Documentation
README
Agentic Kaggle Skill
Operating Loop
Treat every competition as a validation problem first and a modeling problem second. The default target platform is Kaggle, so prefer Kaggle-native notebooks/scripts, datasets, model artifacts, competition submissions, and score receipts. For code competitions, assume the final notebook/kernel will be rerun by Kaggle against hidden data unless the competition docs prove otherwise.
This is the opening of the README. Read the full README on GitHub.