semantic-layer-audit

Discover and document BigQuery datasets, tables, views, APIs, and Secret Manager credentials.

10|1|Updated Feb 5, 2026
One-click install
npx skills add https://github.com/pbc-os/agent-skills-public --skill semantic-layer-audit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: semantic-layer-audit
Source: https://github.com/pbc-os/agent-skills-public/tree/main/skills/tier-1-foundation/semantic-layer-audit
Command: npx skills add https://github.com/pbc-os/agent-skills-public --skill semantic-layer-audit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill ensures your AI agent always knows what data is available by maintaining a living data catalog, preventing forgotten datasets, undocumented integrations, and inaccurate data source assumptions.

Core Features & Use Cases

  • Automated Discovery: Scans GCP BigQuery, Secret Manager, APIs, and Service Accounts to inventory data assets.
  • Structured Auditing: Provides templates and guidance for documenting tables, views, and data source relationships.
  • Use Case: An AI agent needs to analyze sales data. This Skill helps ensure the agent knows about the sales_data BigQuery dataset, its tables like orders and daily_summary, and provides documentation on how to use them correctly.

Quick Start

Run the infrastructure audit script to discover your data assets.

Frequently Asked Questions about semantic-layer-audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate discovery of BigQuery datasets and GCP data assets for a semantic layer?

To maintain a semantic data catalog, you must inventory BigQuery datasets, GCP APIs, and Secret Manager credentials. This structured auditing provides templates for documenting tables and views, ensuring your AI agent knows exactly what data is available.

What is a semantic data catalog and why do I need it for AI agent data awareness?

A semantic data catalog is a living inventory of data assets that documents tables, views, and source relationships. You need it to prevent forgotten datasets and undocumented integrations, ensuring your AI agent maintains operational integrity and accurate data awareness.

Does this data catalog audit cover Secret Manager credentials and GCP service accounts?

Yes, the data catalog audit covers Secret Manager credentials and service accounts. It scans these alongside BigQuery datasets and GCP APIs to fully inventory your data assets and facilitate operational integrity for your AI agent.

How do I document BigQuery tables and views for my AI agent to use correctly?

You can document BigQuery tables and views using structured auditing templates. This guides the documentation of tables, views, and data source relationships, ensuring your AI agent knows about specific datasets and how to use them correctly.

What is the best way to maintain a data catalog and prevent undocumented GCP integrations?

The best way to maintain a data catalog and prevent undocumented GCP integrations is automating the discovery of data assets. Running regular infrastructure audits scans BigQuery and Secret Manager to maintain a living semantic data catalog.