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
El comando exacto puede variar según el repositorio. Consulta el README en GitHub.
Para el autor de la skill
Pega en el README de tu repo
Muestra que tu skill está catalogada en Skillteca, genera backlink y tráfico rastreable.
[](https://www.skillteca.com.br/skills/capture-learning?utm_source=badge&utm_medium=readme&utm_campaign=badge)
Recibe nuevas skills de Design e Frontend todos los lunes
Un email corto con solo las skills nuevas de Design e Frontend. 4 minutos de lectura, sin spam, te das de baja con un clic.
Confirmas tu email en el primer envío. Sin spam. Te das de baja con un clic.
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.]
