AutoGineer
Generated banner for Nemo Rl Brev Etiquette
Generated logo for Nemo Rl Brev Etiquette

Nemo Rl Brev Etiquette

NVIDIAOfficialPublished by NVIDIA

  • Skill
  • Guidelines
  • Cloud and DevOps
  • Apache-2.0
  • Medium risk
Download ZIP

From the author

Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.
— the description by NVIDIA

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a structured approach to managing disk space and environment configuration on Brev instances. It establishes a clear separation between the source code repository located in /home/ubuntu/RL and the high-capacity /ephemeral volume used for heavy experiment artifacts, logs, and caches. By following these patterns, agents can prevent disk exhaustion, maintain clean git repositories, and securely handle sensitive credentials like W&B or Hugging Face tokens.

What it does

  • Defines directory structures to separate source code from experiment data.
  • Provides patterns for redirecting caches and temporary files to the /ephemeral volume.
  • Outlines secure procedures for loading and managing environment variables from .env files.
  • Establishes a checklist for monitoring disk capacity before and during long-running jobs.
  • Standardizes the organization of experiment logs, checkpoints, and artifacts.
  • Offers guidance on cleaning up experiment data without disrupting shared caches.

When to use it

  • When launching NeMo-RL auto-research campaigns on a Brev instance.
  • Before starting training jobs or experiments that generate large logs or checkpoints.
  • When configuring environments that require authenticated access to W&B or Hugging Face.
  • When managing shared caches for tools like PyTorch, Hugging Face, or pip.
  • When disk space in the primary workspace is limited and requires offloading to /ephemeral.

Advantages

  • Prevents workspace disk overflow by offloading heavy assets to /ephemeral.
  • Keeps git repositories clean and focused on code rather than bulky artifacts.
  • Ensures reproducible experiments by standardizing path management.
  • Improves security by centralizing and protecting sensitive environment variables.
  • Facilitates efficient resource usage through shared cache directories.

Usage examples

“How should I configure my environment variables for a new NeMo-RL run on Brev?”
The agent will guide you to store secrets in /home/ubuntu/RL/.env and provide the shell snippet to safely load them into the environment before execution.
“I am running out of disk space on my Brev instance during a training job. What should I do?”
The agent will instruct you to check disk usage with df -h, move large output directories to /ephemeral, and update your configuration to point cache and log paths to the /ephemeral volume.

Install

  1. Download the skill as a ZIP:

    https://autogineer.com/agent-skills/nvidia/nemo-rl-brev-etiquette/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip nemo-rl-brev-etiquette.zip -d .agents/skills

Documentation by NVIDIA

Brev Etiquette

Operate as though /home/ubuntu/RL is the source checkout and /ephemeral is the working storage for generated experiment state. Keep the repo small, reproducible, and easy to inspect. Move bulky run outputs to /ephemeral before launching anything expensive.

Storage Rules

  • Keep code edits, small config changes, committed experiment hypotheses, and concise reproducibility records under /home/ubuntu/RL.

  • Put generated experiment assets under /ephemeral, including checkpoints, run logs, Ray temp directories, W&B offline files, profiler traces, evaluation dumps, rollout samples, and per-experiment artifacts.

  • Keep reusable caches under one shared /ephemeral cache root per user, not under each experiment. This includes Hugging Face models, dataset caches, PyTorch caches, Triton caches, uv caches, and pip caches.

  • Before a campaign or long run, check capacity with df -h /home/ubuntu/RL /ephemeral and avoid starting if /ephemeral is missing or nearly full.

  • Create a campaign root such as /ephemeral/nemo-rl/${USER:-ubuntu}/nemo-rl-auto-research/<campaign> and use one subdirectory per experiment.

  • Do not leave large files, cache directories, or generated outputs in the git checkout. If a tool defaults to the repo, override its output/cache path before running it.

Environment Secrets

  • Treat /home/ubuntu/RL/.env as the local secret store. It may contain keys such as WANDB_API_KEY, HF_TOKEN, or HUGGING_FACE_HUB_TOKEN.

