Make a small, reviewable NeMo Relay bug fix without widening scope unnecessarily
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add NVIDIA/NeMo-Relay --skill small-fix --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Small Fix?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/nvidia-small-fix)More formats (shields.io, HTML) on the badges page.
---
name: small-fix
description: Make a small, reviewable NeMo Relay bug fix without widening scope unnecessarily
author: NVIDIA Corporation and Affiliates
license: Apache-2.0
---
# Contribute A Small Fix
## Companion Guidance
Use `karpathy-guidelines` alongside this skill for implementation or review
work. Keep changes scoped, surface assumptions, and define focused validation
before editing.
Use this skill for narrowly scoped bug fixes or behavior corrections.
## Rules
- Reproduce or identify the failing behavior first
- Keep the change as small as possible
- Avoid opportunistic refactors unless they are required to fix the bug safely
- Add or update the smallest meaningful test that proves the fix
## Checklist
- [ ] Scope of the fix is explicit
- [ ] Affected language surfaces are understood
- [ ] A regression test or focused validation path exists
- [ ] Docs updated if public behavior changed
- [ ] PR notes can explain what failed before and why the fix is safe
## References
- `CONTRIBUTING.md`
- `validate-change`
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
