CUDA-Q is a programming platform for hybrid quantum-classical systems that combines quantum processing units with GPUs and CPUs. Developers and researchers use its C++ and Python tools, compiler, runtime, and hardware backends to build and test quantum applications. The catalogue skills support development with CUDA-Q.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NVIDIA/cuda-quantum --skill qiskit-to-cudaqgit clone --depth 1 https://github.com/NVIDIA/cuda-quantumWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nvidia/cuda-quantum/qiskit-to-cudaq)<a href="https://agentmods.dev/skills/nvidia/cuda-quantum/qiskit-to-cudaq"><img src="https://agentmods.dev/badge/skills/nvidia/cuda-quantum/qiskit-to-cudaq/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nvidia/cuda-quantum/qiskit-to-cudaq"><img src="https://agentmods.dev/badge/skills/nvidia/cuda-quantum/qiskit-to-cudaq.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00028 | $0.01510 |
| Opus 5 | $0.00014 | $0.00755 |
| Sonnet 5 | $0.00006 | $0.00302 |
| Haiku 4.5 | $0.00003 | $0.00151 |
Grade A, and why
qiskit-to-cudaq scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Qiskit to CUDA-Q
Purpose
Use this skill to port Qiskit Python code, or code with Qiskit-style circuit construction, to CUDA-Q Python kernels. The goal is a framework-free CUDA-Q port that preserves the source quantum algorithm, matches source behavior at small test sizes, and documents any unavoidable CUDA-Q limitations.
Prerequisites
- Python 3.10+.
- CUDA-Q installed in the target environment. Check the runtime with:
python -c "import cudaq; print(getattr(cudaq, '__version__', 'unknown'))". - Access to the source implementation and a way to run or inspect its expected behavior.
- For validation against Qiskit, Qiskit/Aer must be installed in the validation environment. The final CUDA-Q port itself must not require Qiskit.
- When using CUDA-Q documentation or repository MCP connectors, verify the connector is available before relying on it; otherwise use local docs or the source tree.
- When debugging and the installed CUDA-Q version differs from the latest documentation, review relevant documentation or source changes before treating a behavior difference as a porting bug.
Workflow
- Read the source circuit construction and identify the exact algorithm, qubit/register layout, measurement behavior, and any framework helpers.
- Preserve the high-level quantum algorithm. Do not replace mid-circuit measurement, QPE structure, oracle definitions, or decomposition strategy without explicit user permission.
- Select the CUDA-Q execution pattern:
- Use
cudaq.samplefor final-measurement sampling. - Use
cudaq.runwhen mid-circuit measurement values must be returned or used per shot. - Use runtime-argument kernels instead of generated per-size kernels unless CUDA-Q requires a fixed-length return shape.
- Use
- Translate gates and subcircuits. For detailed gate mappings, ordering rules, precision guidance, and helper-extraction patterns, read references/porting-reference.md.
- Remove runtime source-framework dependencies from the CUDA-Q port. Extract pure helpers into framework-free modules.
- Validate with small deterministic inputs before scaling. Compare raw count keys and distributions, not just aggregate fidelity.
- Re-run any previously failing configurations after every fix.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 155 lines · 28 tokens per session scan A 21e2cfce3e34
qiskit-to-cudaq is a skill published in the GitHub repository NVIDIA/cuda-quantum (1,126 stars, last pushed today), licensed Apache-2.0. It adds 28 tokens to every session and 1,510 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
quantum-algorithms-expert
Develop production-ready quantum algorithms for optimization, simulation, and machine learning on near-term quantum devices. Use when the user mentions quantum computing, Qiskit or Cirq, quantum circuits, QAOA, VQE, Grover or Shor, or quantum machine learning on NISQ devices.
qiskit-quantum
Use this Skill for quantum computing experiments with Qiskit: qubit circuits, gates, measurement, VQE/QAOA variational algorithms, noise models, and statevector vs shot simulation.
cudaq-guide
CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.
cuopt-numerical-optimization-api
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
cuopt-developer
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
tlaplus-spec-generator
Automatically generate TLA+ specifications from source code (C/C++, Python) for formal verification of distributed systems. Use when users need to: (1) Generate TLA+ specs from program implementations, (2) Model distributed systems, consensus protocols, or concurrent algorithms, (3) Extract state variables, actions…