Acerca de
This skill empowers users to create sophisticated ETL (Extract, Transform, Load) pipelines for unstructured data by leveraging the DocETL framework and Claude Haiku models. It facilitates a robust iterative workflow—write, run, inspect, and iterate—enabling data analysts to collect information, perform schema-driven extraction, resolve entities, and aggregate complex datasets. With built-in support for prompt optimization, validation rules, and automated visualization, it streamlines the journey from raw text to structured, actionable insights.