  • Before any run that may need external auth, load /home/ubuntu/RL/.env when it exists. Never print, cat, log, commit, or summarize secret values.

  • If /home/ubuntu/RL/.env is absent, or a required key is still unset after loading it, remind the user to add the needed key to that file before launching authenticated work.

if [ -f /home/ubuntu/RL/.env ]; then
  set -a
  . /home/ubuntu/RL/.env
  set +a
else
  echo "Missing /home/ubuntu/RL/.env; add required keys such as WANDB_API_KEY or HF_TOKEN before authenticated runs."
fi

Auto-Research Pattern

When using nemo-rl-auto-research, keep the git ledger in the repo and heavy evidence on /ephemeral.

if [ -f /home/ubuntu/RL/.env ]; then
  set -a
  . /home/ubuntu/RL/.env
  set +a
fi

BREV_ROOT=/ephemeral/nemo-rl/${USER:-ubuntu}
CACHE_ROOT=$BREV_ROOT/cache
CAMPAIGN_ROOT=$BREV_ROOT/nemo-rl-auto-research/<campaign>
EXP_DIR=$CAMPAIGN_ROOT/<experiment>
mkdir -p "$EXP_DIR"/{logs,checkpoints,artifacts,ray,tmp,wandb}
mkdir -p "$CACHE_ROOT"/{huggingface,torch,triton,uv,pip,xdg,wandb}

export HF_HOME=$CACHE_ROOT/huggingface
export HF_HUB_CACHE=$HF_HOME/hub
export HF_DATASETS_CACHE=$HF_HOME/datasets
export TRANSFORMERS_CACHE=$HF_HOME/transformers
export TORCH_HOME=$CACHE_ROOT/torch
export TRITON_CACHE_DIR=$CACHE_ROOT/triton
export UV_CACHE_DIR=$CACHE_ROOT/uv
export PIP_CACHE_DIR=$CACHE_ROOT/pip
export XDG_CACHE_HOME=$CACHE_ROOT/xdg
export WANDB_CACHE_DIR=$CACHE_ROOT/wandb
export RAY_TMPDIR=$EXP_DIR/ray
export TMPDIR=$EXP_DIR/tmp
export WANDB_DIR=$EXP_DIR/wandb

Record the absolute /ephemeral paths in the nemo-rl-auto-research TSV fields for log path, checkpoint path, artifacts, shared cache root, and command. If the TSV itself may grow large, store the full TSV in /ephemeral and keep a small pointer file or summary in the repo.

Launch Checklist

  • Inspect disk first: df -h /home/ubuntu/RL /ephemeral.

  • Choose a unique /ephemeral run root before editing recipes or launching jobs.

  • Reuse a shared cache root such as /ephemeral/nemo-rl/${USER:-ubuntu}/cache across experiments unless a run explicitly requires a clean cache.

  • Override recipe output paths, logger paths, checkpoint paths, and temp paths to point under the experiment directory.

  • Override cache paths to point under the shared cache root.

  • Stream stdout/stderr to $EXP_DIR/logs/run.log or an equivalent file under /ephemeral.

  • Periodically check disk during long runs with df -h /ephemeral and stop gracefully if the volume is approaching exhaustion.

  • At the end, summarize the important metrics and paths in the repo ledger; do not copy bulky artifacts back into /home/ubuntu/RL.

Cleanup

  • Clean only files that belong to the current campaign or experiment.

  • Prefer pruning clearly named experiment directories under /ephemeral/nemo-rl/...; never remove shared caches or another user's run directory without an explicit instruction.

  • Preserve enough small metadata in the repo to reproduce a result after /ephemeral is cleaned.

Files

BENCHMARK.md

Evaluation Report

Evaluation of the nemo-rl-brev-etiquette skill before publication through NVSkills-Eval.

This benchmark summarizes 3-Tier Evaluation from NVSkills-Eval results for the skill. The goal is to document whether the skill is safe, discoverable, effective, and useful for agents before it is published for broader workflow use.

