PennyLane Quantum ML
A skill for building, differentiating and training quantum circuits with PennyLane across IBM, Google, Rigetti and IonQ backends.
What it does
Guides Claude in writing PennyLane 0.45 code: constructing quantum circuits, computing gradients automatically (parameter-shift, backprop, adjoint) and optimizing parameters. It covers variational algorithms (VQE, QAOA), quantum neural networks, hybrid models with PyTorch/JAX, and switching between simulators and real hardware (Qiskit/IBM, Braket, Cirq, Rigetti, IonQ). Deeper material lives in a references/ folder split by topic: circuits, QML, quantum chemistry, devices, optimization and advanced features.
Who it's for
- Researchers and grad students working on variational quantum algorithms or QML
- Computational chemists building molecular Hamiltonians, VQE runs and dissociation curves
- Developers who want to benchmark the same circuit across multiple quantum backends
Examples
- "Write a VQE script for the H2 ground-state energy" → Hamiltonian construction, UCCSD ansatz and an Adam optimization loop
- "Build a 4-qubit variational classifier using AngleEmbedding" → QNN with StronglyEntanglingLayers plus a training loop
- "Move my simulator-tested circuit to an IBM backend and use parameter-shift gradients" → device swap and hardware-safe differentiation setup
· · · Install guide · · ·
Install in the Claude app (no terminal)
- Download the ZIP with the button below.
- In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
- Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Install in Claude Code
Let Claude do it — paste this into Claude Code
Install the skill I found on Claude Skill Mart. Copy the skills/pennylane folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/pennylane/. When it's done, tell me in one line what this skill can do.
Install with a command instead
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/pennylane ~/.claude/skills/⚠ This is a third-party skill. Check the source repository before installing.
- Open a terminal and confirm Python 3.11+ and git are installed.
- Clone the repository:
git clone https://github.com/K-Dense-AI/scientific-agent-skills.git - Create the skills directory:
mkdir -p ~/.claude/skills - Copy the whole skill folder so the
references/docs come with it:cp -r scientific-agent-skills/skills/pennylane ~/.claude/skills/ - Install the library in your environment:
uv pip install "pennylane==0.45.0", plus provider plugins such aspennylane-qiskitif you target hardware. - Restart Claude Code and try a prompt like "use PennyLane to write a VQE example" to confirm the skill activates.