SkillsAdd

nvidia/model-optimizer · Archived

evaluation

Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU",…

First seen Jul 6, 2026

Installation

$ npx skills add https://github.com/nvidia/model-optimizer
View on skills.sh ↗ GitHub repository ↗

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

accessing-mlflow Same source · more installs
nvidia/model-optimizer

Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs b…

12 installs
ptq Same source · more installs
nvidia/model-optimizer

Use when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 q…

12 installs
quant-recipe-search Same source · more installs
nvidia/model-optimizer

Use when the user asks to find, search for, or optimize the best quantization recipe for a mode…

11 installs
launching-evals Same source · more installs
nvidia/model-optimizer

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running ev…

11 installs

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

llm-evaluation Similar name
wshobson/agents

Implement comprehensive evaluation strategies for LLM applications using automated metrics, hum…

11K installs
evaluation-methodology Similar name
wshobson/agents

PluginEval quality methodology — dimensions, rubrics, statistical methods, and scoring formulas…

5.9K installs
scholar-evaluation Similar name
affaan-m/ecc

Structured scholarly-work evaluation for papers, proposals, literature reviews, methods section…

5.1K installs
detection-engineering-coverage-evaluation Similar name
google/skills

Automates the end-to-end detection engineering workflow in Google SecOps using MCP tools. Use w…

4K installs
agent-self-evaluation Similar name
affaan-m/ecc

Use after completing any non-trivial task. The agent self-rates its output on 5 axes — accuracy…

2.9K installs
heuristic-evaluation Similar name
owl-listener/designer-skills

Run an expert review against Nielsen's heuristics and domain criteria, with severity ratings. U…

1.6K installs

Also in this package

Other skills from nvidia/model-optimizer · top by installs.

npx skills add https://github.com/nvidia/model-optimizer
accessing-mlflow 12 ptq 12 quant-recipe-search 11 launching-evals 11 compare-results 11 day0-release 11 monitor 10 debug 10 deployment 8 release-cherry-pick 7

Browse all from nvidia/model-optimizer

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Also listed on

Alternate registries and mirrors of this skill.

Repository health

Stars 3.8K
License LICENSE
Default branch main
Open issues 93
Status Archived

History

  1. First seen on skills.sh
  2. First recorded snapshot · 10 installs