Mindquantum

What it does

When your agent uses it

• Code imports mindquantum
• The user mentions MindQuantum
• Quantum circuits in Python with MindSpore
• Asks about quantum simulation

Example prompts

• “/mindquantum”

Requirements

• Python 3

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Endianness: MindQuantum uses little-endian — qubit 0 is the rightmost (least significant) bit in state vectors and measurement results.
2. 2get_expectation_with_grad requires encoder+ansatz split: If your circuit has no as_encoder() call, all params are treated as ansatz…
3. 3MindSpore context: mindquantum.framework operations are documented as PYNATIVE_MODE only. Use ms.set_device("CPU") with…
4. 4Simulator state persistence: apply_circuit and apply_gate modify the simulator state. Use sim.reset() to return to |0⟩. sampling does not…
5. 5Noise via Monte Carlo: When using noise channels with mqvector, each call to sampling runs Monte Carlo trajectories. Results are…
6. 6UN requires a list: UN(H, 5) is wrong — use UN(H, range(5)) or UN(H, [0,1,2,3,4]).

What it can do on your machine

Read from SKILL.md and the folder at commit 2a0ca08. 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:

  • pip
  • python

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

• Network

  No URLs in SKILL.md. Its commands use pip, which can reach the network depending on how they are called.

  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

Mindquantum loads about 2.3k tokens when it runs. Until then it costs about 112 tokens; SKILL.md has 698 words of instructions outside code blocks.

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

~112

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

~2.3k

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 mindspore-ai/mindquantum at commit 2a0ca08, republished under its Apache-2.0 licence (© mindspore-ai). 698 words, ~2,279 tokens.

name

mindquantum

description

Build, simulate, and analyze quantum circuits with MindQuantum. Provides API patterns, simulator selection, circuit construction, operator algebra, and common pitfalls. Use whenever code imports mindquantum, the user mentions MindQuantum, quantum circuits in Python with MindSpore, or asks about quantum simulation, parameterized quantum circuits, quantum gates, Hamiltonians, or quantum computing in the MindQuantum/MindSpore ecosystem.

python -c "import mindquantum; print(mindquantum.__version__)"

# Python 3.9-3.12 is required by this package.
pip install mindquantum

# Minimal verification
import mindquantum as mq
from mindquantum.core.circuit import Circuit
from mindquantum.core.gates import H, CNOT
from mindquantum.simulator import Simulator

circ = Circuit().h(0).x(1, 0)
sim = Simulator("mqvector", 2)
sim.apply_circuit(circ)
print(sim.get_qs(ket=True))
# Expected: √2/2¦00⟩ + √2/2¦11⟩

from mindquantum.core.circuit import Circuit
from mindquantum.core.gates import H, RX, RY, CNOT, Measure
from mindquantum.core.operators import QubitOperator, Hamiltonian
from mindquantum.simulator import Simulator

# Build circuit
circ = Circuit()
circ += H.on(0)
circ += CNOT.on(1, 0)  # target=1, control=0
circ += RX("theta").on(0)  # parameterized gate

# Simulate
sim = Simulator("mqvector", 2)
sim.apply_circuit(circ, pr={"theta": 0.5})
print(sim.get_qs(ket=True))

# Sample
circ += Measure().on(0)
circ += Measure().on(1)
sim.reset()
result = sim.sampling(circ, pr={"theta": 0.5}, shots=1000)

X.on(1, 0)  # CNOT: target=1, control=0
X.on(0, [1, 2])  # Toffoli: target=0, controls=[1,2]
H.on(0)  # Single-qubit gate on qubit 0

RX("alpha").on(0)  # named parameter
RX({"alpha": 2}).on(0)  # scaled: rotation = 2*alpha
RX(1.5).on(0)  # fixed value (not trainable)

circ1 + circ2  # concatenate
circ * 3  # repeat 3 times
circ.hermitian()  # adjoint / inverse
dagger(circ)  # same as hermitian()
UN(H, range(5))  # apply H to qubits 0-4

encoder = Circuit().rx("x0", 0).ry("x1", 1)
encoder.as_encoder()  # marks params as data-encoding (not trainable)

ansatz = Circuit().ry("w0", 0).x(1, 0).ry("w1", 1)
ansatz.as_ansatz()  # marks params as trainable (default)

full_circuit = encoder + ansatz

© mindspore-ai, Apache-2.0. 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 5 other files in skills/mindquantum of mindspore-ai/mindquantum.

• SKILL.md
• reference/circuit-and-gates.md
• reference/io-and-visualization.md
• reference/operators-hamiltonian.md
• reference/parameter-resolver.md
• reference/simulator-backends.md

Open the folder on GitHubat commit 2a0ca08