A workflow assistant for measuring how accurately language models perform on standardized tests, including tests for general knowledge and software engineering.

Use it to prepare NeMo Evaluator Launcher configurations, evaluate regular or quantized models, run supported benchmarks, and check completed results.

It organizes the configuration, deployment, dry runs, monitoring, and verification needed to run model evaluations reliably.

evaluation — Skill for Claude Code by NVIDIA/Model-Optimizer

About the project

NVIDIA Model Optimizer is a library that changes deep-learning models through techniques such as quantization, pruning, distillation, neural architecture search, speculative decoding, and sparsity so they can run more efficiently. Developers use it to optimize Hugging Face, PyTorch, or ONNX models and export checkpoints for inference frameworks such as SGLang, TensorRT-LLM, TensorRT, or vLLM. The catalogue entries provide skills, instructions, and a plugin for using its workflows.

NVIDIA/Model-Optimizer · 5,398 stars · on GitHub · nvidia.github.io

Install

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.

Any agent

npx skills add NVIDIA/Model-Optimizer --skill evaluation

Clone the repo

git clone --depth 1 https://github.com/NVIDIA/Model-Optimizer

Made for: Claude Code.

Or install modelopt, the plugin that ships this one along with the rest of its 16 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/nvidia/model-optimizer/evaluation/github.svg)](https://agentmods.dev/skills/nvidia/model-optimizer/evaluation)

Your own site

<a href="https://agentmods.dev/skills/nvidia/model-optimizer/evaluation"><img src="https://agentmods.dev/badge/skills/nvidia/model-optimizer/evaluation/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/nvidia/model-optimizer/evaluation"><img src="https://agentmods.dev/badge/skills/nvidia/model-optimizer/evaluation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,273 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 4 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high Privilege Escalation · line 124
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
high Privilege Escalation · line 469
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
high Privilege Escalation · line 470
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
high Privilege Escalation · line 471
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00110	$0.02273
Opus 5.5	$0.00044	$0.00909
Sonnet 5.5	$0.00022	$0.00455
Haiku 4.5	$0.00011	$0.00227

Measured 2d ago against content hash 880b6e6c9b07, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evaluation 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 2d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/nel-gym.sh, scripts/nel-next.sh, tests/test_example_mrcr.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

plugins/modelopt/skills/evaluation/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

NeMo Evaluator Launcher Assistant

Guide the user through creating NEL YAML configs, running evaluations, and monitoring progress. NEL manages serving for canaries and full runs; see Step 3's serving-handoff check for external endpoints.

Completed-run analysis

For completed runs, skip launch/config; use launching-evals for artifacts/analysis and apply run-validation.md before scores. Its policy overrides blanket uncapping and fixed token/context limits.

Workspace integration

If MODELOPT_WORKSPACE_ROOT is set, use the common skill's workspace-management.md and reuse existing workspaces (PTQ → checkpoint smoke test → NEL evaluation; carry compatibility requirements into NEL's deployment config).

Workflow

- [ ] Step 0: Check workspace (if MODELOPT_WORKSPACE_ROOT set)
- [ ] Step 1: Check `nel` install + existing config; set up `.env` (+ `modelopttools:eval-config` for judge-scored runs)
- [ ] Step 2: Build base config (5-question flow OR shortcut)
- [ ] Step 3: Configure deployment (model path, params, cross-check)
- [ ] Step 4: Fill remaining ??? values
- [ ] Step 5: Confirm tasks (iterative)
- [ ] Step 6: Multi-node (if needed)
- [ ] Step 7: Interceptors (if needed)
- [ ] Step 7.5: Container auth (SLURM private images)
- [ ] Step 8: Dry-run → canary → full run
- [ ] Step 9: Verify completed run

nel-next path (Terminal-Bench 2.x, SWE-bench, …) — branch here FIRST

A few agentic AA benchmarks do not run on the currently validated nemo-evaluator-launcher 0.2.6 path (Steps 1–9 don't apply). They run on nel-next (nemo-evaluator[harbor] 0.4.x) — a separate package, CLI (nel eval run), -O overrides, and services/benchmarks/cluster/output schema. If the user asks for one, do not add it to a 0.2.6 evaluation.tasks list — instead:

Read references/nel-next.md (shared: venv, schema, AWS creds, architecture, timeout strategy, MLflow, run flow) + the per-benchmark recipe recipes/tasks/aa_next/{terminal_bench_2_1,swebench_verified}.md; start from recipes/examples/example_eval_next.yaml. Read model-card research for generation settings; consult task-specific policy before selecting published budgets or fallbacks.
Isolated nel-next venv: "$SKILL_DIR/scripts/nel-next.sh" --setup-only (keeps 0.2.6 nel untouched).
Run modelopttools:eval-config (Step 3b) to write the AWS-sandbox creds + harbor infra rows (${NEL_NEXT_EVAL_IMAGE}, ${HARBOR_*_ECR_REPOSITORY}, ${HARBOR_ECS_REGION}) into .env; always include the output.export_config.mlflow block.
Dry-run → canary → full (nel-next.sh eval run), then push to MLflow — SLURM doesn't auto-export, so run nel-next.sh mlflow-push -r <run_id> -c <cfg> after (config-driven; see references/nel-next.md).
Before reporting a full-run score, apply references/run-validation.md, including its benchmark-specific checks.

Read the full file on GitHub · 152 lines

Files

What ships with it

34 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.

Changes

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.

2d ago Changed · +3 lines 880b6e6c9b07
7d ago Changed · +1 lines c7d58bc15b60
13d ago Changed · +3 lines d742aff64a74
15d ago Changed · -3 tokens per session ed44a553495e
16d ago Changed · +4 lines · +18 tokens per session 5d916a48064e
23d ago Changed · +2 lines 4dd8b93f64be
29d ago Changed · -408 lines ffb5ba391b16
1mo ago Changed · -21 lines e77895e431e9
1mo ago Changed · +38 lines e112b13af630
1mo ago First seen · 530 lines · 95 tokens per session scan A 55e0ed27957a

Subscribe to this mod's changes

evaluation is a skill published in the GitHub repository NVIDIA/Model-Optimizer (5,398 stars, last pushed today), licensed Apache-2.0. It adds 110 tokens to every session and 2,273 once invoked, about $0.0004 per session on Opus 5.5. 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.

Analytics and metrics Data and AI

agent-platform-model-registry

Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.

google/skills · 60 tokens

foundry-config-setup

Resolve missing setup caused by a hardcoded Foundry project endpoint or model in a sample. Use when a sample fails because it uses a placeholder/hardcoded projectendpoint (for example "https://your-project.services.ai.azure.com") or a hardcoded model instead of reading them from the environment.

microsoft/agent-framework · 65 tokens

google-cloud-solution-agentic-analytics-spark-knowledge-catalog

Discovers requirements and designs an end-to-end governed agentic analytics solution using Knowledge Catalog and Managed Service for Apache Spark (Lightning Engine). Use when designing data science and analytics workflows across structured and unstructured distributed data (including in S3, Azure Blob, AlloyDB, and…

google/skills · 132 tokens

training-check

Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.

wanshuiyin/Auto-claude-code-research-in-sleep · 35 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens

finetuning

Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file…

microsoft/skills · 132 tokens