Review Nvbench Agent Skill
Use this skill when the user invokes /review-nvbench to review an NVBench pull request, PR branch, commit range, or diff. Supports context, feedback, and adversarial modes.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/NVIDIA/nvbench --skill review-nvbenchThe instruction itself
4 sections, as written by the authorReview NVBench Pull Request
Read AGENTS.md and docs/pr_review.md before acting.
Use one of these modes:
context: Gather PR context and explain the change without review findings.feedback: Produce normal review findings after the human reviewer has inspected the PR.adversarial: Challenge assumptions, design direction, compatibility risks, and hidden failure modes after the PR context is understood.
If no mode is provided, default to context.
Context Mode
Run or inspect ci/util/pr_review_context.sh when reviewing a checked-out PR branch. If the user provided a PR number, pass --pr <number>. If the user provided an issue number, pass --issue <number>.
Summarize:
- The linked issue or PR context.
- The problem the PR is trying to solve.
- How the PR attempts to solve it.
- The important changed files and a sensible human review order.
- Any missing context, such as no discoverable linked issue.
Do not produce review findings in context mode.
Feedback Mode
Before producing findings, make sure the context pass has happened. If it has not, gather and summarize the PR context first.
Review for correctness, benchmark validity, performance, API compatibility, build and packaging impact, and consistency with existing code. Let the changed files determine which risks matter, while paying attention to relevant NVBench contracts such as CUDA stream ordering, timing boundaries, cold/batch/CPU-only measurement behavior, manual timer semantics, axis generation, output schemas, optional CUPTI/NVML behavior, CMake options, Python bindings, and test coverage.
Report findings first, ordered by severity, with file and line references. Do not post comments to GitHub; the human reviewer decides which findings to use.
Adversarial Mode
Before producing adversarial feedback, make sure the PR intent and implementation strategy are understood.
Focus on whether the approach is sound:
- Hidden assumptions that could fail.
- Simpler or safer alternative designs.
- Compatibility, layering, maintenance, or rollout risks.
- Cases where the implementation solves the local issue but weakens a broader NVBench contract.
Keep this distinct from normal feedback. It is acceptable for adversarial mode to produce questions or risks rather than concrete blocking findings.
Other skills for the same job
different authors, same section of the catalogue
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
Execute git commit with conventional commit message analysis, intelligent staging, and message generation. Use when user asks to commit changes, create a git commit, or mentions "/commit". Supports: (1) Auto-detecting type and scope from changes, (2) Generating conventional commit messages from diff, (3) Interactive commit with optional type/scope/description overrides, (4) Intelligent file staging for logical grouping
Comprehensive GitHub code review with AI-powered swarm coordination
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
Use this skill to review code. It supports both local changes (staged or working tree) and remote Pull Requests (by ID or URL). It focuses on correctness, maintainability, and adherence to project standards.
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation.
Create high-quality git commits: review/stage intended changes, split into logical commits, and write clear commit messages (including Conventional Commits). Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.
How to use it
Take nvidia/review-nvbench from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.