safe-debug
This skill is designed for debugging and auditing deep learning research work. When users encounter issues like tracebacks, terminal errors, CUDA OOM, checkpoint load failures, shape mismatches, or training failures, this Skill provides conservative diagnoses and minimal patch suggestions. It clearly separates debugging fixes from research contributions, helping users quickly identify and resolve problems while ensuring the rigor and efficiency of their research process.
npx skills add https://github.com/lllllllama/rigorpilot-skills --skill safe-debugBefore / After Comparison
1 组Without this skill, developers manually spent significant time analyzing stack traces, logs, and code to pinpoint root causes of complex errors in deep learning research. This was inefficient and risked introducing new issues or conflating research outcomes during debugging, leading to project delays.
This Skill quickly diagnoses deep learning errors, provides precise and minimal patch suggestions, and clearly separates debugging from research contributions. It significantly reduces troubleshooting time, lowers the risk of introducing new errors, and ensures the purity of research code, greatly enhancing developer efficiency and research quality.
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
../../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.
When not to apply
- When the user wants a broad repository walkthrough without an active failure.
- When the task is speculative experimentation or code adaptation.
- When the user is asking for a large refactor or readability rewrite.
Clear boundaries
- Diagnose first.
- Do not modify repository code by default.
- If a patch is needed, propose the smallest fix and require explicit approval first.
- Escalate savepoint or branch creation before medium-risk or high-risk changes.
- A debug fix is not automatically a research contribution; if it changes experiment meaning or comparability, say so explicitly.
Output expectations
debug_outputs/DIAGNOSIS.mddebug_outputs/PATCH_PLAN.mddebug_outputs/status.json
Notes
Use references/debug-policy.md, ../../references/research-rigor-principles.md, and the shared references/research-pitfall-checklist.md.
User Reviews (0)
Write a Review
No reviews yet
Statistics
User Rating
Rate this Skill