Capture a single learning to .learnings/ when something surprising, painful, or validation-worthy happens during Kaggle work. Use proactively whenever an experiment fails for a non-obvious reason, a submission regresses, you hit a tool/API quirk, or a non-obvious approach is confirmed to work. Also use when the user says "remember this", "save this learning", "log this", or describes a mistake the
Receba novas skills de Design e Frontend toda segunda
1 email curto, só com as skills novas de Design e Frontend. 4 minutos de leitura, sem spam, cancela com 1 clique.
Você confirma o email no primeiro envio. Sem spam. Cancela com 1 clique.
Ler descrição completaRecolher descrição
Capturing a Learning
Claude writes a single self-contained learning file to .learnings/. Each file is a durable memory that future sessions will read via the SessionStart hook and the recall-learnings skill.
When to invoke proactively
Any of:
Submission score regressed and we now know why.
An experiment failed for a non-obvious reason (class imbalance, leak, time budget, CV/LB mismatch).
A Kaggle CLI / MCP / env quirk bit us (auth, rate limit, flag syntax, format gotcha).
A
[Description truncada. Veja o README completo no GitHub.]
