Nemo Rl Brev Etiquette

What it does

When your agent uses it

• Running nemo-rl-auto-research campaigns
• Dataset downloads
• Shared cache-heavy commands
• Log-producing runs

Example prompts

• “/nemo-rl-brev-etiquette”

Requirements

• A credential in WANDB_API_KEY
• A credential in HUGGING_FACE_HUB_TOKEN

What it can do on your machine

Read from SKILL.md and the folder at commit dfdd080. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • WANDB_API_KEY
  • HF_TOKEN
  • HUGGING_FACE_HUB_TOKEN

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nemo Rl Brev Etiquette loads about 1.3k tokens when it runs. Until then it costs about 119 tokens; SKILL.md has 472 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~119

When it runs · the whole SKILL.md, loaded when a task matches

~1.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NoteMentions a .env fileSKILL.md:4

  ral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, tr

• NoteMentions a .env fileSKILL.md:23

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

• NoteMentions a .env fileSKILL.md:24

  eed external auth, load `/home/ubuntu/RL/.env` when it exists. Never print, `cat`, log, commit, or summarize secret valu

• NoteMentions a .env fileSKILL.md:25

  - If `/home/ubuntu/RL/.env` is absent, or a required key is still unset after loading it, remind the user to add the nee

• NoteMentions a .env fileSKILL.md:28

  if [ -f /home/ubuntu/RL/.env ]; then

• NoteMentions a .env fileSKILL.md:30

  . /home/ubuntu/RL/.env

• NoteMentions a .env fileSKILL.md:33

  echo "Missing /home/ubuntu/RL/.env; add required keys such as WANDB_API_KEY or HF_TOKEN before authenticated runs."

• NoteMentions a .env fileSKILL.md:42

  if [ -f /home/ubuntu/RL/.env ]; then

• NoteMentions a .env fileSKILL.md:44

  . /home/ubuntu/RL/.env

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NVIDIA/skills at commit dfdd080, republished under its Apache-2.0 licence (© NVIDIA). 472 words, ~1,315 tokens.

name

nemo-rl-brev-etiquette

description

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.

license

Apache-2.0

when_to_use

Running on a Brev instance; launching nemo-rl-auto-research campaigns or long jobs; managing large logs, checkpoints, caches, datasets, Ray temp files, W&B…

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

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

© NVIDIA, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files in skills/nemo-rl-brev-etiquette of NVIDIA/skills.

• SKILL.md
• BENCHMARK.md
• evals/evals.json
• skill-card.md
• skill.oms.sig

Open the folder on GitHubat commit dfdd080