Menu
Sequence cleaning steps in a chain — trim/case/replace, null handling, deduplication, and type casting — in the right order. Use when raw ingested data needs cleaning before joins or aggregation.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Place Assert and Schema Validation nodes as gates that halt a chain when data is wrong, so bad data never reaches the output. Use when the pipeline must guarantee correctness before exporting or loading downstream.
Choose the right sink format, compression, and destination for a chain's output, and decide between exporting a file vs creating a table. Use at the end of a pipeline when deciding how to persist results.
Best practices for loading files into a chain — single file, folder globs, type detection, and union of many files. Use when the pipeline starts from CSV/Parquet/JSON/Excel files or a folder of files.
Decide between Merge (stack rows / UNION) and Join (match on a key) when a chain has multiple inputs, and set keys and join type correctly. Use when a pipeline combines two or more upstream tables.
Descompone un objetivo de procesamiento en un flujo de nodos Chains (source → transform → sink). Use when the user wants to build a data pipeline / chain, or describes an end-to-end "load X, clean it, summarize, export" goal.
Framework de razonamiento para convertir resultados de análisis en una narrativa visual clara y convincente
| name | Limpieza en Pipeline |
| description | Sequence cleaning steps in a chain — trim/case/replace, null handling, deduplication, and type casting — in the right order. Use when raw ingested data needs cleaning before joins or aggregation. |
| keywords | limpieza, limpiar, clean, trim, nulos, null, duplicados, dedup, cast, tipos, normalizar, estandarizar, formato, reemplazar |
| next | data-quality-gates |
| scope | engineering |
Activa después de la ingesta, antes de joins/agregaciones. El orden importa: limpiar texto antes de deduplicar, tipar antes de calcular.
TRY_CAST (el nodo ya lo hace): valores inválidos → NULL en vez de romper.amount > 100 sobre texto no compara como número.Tras limpiar, pon una puerta de calidad ([[data-quality-gates]]) antes de seguir con joins o agregaciones.