launching-evals

Official

Run, monitor, and debug Nemo Evaluator runs.

AuthorNVIDIA
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Running complex LLM evaluation workflows with Nemo Evaluator Launcher can be error-prone and hard to track across clusters; this skill provides a structured approach to launching, monitoring, debugging, and analyzing evaluations, including artifact export and log inspection.

Core Features & Use Cases

  • Launch evaluations with a config, monitor status and live progress, and collect results.
  • Debug failed runs by inspecting client and server logs, and export artifacts for analysis.
  • Analyze results and metrics across runs with benchmark-specific guidance stored under references.

Quick Start

Submit an evaluation config to start a run and monitor its progress.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: launching-evals
Download link: https://github.com/NVIDIA/skills/archive/main.zip#launching-evals

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.