Pennylane hybrid executor
PennyLane integration skill for hybrid quantum-classical machine learning and variational algorithmsFrom its SKILL.md
npx -y skills add a5c-ai/babysitter --skill pennylane-hybrid-executorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
1.7 KB, 234 tokens by cl100k_base, as published. Nobody here has run it
PennyLane Hybrid Executor
Purpose
Provides expert guidance on hybrid quantum-classical workflows using PennyLane, enabling seamless integration of quantum circuits with classical machine learning frameworks.
Capabilities
- Quantum node (QNode) definition and execution
- Automatic differentiation for quantum circuits
- Device-agnostic circuit execution
- Integration with ML frameworks (PyTorch, TensorFlow, JAX)
- Variational algorithm optimization
- Parameter shift rule gradients
- Shot-based and analytic differentiation
- Multi-device workflow orchestration
Usage Guidelines
- QNode Definition: Create differentiable quantum functions with device specification
- Gradient Computation: Select appropriate differentiation method for the use case
- Framework Integration: Seamlessly combine with PyTorch, TensorFlow, or JAX models
- Optimization: Use classical optimizers to train variational circuits
- Device Switching: Test on simulators before deploying to hardware
Tools/Libraries
- PennyLane
- PennyLane-Lightning
- PennyLane-Qiskit
- PennyLane-Cirq
- PennyLane-SF (Strawberry Fields)
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.