From qml-backends
Specialized interop skill for deliberate experiments with native Qiskit Machine Learning abstractions.
How this skill is triggered — by the user, by Claude, or both
Slash command
/qml-backends:qiskit-machine-learning-interopThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when native Qiskit Machine Learning abstractions need to be evaluated or integrated deliberately alongside a PennyLane-first codebase. The goal is to keep native Qiskit ML as a targeted branch for specific experiments such as `EstimatorQNN`, `SamplerQNN`, or `TorchConnector`, rather than letting it accidentally replace the main project architecture.
Use this skill when native Qiskit Machine Learning abstractions need to be evaluated or integrated deliberately alongside a PennyLane-first codebase. The goal is to keep native Qiskit ML as a targeted branch for specific experiments such as EstimatorQNN, SamplerQNN, or TorchConnector, rather than letting it accidentally replace the main project architecture.
TorchConnector against PennyLane-based PyTorch integration.Before applying this skill, identify:
When this skill is applied, native Qiskit ML usage should remain a disciplined experimental branch rather than architectural sprawl.
Creates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.
npx claudepluginhub tquang122/quantum-ml-skills --plugin qml-backends