Show HN: A skill to audit your dbt project for what an AI agent will get wrong

Category: devtools

Tags: dbt, ai-agent, data-audit, claude-code, data-quality

Score: 7.3/10 (Innovation: 7, Technical: 7, Documentation: 8, Utility: 7)

A Claude Code skill that audits dbt projects for issues that would cause AI agents to fail when querying the data, such as naming inconsistencies, broken joins, and misleading model descriptions. It combines static analysis of SQL and YAML with AI-powered pattern recognition to produce a prioritized remediation plan, making it a novel tool for teams adopting AI copilots in analytics workflows.

Target audience: data engineers, analytics engineers, data platform teams

Repository: https://github.com/GetCassis/dbt-agent-readiness · Python · MIT · 4 stars

View on Hacker News