Edit code → commit → run benchmark → measure metric → keep improvement or revert → repeat forever. Works for any optimization target: LLM training loss, test speed, bundle size, build time, Lighthouse scores, and more. Inspired by Karpathy's autoresearch, pi-autoresearch, and litesearch. This plugin provides two skills that work together. Autoresearch is the core engine (works for any metric), and
Add this skill
npx mdskills install proyecto26/autoresearch-mlComprehensive autonomous ML training loop with excellent GPU support and detailed experiment tracking
No forks yet. Be the first to fork and customize this skill.
Visual fork tree and fork list coming soon.