Guided workflow for SQL data analysis using db_tools
npx skills add https://github.com/Datus-ai/Datus-agent --skill sql-analysisCopy and paste this command into Claude Code to install the skill
Generate MetricFlow metrics from natural language business descriptions
Generate MetricFlow semantic models from database tables with validation and Knowledge Base publishing
Create database tables from SQL (CTAS) or natural language descriptions
Activate when the gen_job agent detects that the source and target databases differ. Covers cross-database transfer lifecycle - type mapping via adapter Mixin hints, DDL generation, data transfer via transfer_query_result, and lightweight reconciliation.
Execution guide for Airflow scheduled jobs — troubleshooting, updating, conn_id conventions, and cron references
Scheduler validator driven by ValidationHook — read-only static verification of scheduled jobs (schedule correctness, configuration, runtime context already collected by deterministic hook). Does not trigger test runs.
| name | sql-analysis |
| description | Guided workflow for SQL data analysis using db_tools |
| tags | ["sql","analysis","workflow"] |
| version | 1.0.0 |
This skill guides you through a structured data analysis workflow using database tools.
First, understand the database schema:
Use db_tools.list_tables() to see available tables
Use db_tools.describe_table(table_name) for each relevant table
Explore the data with sample queries:
Use db_tools.execute_sql("SELECT * FROM {table} LIMIT 10")
Based on the user's question, construct and execute the analysis query.
Analyze the results and provide insights.