NVIDIA-NeMo/RL

cicd

CI/CD reference for NeMo-RL. Covers GitHub Actions pipeline structure, CI triggering via /ok to test, and CI failure investigation.

review-pr-team

Agent-team-based parallel code review for NVIDIA-NeMo/RL pull requests. Spawns specialized agents (RL expert, submodule experts, bug finder, design reviewer, test agent, devil's advocate, comment reviewer) that coordinate via shared task list and direct…

review-pr-team-verify-followup

After a published PR review, check the author's fixes, scan the new commits for major issues, close fixed threads, stage follow-ups

build-and-dependency

Build and dependency management for NeMo-RL. Covers Docker image building and running, uv usage, venv setup, and adding dependencies.

config-conventions

Configuration conventions for NeMo-RL. YAML is the single source of truth for defaults. Covers BaseModel/TypedDict usage, dataclass for internal classes, exemplar YAML updates, and forbidden default patterns.

contributing

Contribution conventions for NeMo-RL. Covers PR title format, commit sign-off, and CI triggering.

copyright

NVIDIA copyright header requirements for NeMo-RL. Covers which files need headers and the exact header text.

cp-to-main

Manually cherry-pick a merged NVIDIA-NeMo/RL PR from a release branch (r0.X.0) back onto main when the auto cherry-pick bot failed. Stops at conflicts for the user to resolve, then verifies, pushes, opens a cp PR, copies CI labels and posts /ok to test.

cp-to-release

Manually cherry-pick a merged NVIDIA-NeMo/RL PR onto the current release branch (r0.X.0) and open a cp PR with matching CI labels and /ok to test.

error-handling

Error handling guidelines for NeMo-RL. Covers exception specificity, minimal try bodies, and else blocks.

linting-and-formatting

Code style guidelines for NeMo-RL (Python and shell). Covers naming, indentation, comments, docstrings, reflection avoidance, and uv usage.

pr-html-concise-public

One-page-per-question HTML explainer for a PR — classify the PR first: a new feature owes a page comparing it with the existing way, a fix owes a page showing the failure and the fix, and a PR with both owes two cross-linked pages. Leads with a diagram, plain…

removing-outdated-config

How to remove or rename a config key in NeMo-RL so stale configs fail at startup with the migration to apply, instead of failing deep in a run or being silently ignored.

review-pr

Interactive code review for NVIDIA-NeMo/RL pull requests. Checks out PR locally, reads existing comments, applies coding guidelines from skills, previews findings, and posts review comments. Also supports reviewing the current branch locally.

review-pr-team-with-html

/review-pr-team plus a public /pr-html-concise-public explainer, built before staging

testing

Testing conventions for NeMo-RL. Covers Ray actor coverage pragmas, nightly test requirements, and recipe naming rules.

launch-nemo-rl

Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.

nemo-rl-auto-research

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and…