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.
A direct command skips the review prompt. Inspect the source before running it.
Profiles data assets to assess quality dimensions and detect anomalies across the six core data quality dimensions.
Overview
This skill performs comprehensive data profiling to assess completeness, accuracy, consistency, validity, timeliness, and uniqueness. It generates statistical profiles, detects anomalies, identifies PII, and provides actionable recommendations for data quality improvement.
PII detection and classification - Sensitive data identification
Input Schema
{"dataSource":{"type":"object","required":true,"properties":{"type":{"type":"string","enum":["table","file","query"],"description":"Type of data source"},"connection":{"type":"object","description":"Connection details (platform, database, schema)"},"identifier":{"type":"string","description":"Table name, file path, or query string"}}},"sampleSize":{"type":"number","description":"Number of rows to sample (null for full scan)","default":10000},"dimensions":{"type":"array","items":{"type":"string","enum":["accuracy","completeness","consistency","validity","timeliness","uniqueness"]},"default":["completeness","validity","uniqueness"],"description":"Quality dimensions to assess"},"previousProfile":{"type":"object","description":"Previous profile for drift detection"},"businessRules":{"type":"array","items":{"column":"string","rule":"string","threshold":"number"},"description":"Custom business rules to validate"},"piiDetection":{"type":"boolean","default":true,"description":"Enable PII detection and classification"}}
Output Schema
{"profile":{"type":"object","properties":{"tableName":"string","rowCount":"number","columnCount":"number","profileTimestamp":"string","columns":{"type":"array","items":{"name":"string","declaredType":"string","inferredType":"string","statistics":{"nullCount":"number","nullPercent":"number","distinctCount":"number","distinctPercent":"number","min":"any","max":"any","mean":"number","median":"number","stddev":"number","histogram":"array"},"patterns":{"mostCommon":"array","detectedFormat":"string","regexPattern":"string"},"qualityScores":{"completeness":"number","validity":"number","uniqueness":"number"}}}}},"anomalies":{"type":"array","items":{"column":"string","type":"outlier|drift|unexpected_null|unexpected_value|format_violation","severity":"high|medium|low","description":"string","examples":"array","recommendation":"string"}},"piiFindings":{"type":"array","items":{"column":"string","piiType":"email|phone|ssn|credit_card|name|address|ip|custom","confidence":"number","sampleCount":"number","recommendation":"string"}},"overallScore":{"type":"number","description":"Weighted quality score (0-100)"},"dimensionScores":{"completeness":"number","accuracy":"number","consistency":"number","validity":"number","timeliness":"number","uniqueness":"number"},"recommendations":{"type":"array","items":{"priority":"high|medium|low","category":"string","description":"string","impact":"string"}},"drift":{"type":"object","description":"Changes compared to previous profile","properties":{"schemaChanges":"array","statisticalDrift":"array","volumeChange":"object"}}}
{"dataSource":{"type":"query","connection":{"platform":"bigquery","project":"my-project"},"identifier":"SELECT * FROM orders WHERE order_date >= '2024-01-01'"},"businessRules":[{"column":"order_total","rule":"positive","threshold":0},{"column":"status","rule":"in_set","values":["pending","completed","cancelled"]},{"column":"customer_id","rule":"not_null","threshold":100}]}