Qiskit

What it does

When your agent uses it

• Working with quantum algorithms
• Quantum hardware including
• Building quantum circuits with gates and measurements
• Running quantum algorithms (VQE

Example prompts

• “/qiskit”

Requirements

• Python 3

Workflow steps

8 steps, taken from the step headings in SKILL.md.

1. 1Setup and Installation
2. 2Building Quantum Circuits
3. 3Primitives (Sampler and Estimator)
4. 4Transpilation and Optimization
5. 5Visualization
6. 6Hardware Backends
7. 7Qiskit Patterns Workflow
8. 8Quantum Algorithms and Applications

What it can do on your machine

Read from SKILL.md and the folder at commit 14680ec. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • uv

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • quantum.ibm.com
  • qiskit.org
  • docs.quantum.ibm.com
  • quantum.cloud.ibm.com

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Qiskit loads about 2.2k tokens when it runs, and up to ~18k if it reads all its reference files. Until then it costs about 140 tokens; SKILL.md has 655 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~140

When it runs · the whole SKILL.md, loaded when a task matches

~2.2k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~18k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from davila7/claude-code-templates at commit 14680ec, republished under its MIT licence (© davila7). 655 words, ~2,209 tokens.

name

qiskit

description

Comprehensive quantum computing toolkit for building, optimizing, and executing quantum circuits. Use when working with quantum algorithms, simulations, or quantum hardware including (1) Building quantum circuits with gates and measurements, (2) Running quantum algorithms (VQE, QAOA, Grover), (3) Transpiling/optimizing circuits for hardware, (4) Executing on IBM Quantum or other providers, (5) Quantum chemistry and materials science, (6) Quantum machine learning, (7) Visualizing circuits and results, or (8) Any quantum computing development task.

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

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}

from qiskit.visualization import plot_histogram

qc.draw('mpl')           # Circuit diagram
plot_histogram(counts)   # Results histogram

from qiskit import QuantumCircuit, transpile
from qiskit.primitives import StatevectorSampler

qc = QuantumCircuit(2)
qc.h(0)
qc.cx(0, 1)
qc.measure_all()

sampler = StatevectorSampler()
result = sampler.run([qc], shots=1024).result()
counts = result[0].data.meas.get_counts()

from qiskit_ibm_runtime import QiskitRuntimeService, SamplerV2 as Sampler
from qiskit import transpile

service = QiskitRuntimeService()
backend = service.backend("ibm_brisbane")

qc_optimized = transpile(qc, backend=backend, optimization_level=3)

sampler = Sampler(backend)
job = sampler.run([qc_optimized], shots=1024)
result = job.result()

from qiskit_ibm_runtime import Session, EstimatorV2 as Estimator
from scipy.optimize import minimize

with Session(backend=backend) as session:
    estimator = Estimator(session=session)

    def cost_function(params):
        bound_qc = ansatz.assign_parameters(params)
        qc_isa = transpile(bound_qc, backend=backend)
        result = estimator.run([(qc_isa, hamiltonian)]).result()
        return result[0].data.evs

    result = minimize(cost_function, initial_params, method='COBYLA')

© davila7, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 8 other files (references) in cli-tool/components/skills/scientific/qiskit of davila7/claude-code-templates.

• SKILL.md
• references/algorithms.md
• references/backends.md
• references/circuits.md
• references/patterns.md
• references/primitives.md
• references/setup.md
• references/transpilation.md
• references/visualization.md

Open the folder on GitHubat commit 14680ec

Used in 10 other repositories

We found 35 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 10 other GitHub owners. This page covers the copy in davila7/claude-code-templates, which our catalogue first saw on October 7, 2026.

• Microck/ordinary-claude-skillsskills_all/claude-scientific-skills/scientific-skills/qiskitskills_categorized/scientific-computing/claude-scientific-skills/scientific-skills/qiskit
• aiskillstore/marketplaceskills/davila7/qiskitskills/k-dense-ai/qiskit
• majiayu000/claude-skill-registryskills/ai-ml/qiskitskills/ai-ml/scientific-qiskit+13 more
• sickn33/agentic-awesome-skillsskills/qiskitplugins/agentic-awesome-skills/skills/qiskit+1 more
• lamm-mit/scienceclawskills/qiskit
• agent-skills-hub/agent-skills-hubskills/qiskit
• lingxling/awesome-skills-cnantigravity-awesome-skills/skills/qiskitantigravity-awesome-skills/plugins/agentic-awesome-skills/skills/qiskit+1 more
• LeonChaoX/qinyan-academic-skillsskills/10-材料科学与物理计算/qiskit
• henryalouf/ruflow.agents/skills/qiskit.agents/skills/antigravity-awesome-skills/skills/qiskit+4 more
• infometa/workbuddyskillsplugins/codebuddy-plugins-official/external_plugins/scientific-skills/qiskit