterns â /skill speech
- SpeechAnalyzer setup (iOS 26+)
- SpeechTranscriber configuration
- Live transcription
- File transcription
- Volatile vs finalized results
- Model asset management
Decision Tree
- Implementing / converting ML models? â coreml
- CoreML API reference? â coreml-ref
- Debugging ML issues (load, inference, compression)? â coreml-diag
- Speech-to-text / transcription? â speech
Anti-Rationalization
| 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. |
Critical Patterns
coreml:
- Model conversion (PyTorch â 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
speech:
- SpeechAnalyzer + SpeechTranscriber setup
- AssetInventory model management
- Live transcription with volatile results
- Audio format conversion
Example Invocations
User: “How do I convert a PyTorch model to CoreML?”
â Invoke: /skill coreml
User: “Compress my model to fit on iPhone”
â Invoke: /skill coreml
User: “Implement KV-cache for my language model”
â Invoke: /skill coreml
User: “Model loads slowly on first launch”
â Invoke: /skill coreml-diag
User: “My compressed model has bad accuracy”
â Invoke: /skill coreml-diag
User: “Add live transcription to my app”
â Invoke: /skill speech
User: “Transcribe audio files with SpeechAnalyzer”
â Invoke: /skill speech
User: “What’s MLTensor and how do I use it?”
â Invoke: /skill coreml-ref