burn-plugin

This skill should be used when the user asks about "Burn tensors", "tensor operations", "Module derive", "burn config", "autodiff", "backward pass", "gradient", "record serialization", "model weights", or core Burn application development patterns.

This skill should be used when the user asks about "Burn backend", "WGPU", "NdArray", "Candle", "LibTorch", "custom kernel", "CubeCL", "quantization", "WebAssembly", "no_std", or backend selection and extension.

This skill should be used when the user asks about "contributing to Burn", "adding an operation", "burn internals", "burn-tensor", "burn-autodiff", "ONNX converter", "NodeProcessor", or Burn framework development.

Diagnoses Burn deep learning errors including tensor shape mismatches, backend panics, autodiff issues, and training failures. Use when encountering runtime errors, compilation failures, or unexpected behavior in Burn code.

This skill should be used when the user asks about "ONNX import", "PyTorch to Burn", "safetensors", "model conversion", "burn-import", "unsupported operator", "opset version", or importing external models into Burn.

Specializes in ONNX model import failures, unsupported operators, opset version mismatches, and dynamic shape issues. Use when burn-import fails or produces incorrect results.

Reviews Burn deep learning code for idiomatic patterns, performance, backend portability, and best practices. Use when asked for code review, refactoring suggestions, or "is this idiomatic".

This skill should be used when the user mentions "burn", "tensor", "module", "backend", "training", "ONNX", "autodiff", "deep learning in Rust", or any Burn framework related query. Routes to appropriate domain skills and enforces evidence-seeking behavior.

This skill should be used when the user asks about "training loop", "Learner", "metrics", "dataset", "dataloader", "checkpointing", "optimizer", "learning rate scheduler", "custom training", or Burn training workflows.