safe-debug
#6 in Debugging & ProfilingRigor Debug / Rigor Audit skill for deep learning research work.
Overview
Rigor Debug / Rigor Audit skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching, with debug fixes clearly separated from research contributions. Do not use for broad refactoring, speculative adaptation, automatic exploratory patching, or general repository familiarization.From the project's GitHub description
Our editorial assessment of safe-debug is still in review. Facts below come from the repository and our catalogue.
Technical specifications
Each attribute is labelled with where it came from.
Install
A skill is a set of instructions your agent loads. Install it into the agent you use; there is nothing to host.
$ npx skills add https://github.com/lllllllama/RigorPilot-Skills --skill safe-debug- Listing
- skills.shInstall counts come from skills.sh.
Alternatives
Also in Debugging & Profiling
Same category, not necessarily equivalent.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
web-perf
Audit, diagnose, or optimize website loading and interaction performance, Core Web Vitals, and Lighthouse performance scores.
animation-performance
Keep web animations inside the frame budget — animate composite-only properties, keep motion off the main thread when the page is busy, and find the cause when an animation drops frames.
Reviews
Community ratings are kept separate from Beav Scout rankings.
No reviews yet. Community reviews and comments are opening soon; you'll be able to rate safe-debug once signed in.