Skip to content
Back to Skills Index

ELELAND INTELLIGENCE

SKILL 161 OF 500 · github

safe-debug

lllllllama/rigorpilot-skills

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.

310,472installs

Rank #161 of 500 · top 32.2%

Position on the top-500 install curve (log scale) · Data as of 2026-08-24

Security audit

SAFE

The skill is a safe and conservative debugging tool designed for deep learning research. it focuses on error diagnosis and root-cause analysis without performing automatic code modifications or network operations. it strictly enforces human-in-the-loop approval for any proposed fixes.

Audited by Gen Agent Trust Hub · 2026-05-29 · pass

MARKET SIGNALS · SKILL INDEX