pennylane — Claude Code skill: what it does, how to install
Guides an agent in setting up PennyLane 0.45.1 quantum circuits, variational VQE algorithms, and hybrid neural models.
npx skills add K-Dense-AI/scientific-agent-skills --skill pennylane -a claude-codeWhat pennylane does
This skill provides workflows and failure checks for PennyLane 0.45.1. It assists the agent in creating parameterized quantum circuits, calculating analytical gradients, and connecting quantum nodes with PyTorch or JAX. When your task requires specialized hardware compilation, the instructions recommend routing to Qiskit or Cirq, or to QuTiP for open quantum dynamics.
Execution details depend on strict version constraints. You need Python 3.11 or higher alongside NumPy 2+. If you integrate JAX, stick to the tested JAX 0.7.1 and JAXlib 0.7.1 combination because newer releases might cause unexpected issues. The skill also enforces 0.45.1 syntax nuances, such as handling mid-circuit measurements via qml.cond rather than native Python branching, and retrieving circuit stats from the .resources attribute of CircuitSpecs.
Local simulation runs on synthetic toy setups, so successful convergence will not indicate real hardware fidelity. Still, checking mathematical consistency beforehand saves runtime when moving circuits to remote quantum providers.
What it helps with
- construct and differentiate parameterized quantum circuits
- build hybrid quantum-classical pipelines with PyTorch or JAX
- calculate molecular ground state energies using VQE
- set up QAOA circuits for combinatorial MaxCut problems
Example prompts for the agent
- Write a PennyLane quantum node with backprop differentiation to minimize an observable.
- Create a hybrid quantum classification model using PyTorch and TorchLayer.
- Set up a VQE workflow for a small molecule and verify the electron sector.
How to install pennylane
1Skills CLI (Vercel)
npx skills add K-Dense-AI/scientific-agent-skills --skill pennylane -a claude-code2Manually: put the files in place
~/.claude/skills/pennylane/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/pennylane/
1Skills CLI (Vercel)
npx skills add K-Dense-AI/scientific-agent-skills --skill pennylane -a codex2Manually: put the files in place
.agents/skills/pennylane/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add K-Dense-AI/scientific-agent-skills --skill pennylane -a cursor2Manually: put the files in place
.cursor/skills/pennylane/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install K-Dense-AI/scientific-agent-skills pennylane2Manually: put the files in place
.github/skills/pennylane/SKILL.md1Skills CLI (Vercel)
npx skills add K-Dense-AI/scientific-agent-skills --skill pennylane -a gemini-cli2Platform CLI
gemini skills install https://github.com/K-Dense-AI/scientific-agent-skills --path skills/pennylaneManually: put the files in place
.devin/skills/pennylane/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add K-Dense-AI/scientific-agent-skills --skill pennylane -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
From the same set120
The whole set →Similar
Questions about pennylane
How to install pennylane in Claude Code?
Run npx skills add K-Dense-AI/scientific-agent-skills --skill pennylane -a claude-code in your terminal.
What does the pennylane skill do?
It equips the coding agent with execution patterns for PennyLane 0.45.1, covering variational optimization, VQE chemistry routines, and machine learning integration.
What environments and libraries are required?
You need Python 3.11+ and PennyLane 0.45.1 with NumPy 2+. For JAX workflows, the skill specifies the verified JAX 0.7.1 and JAXlib 0.7.1 pair.