Safe Debug

When you paste a CUDA OOM or NaN loss into chat and want a diagnosis before Claude starts changing code, this is the skill to reach for. It enforces a diagnose-first flow: you get a root cause analysis, a minimal patch plan in debug_outputs, and an explicit approval gate before any mutation happens. The boundary discipline is the point here. It won't refactor for readability or speculatively adapt your training loop. It separates debug fixes from research contributions and will tell you when a fix changes experimental comparability. Best for deep learning research where you need conservative debugging that respects the integrity of your setup.

skills.sh installs: 226
GitHub stars: 289
last updated: Jun 3, 2026

View on GitHub

Install

$ npx -y skills add lllllllama/ai-paper-reproduction-skill --skill safe-debug --agent claude-code

Installs into .claude/skills of the current project.

Files

safe-debug

Use this as the Rigor Debug / Rigor Audit skill. The installed slug remains safe-debug for compatibility.

Use the shared operating principles in ../ai-research-reproduction/references/agent-operating-principles.md; this skill should guide conservative diagnosis without blocking the model from finding the local root cause.

When to apply

The user provides a traceback, terminal error, or concrete training or inference failure symptom.
The user wants diagnosis, root-cause narrowing, and minimal patch suggestions before code is changed.
The user wants a safe debug flow with explicit human approval before mutation.