Description
safe-debug is an agent skill from the rigorpilot-skills collection for diagnosing failures in deep learning research code. It is the Rigor Debug and Rigor Audit skill, and its installed name is kept for compatibility. It is used when a user pastes a traceback, a terminal error, a CUDA out-of-memory message, a checkpoint loading failure, a tensor shape mismatch or another concrete training or inference failure. The skill aims for conservative diagnosis: it narrows the root cause, explains the likely local fault and proposes minimal patch suggestions before any code is changed. It is built to keep a human in the loop, so mutation of the code or the environment needs explicit approval, and it does not block the model from finding the real cause on its own. The skill points the assistant to the shared operating principles for the research repository before it works. It is useful for a researcher who wants a fast, cautious explanation of a failure and a small, reviewable fix rather than a sweeping rewrite. It should not be used for planning new experiments or for broad refactoring. The skill passes Gen Agent Trust Hub, Socket and Snyk on skills.sh, and it has about 319,000 installs. Install it with npx skills add https://github.com/lllllllama/rigorpilot-skills --skill safe-debug.…
Highlights
- Diagnoses tracebacks, CUDA out-of-memory and checkpoint load errors
- Narrows the root cause before any change
- Proposes minimal patch suggestions
- Requires explicit human approval before mutation
Ratings & Reviews
No ratings yet
Be the first to rate safe-debug.
People also visit
safe-debug FAQ
What errors does it handle?
A pasted traceback, a terminal error, a CUDA out-of-memory error, a checkpoint load failure, a shape mismatch and similar training or inference failures.
Does it change my code automatically?
No. It diagnoses and suggests minimal patches, and it requires explicit human approval before any change.
When should I not use it?
For planning experiments or broad refactoring, since the skill is for diagnosing a concrete failure.
How do I install it?
Run npx skills add https://github.com/lllllllama/rigorpilot-skills --skill safe-debug.
Which security audits does it have?
On skills.sh, Gen Agent Trust Hub, Socket and Snyk all pass.
What are the best safe-debug alternatives?
Popular alternatives to safe-debug include debug, ai-research-explore and analyze-project. See all safe-debug alternatives