Qiskit

This gives Claude full access to Qiskit, IBM's quantum computing framework with 13M+ downloads. You get circuit building with gates and measurements, transpilation that's 83x faster than competitors, and execution on both local simulators and real quantum hardware like IBM's 100+ qubit systems. The skill covers the complete workflow from constructing circuits to optimizing them for hardware constraints to running variational algorithms like VQE and QAOA. Use it when you're prototyping quantum algorithms, need to interface with IBM Quantum or other providers, or want to experiment with quantum chemistry and optimization problems. The reference docs are well organized around primitives, transpilation stages, and the four step Qiskit Patterns workflow.

skills.sh installs: 234
GitHub stars: 33.2K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add davila7/claude-code-templates --skill qiskit --agent claude-code

Installs into .claude/skills of the current project.

Files

Qiskit

Overview

Qiskit is the world's most popular open-source quantum computing framework with 13M+ downloads. Build quantum circuits, optimize for hardware, execute on simulators or real quantum computers, and analyze results. Supports IBM Quantum (100+ qubit systems), IonQ, Amazon Braket, and other providers.

Key Features:

83x faster transpilation than competitors
29% fewer two-qubit gates in optimized circuits
Backend-agnostic execution (local simulators or cloud hardware)
Comprehensive algorithm libraries for optimization, chemistry, and ML

Quick Start

Installation

uv pip install qiskit
uv pip install "qiskit[visualization]" matplotlib

First Circuit

from qiskit import QuantumCircuit
from qiskit.primitives import StatevectorSampler

# Create Bell state (entangled qubits)
qc = QuantumCircuit(2)
qc.h(0)           # Hadamard on qubit 0
qc.cx(0, 1)       # CNOT from qubit 0 to 1
qc.measure_all()  # Measure both qubits

# Run locally
sampler = StatevectorSampler()
result = sampler.run([qc], shots=1024).result()
counts = result[0].data.meas.get_counts()
print(counts)  # {'00': ~512, '11': ~512}