Pennylane

This is your gateway to quantum computing without getting locked into specific hardware. PennyLane lets you build quantum circuits with automatic differentiation, which means you can train them like neural networks using gradient descent. The real win is device independence: write your circuit once, then run it on simulators during development and swap to actual quantum hardware from IBM, Google, Amazon Braket, or others when you're ready. It integrates directly with PyTorch, JAX, and TensorFlow, so you can build hybrid quantum-classical models in your existing ML workflow. Particularly strong for variational algorithms like VQE for quantum chemistry and QAOA for optimization problems. If you're experimenting with quantum machine learning or need to simulate molecular systems, this handles the messy parts of gradient computation and hardware abstraction.

skills.sh installs: 215
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill pennylane --agent claude-code

Installs into .claude/skills of the current project.

Files

PennyLane

Overview

PennyLane is a quantum computing library that enables training quantum computers like neural networks. It provides automatic differentiation of quantum circuits, device-independent programming, and seamless integration with classical machine learning frameworks.

Installation

Install using uv:

uv pip install pennylane

For quantum hardware access, install device plugins:

# IBM Quantum
uv pip install pennylane-qiskit

# Amazon Braket
uv pip install amazon-braket-pennylane-plugin

# Google Cirq
uv pip install pennylane-cirq

# Rigetti Forest
uv pip install pennylane-rigetti

# IonQ
uv pip install pennylane-ionq

Quick Start

Build a quantum circuit and optimize its parameters:

import pennylane as qml
from pennylane import numpy as np

# Create device
dev = qml.device('default.qubit', wires=2)

# Define quantum circuit
@qml.qnode(dev)
def circuit(params):
    qml.RX(params[0], wires=0)
    qml.RY(params[1], wires=1)
    qml.CNOT(wires=[0, 1])
    return qml.expval(qml.PauliZ(0))

# Optimize parameters
opt = qml.GradientDescentOptimizer(stepsize=0.1)
params = np.array([0.1, 0.2], requires_grad=True)

SKILL.md on GitHub