← All skills
evaluation
47 / 100 · High risk
Only if you trust the author. Some of what it can do is expected: a devops skill usually runs commands, installs tools and uses cloud credentials.
By NVIDIA/Model-Optimizer (GitHub) · devops · 5,579 stars · scanned at commit 6713c5a
Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU", "evaluate quantized model", "run nel". Handles deployment, config generation, and evaluation execution. Always load when validating completed runs or reporting evaluation scores, including standalone launching-evals analysis. Not for quantizing models (use ptq), standalone serving (use deployment), or comparing completed baseline-vs-quantized r…
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. It runs automatically when the plugin is installed. Expected for a devops skill.
Found in 21 places.
Show 17 more
- plugins/modelopt/skills/evaluation/recipes/tasks/gym/mrcr.md, line 135
sub-venv loop also swallows `uv pip install` failures (`|| true`). Both are - plugins/modelopt/skills/evaluation/recipes/tasks/livecodebench.md, line 18
python -m pip install --quiet --no-cache-dir --no-deps --force-reinstall "git+https://github.com/wasiahmad/livecodebench.git@7b16053825437528ce2e00a58213f0ae4f6 - plugins/modelopt/skills/evaluation/references/launcher-workflow.md, line 31
Run `nel --version`; if missing, instruct `pip install nemo-evaluator-launcher`. - plugins/modelopt/skills/evaluation/references/model-card-research.md, line 35
- When using `pip install` in `pre_cmd`, always use `--no-cache-dir` to avoid cross-device link errors in Docker containers (the pip cache and temp directories - plugins/modelopt/skills/evaluation/references/model-card-research.md, line 36
- Example: `pre_cmd: pip3 install --no-cache-dir flash-attn --no-build-isolation` - plugins/modelopt/skills/evaluation/scripts/nel-gym.sh, line 32
command -v uvx >/dev/null 2>&1 || { - plugins/modelopt/skills/evaluation/scripts/nel-gym.sh, line 33
echo "ERROR: 'uvx' is required to run the pinned NeMo Gym launcher" >&2 - plugins/modelopt/skills/evaluation/scripts/nel-gym.sh, line 37
exec uvx --python 3.10 --from "$NEL_GYM_SPEC" nel "$@" - plugins/modelopt/skills/evaluation/scripts/nel-next.sh, line 60
_uvx() { uvx --python 3.12 --from "$INSTALL_SPEC" "$@"; } - plugins/modelopt/skills/evaluation/scripts/nel-next.sh, line 132
command -v uvx >/dev/null 2>&1 || { echo "ERROR: 'uvx' not found (curl -LsSf https://astral.sh/uv/install.sh | sh)" >&2; exit 1; } - plugins/modelopt/skills/evaluation/scripts/nel-next.sh, line 136
--which) echo "uvx --python 3.12 --from \"${INSTALL_SPEC}\" nel"; exit 0 ;; - plugins/modelopt/skills/evaluation/scripts/nel-next.sh, line 142
exec uvx --python 3.12 --from "$INSTALL_SPEC" nel "$@" - plugins/modelopt/skills/evaluation/tests/test_nel_gym.py, line 24
args_file = tmp_path / "uvx-args" - plugins/modelopt/skills/evaluation/tests/test_nel_gym.py, line 25
uvx = tmp_path / "uvx" - plugins/modelopt/skills/evaluation/tests/test_nel_gym.py, line 26
uvx.write_text('#!/usr/bin/env bash\nprintf "%s\\n" "$@" > "$UVX_ARGS_FILE"\n') - plugins/modelopt/skills/evaluation/tests/test_nel_gym.py, line 27
uvx.chmod(0o755) - plugins/modelopt/.claude-plugin/plugin.json, line 22
"command": "uvx",
and 1 more places
Sends data to these websites: astral.sh, huggingface.co
The author does not mention this. Expected for a devops skill.
Found in 7 places.
Show 4 more
Reads your saved credentials, such as SSH keys or .env files
The author does not mention this. Expected for a devops skill.
Found in 3 places.
Changes files outside its own folder
The author does not mention this.
Found in 2 places.
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. It runs automatically when the plugin is installed. Expected for a devops skill.
Found in 4 places.
Show 1 more
Safer alternatives
Low-risk skills in the same category (devops) that look related. Check that one does what you need.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'evaluation' ] || [ -L ~/.agents/skills/'evaluation' ]; then echo 'A skill folder named evaluation already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/NVIDIA/Model-Optimizer' "$d" && git -C "$d" checkout --quiet '6713c5a679fab80fdd9b688df01845f545c307b1' -- 'plugins/modelopt/skills/evaluation' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/modelopt/skills/evaluation' ~/.agents/skills/'evaluation' && rm -rf "$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/'evaluation' ~/.claude/skills/'evaluation' (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/Model-Optimizer shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/NVIDIA/Model-Optimizer/)
Score history
| Date | Version | Score |
|---|
| 2026-11-10 | 6713c5a | 47 |