Example Genie Code skills, custom instructions, and MCP setup for enforcing enterprise data engineering standards across Databricks development.
This repository also configures its own agents. See what genie-code-skills-demo tells them →
databricks-solutions/genie-code-skills-demo
Skill Claude CodeCodex
Identify and label PII columns in SDP pipeline tables. Use when creating or modifying tables that contain customer or personal data. Includes detection patterns, table property labeling, column annotation, and masking guidance. Always generate SDP pipelines using SQL, not Python.
databricks-solutions/genie-code-skills-demo
Skill Claude CodeCodex
Apply basic SDP pipeline best practices for table naming, comments, and table properties. Use when creating or modifying tables in Spark Declarative Pipelines. Always generate SDP pipelines using SQL, not Python.
databricks-solutions/genie-code-skills-demo
Skill Claude CodeCodex
Build sentiment-analysis datasets in SDP pipelines using built-in Databricks AI functions (aianalyzesentiment, aiclassify, aiextract, aisummarize, aiquery). Use when creating or modifying tables that derive sentiment, topics, or entities from free-form text such as customer reviews, support tickets, social posts, or…
databricks-solutions/genie-code-skills-demo
Skill Claude CodeCodex
Enforce table and column documentation standards across all tables. Use for every table you create or modify. Covers COMMENT clauses, TBLPROPERTIES, column descriptions, PII labeling at the table level, and Unity Catalog tags. This is the baseline governance skill -- apply it before any other skill.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: