← All skills
cuopt-install
75 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.
By NVIDIA/skills (GitHub) · coding · 3,933 stars · scanned at commit 2630133
Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.
Works with any agent that supports SKILL.md skills.
What this skill can do
Downloads and installs other software
The author does not mention this.
Found in 21 places.
Show 17 more
- skills/cuopt-install/SKILL.md, line 80
pip install --extra-index-url=https://pypi.nvidia.com 'libcuopt-cu12==26.2.*' - skills/cuopt-install/SKILL.md, line 99
pip install --extra-index-url=https://pypi.nvidia.com cuopt-server-cu12 cuopt-sh-client - skills/cuopt-install/benchmark/evals.json, line 22
"ground_truth": "The agent gives 'pip install --extra-index-url=https://pypi.nvidia.com cuopt-cu12==26.2.*' (or equivalent quoting) as the command and notes tha - skills/cuopt-install/benchmark/evals.json, line 27
"Provides the command for the user to run, does not execute pip install" - skills/cuopt-install/benchmark/evals.json, line 35
"ground_truth": "The agent declines to run pip install on the user's behalf, citing the mandatory rule that it must not install packages automatically. It provi - skills/cuopt-install/benchmark/evals.json, line 37
"Refuses to run pip install on the user's behalf", - skills/cuopt-install/benchmark/evals.json, line 46
"question": "I already ran 'pip install cuopt-cu12'. Should I also run 'conda install cuopt' to make sure I have everything?", - skills/cuopt-install/benchmark/evals.json, line 119
"ground_truth": "The agent names 'cuopt-server-cu12' (or cu13 to match installed CUDA) as the server package, plus 'cuopt-sh-client' as the matching Python clie - skills/cuopt-install/benchmark/evals.json, line 131
"question": "I ran 'pip install cuopt-cu12' but 'import cuopt' fails with 'No module named cuopt'. What went wrong?", - skills/cuopt-install/benchmark/evals.json, line 148
"ground_truth": "The agent declines to run the install on the user's behalf, citing the mandatory rule that it MUST NOT install, upgrade, or modify packages — e - skills/cuopt-install/benchmark/evals.json, line 173
"question": "I have CUDA 12 installed and ran 'pip install cuopt-cu13'. Now imports fail with CUDA errors. What happened?", - skills/cuopt-install/benchmark/evals.json, line 176
"ground_truth": "The agent identifies the cause as a CUDA suffix mismatch: the cu13 package was built for CUDA 13.x, but the runtime has CUDA 12.x. The package - skills/cuopt-install/benchmark/evals.json, line 182
"Does not run pip uninstall or pip install on the user's behalf" - skills/cuopt-install/benchmark/evals.json, line 190
"ground_truth": "No local cuOpt install is needed for the GPU-bearing libraries. The agent recommends installing only 'cuopt-sh-client' locally (pip install --e - skills/cuopt-install/benchmark/evals.json, line 204
"ground_truth": "The agent gives 'conda install -c rapidsai -c conda-forge -c nvidia cuopt' as the command. It mentions the three channels are required and that - skills/cuopt-install/evals/evals.json, line 15
"question": "nvidia-smi on my box reports CUDA 13. Which cuOpt Python package do I pip install, and does it matter which one I pick?", - skills/cuopt-install/evals/evals.json, line 18
"ground_truth": "The agent installs the cu13-suffixed package (cuopt-cu13) and explains that the package CUDA suffix must match the runtime CUDA — installing th
and 1 more places
Runs commands on your computer
The author does not mention this. Expected for a coding skill.
Found in 10 places.
Show 7 more
Sends data to these websites: pypi.nvidia.com
The author does not mention this.
Found in 6 places.
Show 3 more
Safer alternatives
Low-risk skills in the same category (coding) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'cuopt-install' ] || [ -L ~/.agents/skills/'cuopt-install' ]; then echo 'A skill folder named cuopt-install already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/NVIDIA/skills' "$d" && git -C "$d" checkout --quiet '2630133f22e357f2005886567a39eddcc1b520e2' -- 'skills/cuopt-install' && mkdir -p ~/.agents/skills && cp -R "$d"/'skills/cuopt-install' ~/.agents/skills/'cuopt-install' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'cuopt-install' ~/.claude/skills/'cuopt-install' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for NVIDIA/skills shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/NVIDIA/skills/)
Score history
| Date | Version | Score |
|---|
| 2026-11-11 | 2630133 | 75 |
| 2026-11-08 | fce3cca | 75 |
| 2026-11-07 | fce3cca | 75 |