Evaluation Summary

  • Skill: nemo-rl-brev-etiquette

  • Evaluation date: 2026-06-01

  • NVSkills-Eval profile: external

  • Environment: local

  • Dataset: 4 evaluation tasks

  • Attempts per task: 2

  • Pass threshold: 50%

  • Overall verdict: PASS

Agents Used

  • claude-code

  • codex

Metrics Used

Reported benchmark dimensions:

  • Security: checks whether skill-assisted execution avoids unsafe behavior such as secret leakage, destructive commands, or unauthorized access.

  • Correctness: checks whether the agent follows the expected workflow and produces the correct final output.

  • Discoverability: checks whether the agent loads the skill when relevant and avoids using it when irrelevant.

  • Effectiveness: checks whether the agent performs measurably better with the skill than without it.

  • Efficiency: checks whether the agent uses fewer tokens and avoids redundant work.

Underlying evaluation signals used in this run:

  • security (Security): checks for unsafe operations, secret leakage, and unauthorized access.

  • skill_execution (Skill Execution): verifies that the agent loaded the expected skill and workflow.

  • skill_efficiency (Efficiency): checks routing quality, decoy avoidance, and redundant tool usage.

  • accuracy (Accuracy): grades final-answer correctness against the reference answer.

  • goal_accuracy (Goal Accuracy): checks whether the overall user task completed successfully.

  • behavior_check (Behavior Check): verifies expected behavior steps, including safety expectations.

  • token_efficiency (Token Efficiency): compares token usage with and without the skill.

Test Tasks

The benchmark dataset contained 4 evaluation tasks:

  • Positive tasks: 2 tasks where the skill was expected to activate.

  • Negative tasks: 2 tasks where no skill was expected.

  • Unlabeled tasks: 0 tasks where positive/negative intent could not be inferred.

Task composition is derived from the evaluation dataset when possible. Entries with expected_skill set are treated as positive skill-activation cases, while entries with expected_skill: null are treated as negative activation cases.

Results

DimensionNumclaude-codecodex
Security8100% (+0%)100% (+0%)
Correctness881% (+6%)84% (+12%)
Discoverability8100% (+0%)86% (+2%)
Effectiveness884% (+9%)72% (+12%)
Efficiency888% (+1%)78% (+3%)

Score values show skill-assisted performance. Values in parentheses show uplift versus the no-skill baseline when baseline data is available.

Tier 1: Static Validation Summary

Tier 1 validation passed with observations. NVSkills-Eval ran 9 checks and found 11 total findings.

Top findings:

  • MEDIUM QUALITY/quality_correctness: SKILL_SPEC recommended field missing: 'metadata.author' (skills/nemo-rl-brev-etiquette/SKILL.md)

  • MEDIUM QUALITY/quality_correctness: SKILL_SPEC recommended field missing: 'metadata.tags' (skills/nemo-rl-brev-etiquette/SKILL.md)

  • MEDIUM SCHEMA/body_recommended_section: Missing recommended section: '## Instructions' (skills/nemo-rl-brev-etiquette/SKILL.md)

  • MEDIUM SCHEMA/body_recommended_section: Missing recommended section: '## Examples' (skills/nemo-rl-brev-etiquette/SKILL.md)

  • MEDIUM SCHEMA/author_missing: Author not specified in metadata (skills/nemo-rl-brev-etiquette/SKILL.md)

Tier 2: Deduplication Summary

Tier 2 validation passed. NVSkills-Eval ran 2 checks and found 0 total findings.

Notable observations:

  • Context Deduplication: Collected 1 file(s)

  • Inter-Skill Deduplication: Parsed skill 'nemo-rl-brev-etiquette': 454 char description

Publication Recommendation

The skill is suitable to proceed toward NVSkills-Eval publication based on this benchmark. Skill owners should keep this file with the skill and refresh it when the evaluation dataset, skill behavior, or target agents materially change.

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Needs an API key

Security

What our scanner noticed· Medium risk

  • Large base64-encoded blobs

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Published by
NVIDIA
Publisher
NVIDIA (Official)
Source
NVIDIA/skills · skills/nemo-rl-brev-etiquette · commit fce3cca
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE-APACHE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by NVIDIA or NVIDIA.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download nemo-rl-brev-etiquette.zip