القائمة
Detect nulls, duplicates, outliers, and integrity issues in a table, prioritized by downstream impact. Use when auditing data before a business analysis or when the user suspects problems in the data.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
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 | Calidad de Datos |
| description | Detect nulls, duplicates, outliers, and integrity issues in a table, prioritized by downstream impact. Use when auditing data before a business analysis or when the user suspects problems in the data. |
| keywords | quality, null, duplicate, outlier, validate, integrity, calidad, nulos, duplicados, limpieza, limpiar, inconsistente, anomalía, faltantes, errores, validar |
| next | eda-initial |
Activa cuando el objetivo es auditar la integridad del dataset antes de un análisis de negocio, o cuando el usuario sospecha de problemas en los datos.
profile_data en EDA muestra indicadores sospechosos"Calidad" no es absoluta — depende del uso. Antes de correr checks, pregúntate qué rompería el análisis que viene, y prioriza por ahí:
Las queries de abajo son herramientas; elige y ordena los checks por ese impacto, no las corras todas mecánicamente.
profile_data para visión general de nulls, únicos y distribucionesSELECT column_name,
COUNT(*) - COUNT(column_name) AS nulls,
ROUND((COUNT(*) - COUNT(column_name)) * 100.0 / COUNT(*), 1) AS pct_null
FROM tabla UNPIVOT ...
-- O más simple:
SELECT COUNT(*) AS total,
COUNT(col_a) AS col_a_ok, COUNT(*) - COUNT(col_a) AS col_a_null
FROM tabla
SELECT col_clave1, col_clave2, COUNT(*) AS duplicados
FROM tabla
GROUP BY col_clave1, col_clave2
HAVING COUNT(*) > 1
ORDER BY duplicados DESC
LIMIT 20
WITH stats AS (
SELECT PERCENTILE_CONT(0.25) WITHIN GROUP (ORDER BY metrica) AS q1,
PERCENTILE_CONT(0.75) WITHIN GROUP (ORDER BY metrica) AS q3
FROM tabla
)
SELECT * FROM tabla, stats
WHERE metrica < q1 - 1.5*(q3-q1) OR metrica > q3 + 1.5*(q3-q1)
LIMIT 50
display_chart (bar) con distribución de nulls por columnafinal_answer con: resumen de issues críticos, tabla de nulls/duplicados, recomendaciones de limpieza