Practical workflows for assessing and improving product-specific LLM evaluations.
1.7KStars120Forks
Repository last pushed
Explore skills
Original workflows for websites, images, presentations, and everything in motion.
Audit an LLM evaluation pipeline for missing error analysis, unvalidated judges, data leakage and stale checks.
1.7KStars120Forks
Repository last pushed
A small library, made with care. More skills are on the way.