Surface prior learnings relevant to the current task. Use before starting any non-trivial work — new experiment, new feature, new submission strategy, debugging a pattern — to check if we've been here before. Also use when the user says "what have we learned about X", "any past notes on Y", "recall", or "check learnings".
1 email curto, só com as skills novas de Produtividade. 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
Recalling Prior Learnings
Surfaces the most relevant learnings from .learnings/ for the task at hand. This is the compound-interest mechanism — every session should call it before committing to an approach.
When to invoke proactively
Before:
Picking a modeling approach ("LightGBM vs CatBoost for tabular").
Designing a CV split strategy.
Writing submission glue code for a new competition.
Starting an agent's main decision loop.
Deciding a hyperparameter range.
Writing code t
[Description truncada. Veja o README completo no GitHub.]
