Ryusei Nishide
Community@nishide-dev · Nagoya, Japan
Agent Skills by Ryusei Nishide
Showing 21 vetted skills indexed across 1 GitHub repositories.
ml-debug
Diagnose ML training failures and generate actionable debug reports from logs.
ml-transformers
Build Hugging Face Transformer fine-tuning pipelines on PyTorch Lightning.
ml-config-manager
Generates Hydra configuration files for PyTorch Lightning ML training and Optuna sweeps.
ml-hydra-config
Compose hierarchical Hydra configs with command-line overrides for PyTorch Lightning training runs.
ml-train
Execute PyTorch Lightning and Hydra training runs with monitoring, checkpointing, and W&B integration.
tool-marimo
Convert notebooks into reactive marimo .py files with uv sandboxing.
ml-cli-tools
Build type-hinted Typer CLIs with Rich output for ML workflows.
ml-project-init
Initialize ML research repositories with PyTorch Lightning and Hydra via Copier.
ml-wandb-tracking
Log metrics, hyperparameters, artifacts, and checkpoints to W&B for PyTorch Lightning runs.
ml-lightning-basics
Organize PyTorch Lightning training into LightningModule, LightningDataModule, and Trainer modules.
ml-format
Format Python source code with ruff and optionally auto-fix lint issues.
tool-uv-monorepo
Configure uv workspaces for Python monorepos with a unified dependency graph.
ml-model-export
Export trained PyTorch models to ONNX, TorchScript, and TensorRT formats.
ml-pytorch-geometric
Build graph neural networks with PyTorch Geometric for node and graph classification.
tool-pixi
Manage reproducible ML Python environments with Pixi and pixi.lock.
ml-experiment
Track ML experiment results and store resolved Hydra configurations.
ml-validate
Validates ML project structure, Hydra configs, and runtime instantiation paths before training runs.
ml-setup
Automate ML project environment setup with uv or pixi and dev tooling.
ml-profile
Profile PyTorch Lightning training to diagnose data loading, computation, and GPU memory bottlenecks.
ml-data-pipeline
Create PyTorch Lightning DataModules for vision and graph ML pipelines.
ml-lint
Run Ruff formatting, lint, and optional ty type checks on Python code.