feat: Auto research skill

[vinhngx]

What does this PR do ?

This PR adds an auto research skill that guides agents on how to do a prolonged research session with Nemo-RL and Nemo-gym. It sets some operating guidelines on how to form and test hypotheses, how to organize git branches, how to monitor and report progress, and how to explicitly check for the stopping conditions of the campaign.

Issues

N/A

Usage

You can prompt Codex, such as:

Use the @skill/auto_research skill and train the Qwen-3-VL-2B-instruct model to high accuracy in the Nemo-gym circle click environment. Time budget: 5h

For this skill to be effective, Codex should have sufficient knowledge of the local operating environment (e.g. Slurm or local machine). A prerequisite to using the auto research skill is therefore, for the agent to be able to automatically run a baseline workload on the given environment.

[copy-pr-bot]

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

[terrykong]

/claude review

[terrykong]

Review: PR #2419 — feat: Auto research skill

Nice work — this skill provides a well-structured framework for running iterative RL experiments with git as the experiment journal. The exploration-ideas guide and git-workflow reference are thorough and practical. The safety guardrails in git-workflow.md (no stash/reset/overwrite without consent) are particularly good.

A few suggestions to align with existing repo conventions and improve consistency:

Directory naming mismatch

All other skill directories use hyphens (build-and-dependency, config-conventions, launch-nemo-rl, etc.), but this one uses an underscore (auto_research). The frontmatter name field is auto-research (with hyphen), creating an inconsistency. Consider renaming the directory to auto-research/ to match the convention.

Nemo-gym coverage

The PR description mentions guiding agents on research with "Nemo-RL and Nemo-gym", but the SKILL.md workflow (step 3) only references NeMo-RL paths (examples/run_grpo.py, nemo_rl/models/, etc.). The Nemo-gym entrypoints (examples/nemo_gym/) are not mentioned. Consider either adding Nemo-gym paths to the workflow or adjusting the PR description to match the actual scope.

See inline comments for additional suggestions.

Generated by Claude Code

[vinhngx]

Thanks, @terrykong, for the prompt review. Fixed the reported issues and tightened all 3 skills. Add best practices and gotchas observed with Codex, but could happen with other agents.

[terrykong]

/ok to test a8b8513

[terrykong]

/ok to test 54c71ec

[yuki-97]

/ok to test 9880d5e

[chtruong814]

/ok to test 39de685