Menu
Trend analysis over time — growth rates, seasonality, anomalies, and period comparisons. Use when the question involves how a metric evolves over a date/time dimension.
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
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.
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.
| name | Análisis de Series Temporales |
| description | Trend analysis over time — growth rates, seasonality, anomalies, and period comparisons. Use when the question involves how a metric evolves over a date/time dimension. |
| keywords | trend, time, growth, decline, seasonal, temporal, date, historical, tendencia, tiempo, evolución, crecimiento, mensual, semanal, diario, anual, período, histórico, mes, semana, año |
| next | data-storytelling |
Activa cuando el análisis involucra una dimensión temporal: evolución de métricas, tendencias, comparación de períodos y anomalías temporales.
Antes de tratar algo como "serie temporal", verifica que de verdad lo sea: necesitas varios puntos en el tiempo. Con 2–3 períodos no hay tendencia que mostrar — es una comparación (ver paso de visualización).
describe_table y verifica tipo DATE/TIMESTAMP. Si es string, conviértela con STRPTIME o CAST.DATE_TRUNC('<gran>', fecha) agrupando la métrica clave, ordenada por período.line / area (la evolución real).split_by si comparas categorías). Una línea de 2 puntos engaña.LAG() para % período a período:
SELECT periodo, metrica,
ROUND((metrica - LAG(metrica) OVER (ORDER BY periodo))
/ NULLIF(LAG(metrica) OVER (ORDER BY periodo), 0) * 100, 1) AS pct_cambio
FROM serie
AVG(), STDDEV()).final_answer: tendencia principal, tasa de crecimiento/caída, períodos anómalos.DATE_TRUNC('month', col) — truncar a inicio de mes · DATE_PART('week', col) — número de semanaDATEDIFF('day', ini, fin) — diferencia en díasGENERATE_SERIES para rellenar fechas faltantes (evita líneas que "saltan" períodos vacíos).