Nemo Rl Docs

From the author

Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes, performance tuning, or any task that does not involve writing or updating documentation.

— the description by NVIDIA

AutoGineer summary

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

This skill provides the established guidelines for maintaining documentation within the NeMo-RL project. It outlines the requirements for updating the central index file when new documentation is added and specifies the use of Google-style docstrings to ensure compatibility with Sphinx documentation generation.

What it does

Defines the structure for updating the project index file.
Mandates Google-style docstrings for classes and functions.
Provides guidance on where to place new documentation files.
Distinguishes between appropriate use of docstrings versus internal code comments.

When to use it

When adding or updating project documentation.
When creating new markdown files within the documentation directory.
When reviewing or writing docstrings for public interfaces.
When determining the correct location for new feature documentation.

Advantages

Ensures consistent documentation structure across the project.
Facilitates automated documentation generation via Sphinx.
Improves readability and maintainability of public-facing code interfaces.

Usage examples

“How should I format my function docstrings?”: The agent will advise using Google-style docstrings to ensure they are correctly parsed by Sphinx.
“Where do I register a new documentation file?”: The agent will instruct you to update the docs/index.md file and place the new file in the appropriate section.

Install

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/nvidia/nemo-rl-docs/download

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

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

Documentation by NVIDIA

Documentation Conventions

Keep docs/index.md Up to Date

When a new markdown doc is added under docs/**/*.md or a markdown file is renamed, ensure that @docs/index.md is updated and the document appears in the most appropriate section.

Docstring Format

Use Google style docstrings for classes and functions. These are parseable by Sphinx.

For interfaces that may be used outside a file, prefer docstrings over comments. Comments should be reserved for code within a function or interfaces local to a file.

Document New Features

When a new feature is added, update or create documentation in the docs/ directory that most closely matches the feature. Look at existing docs to find the best fit — if none exists, create a new doc and add it to @docs/index.md.

Documentation changes are not required for bug fixes or CI-related changes.

Files

ATTRIBUTION.mdAdded by AutoGineer823 B
BENCHMARK.md4.1 KiB
LICENSELicence file added by AutoGineer11.2 KiB
SKILL.md1.4 KiB
evals/evals.json2.4 KiB
skill-card.md3.6 KiB
skill.oms.sig4.5 KiB

skill-card.md

Description:

Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format.

This skill is ready for commercial/non-commercial use.

Owner

NVIDIA

License/Terms of Use:

Apache 2.0

Use Case:

Developers and engineers adding or updating documentation in the NeMo-RL project, including maintaining docs/index.md and writing Google-style docstrings.

Deployment Geography for Use:

Global

Known Risks and Mitigations:

Risk: Review before execution as proposals could introduce incorrect or misleading guidance into skills. Mitigation: Review and scan skill before deployment.

Reference(s):

Google Python Style Guide — Docstrings
NeMo RL Documentation

Skill Output:

Output Type(s): [Configuration instructions, Analysis] Output Format: [Markdown] Output Parameters: [1D] Other Properties Related to Output: [None]

Evaluation Agents Used:

Claude Code (claude-code)
Codex (codex)

Evaluation Tasks:

Evaluated against 5 internal evaluation tasks (3 positive skill-activation, 2 negative activation) with 2 attempts per task.

Evaluation 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: Checks for unsafe operations, secret leakage, and unauthorized access.
skill_execution: Verifies that the agent loaded the expected skill and workflow.
skill_efficiency: Checks routing quality, decoy avoidance, and redundant tool usage.
accuracy: Grades final-answer correctness against the reference answer.
goal_accuracy: Checks whether the overall user task completed successfully.
behavior_check: Verifies expected behavior steps, including safety expectations.
token_efficiency: Compares token usage with and without the skill.

Evaluation Results:

Dimension	Num	`claude-code`	`codex`
Security	8	100% (+0%)	100% (+0%)
Correctness	8	91% (+7%)	83% (+11%)
Discoverability	8	99% (-1%)	90% (+5%)
Effectiveness	8	81% (+8%)	80% (+18%)
Efficiency	8	85% (-0%)	79% (+3%)

Skill Version(s):

69adf2b2e (source: git SHA, committed 2026-06-01)

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal team to ensure this skill meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

(For Release on NVIDIA Platforms Only) Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here.

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.

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.

Doc Coauthoring
AnthropicOfficial
Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Documents and contentClaude CodeClaude appsOpenAI Codex+14 more
Link-onlyGitHub stars of the source repository188.6k
Markdown Mermaid Writing
K-Dense· Community
Generates scientific Markdown documentation and Mermaid structural diagrams for workflows, schemas, and relationships.
Documents and contentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0Low riskGitHub stars of the source repository56.4k
JSON Canvas
Steph Ango (Obsidian)· Community
Create and edit JSON Canvas files for visual organization and mapping.
Documents and contentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository51k
Obsidian Markdown
Steph Ango (Obsidian)· Community
Generate and format Obsidian-specific Markdown syntax for notes, links, and embeds.
Documents and contentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository51k
Faq
AnthropicOfficial
Generate a team-specific FAQ document to address recurring questions about AI tool usage and project conventions.
Documents and contentClaude CodeClaude appsOpenAI Codex+14 more
Apache-2.0GitHub stars of the source repository46.3k
Hads
Seth Hobson· Community
A standardized Markdown format for technical documentation optimized for both human readability and AI model consumption.
Documents and contentClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k

Download ZIP

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

From the author