Babysitter tensorflow-physics-ml
TensorFlow machine learning skill specialized for physics applications including neural network potentials and surrogate models
install
source · Clone the upstream repo
git clone https://github.com/a5c-ai/babysitter
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/a5c-ai/babysitter "$T" && mkdir -p ~/.claude/skills && cp -r "$T/library/specializations/domains/science/physics/skills/tensorflow-physics-ml" ~/.claude/skills/a5c-ai-babysitter-tensorflow-physics-ml && rm -rf "$T"
manifest:
library/specializations/domains/science/physics/skills/tensorflow-physics-ml/SKILL.mdsource content
TensorFlow Physics ML
Purpose
Provides expert guidance on TensorFlow for physics applications, including physics-informed neural networks and neural network potentials.
Capabilities
- Physics-informed neural networks (PINNs)
- Neural network potentials (NNP)
- Normalizing flows for density estimation
- Graph neural networks for molecular systems
- Automatic differentiation for physics
- TensorBoard experiment tracking
Usage Guidelines
- Architecture Design: Build appropriate neural network architectures
- PINNs: Incorporate physical constraints in loss functions
- Potentials: Train neural network interatomic potentials
- GNNs: Use graph networks for molecular systems
- Training: Monitor and optimize training with TensorBoard
Tools/Libraries
- TensorFlow
- DeepMD-kit
- SchNet