Pennylane

A hardware-agnostic quantum ML framework that lets you train quantum circuits with automatic differentiation, just like you would with PyTorch or TensorFlow. You'd reach for this when building variational algorithms like VQE or QAOA, or when you want to prototype quantum neural networks without locking into IBM's Qiskit or Google's Cirq. The killer feature is device portability: write your circuit once and run it on simulators or swap in real quantum hardware from IBM, Google, Rigetti, or IonQ by changing one line. It integrates cleanly with PyTorch, JAX, and TensorFlow for hybrid classical-quantum models. The learning curve is real if you're new to quantum computing, but the API is cleaner than most alternatives once you grok the basics.

skills.sh installs: 2K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill pennylane --agent claude-code

Installs into .claude/skills of the current project.

Files

PennyLane

When to use

Use PennyLane to optimize parameterized circuits, build hybrid quantum-classical models, estimate molecular energies, or compare a validated circuit across devices. This skill targets stable PennyLane 0.45.1. The local examples use small synthetic systems; successful optimization does not establish quantum advantage, molecular accuracy, or hardware fidelity.

Installation

Create a dedicated environment; provider plugins and compiler dependencies should be resolved separately from unrelated scientific packages:

uv venv --python 3.13 .venv-pennylane
uv pip install --python .venv-pennylane/bin/python "pennylane==0.45.1"

PennyLane 0.45 requires NumPy 2+. Core installation includes Lightning. For ML, use the tested JAX 0.7.1/JAXlib 0.7.1 pair or PyTorch; do not assume the latest JAX is supported by this PennyLane release. See device setup for optional plugin versions and their verification limits.