pennylane

Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.

1.07x

Quality

86%

Does it follow best practices?

Impact

89%

1.07x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Evaluation results

90%

Quantum Sentiment Classifier

QML encoding and template usage

Criteria

Without context

With context

PennyLane numpy import

60%

100%

QNode decorator

100%

default.qubit device

100%

Data encoding template

100%

Variational template

100%

Template shape helper

100%

Adam optimizer

100%

requires_grad=True

100%

Circuit drawing

100%

Circuit specs

100%

uv installation

91%

15%

Hydrogen Molecule Ground State Energy

VQE molecular ground state workflow

Criteria

Without context

With context

qchem Hamiltonian

83%

hf_state preparation

100%

BasisState initialization

50%

30%

UCCSD ansatz

100%

UCCSD excitation generation

100%

Zero parameter initialization

100%

Adam optimizer

100%

step_and_cost usage

100%

default.qubit device

100%

PennyLane numpy import

71%

100%

uv installation

100%

88%

-1%

Gradient Benchmarking for Hardware Deployment

Parameter-shift gradients and device selection

Criteria

Without context

With context

parameter-shift diff_method

100%

backprop diff_method

100%

hardware-only note

100%

lightning.qubit device

100%

default.qubit device

100%

qml.grad usage

100%

PennyLane numpy

62%

50%

requires_grad=True

100%

QNode decorator

100%

uv installation

100%

Circuit transform applied

Repository: K-Dense-AI/claude-scientific-skills
Commit: b58ad7e

Evaluated: 27 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Quantum Sentiment Classifier Hydrogen Molecule Ground State Energy Gradient Benchmarking for Hardware Deployment

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.