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.

Install to Claude Code

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