CData Connect AI — HubSpot Skill

⚠️ Prerequisites — load these first

• connect-ai-base skill

Before proceeding, locate and read the connect-ai-base skill. If it is not available in the current environment (not loaded, not enabled, or not installed), stop immediately. Do not proceed with the task. Tell the user that the connect-ai-base skill is required and ask them to install and enable it before continuing.

This skill provides HubSpot-specific guidance for querying HubSpot data through CData Connect AI. It composes on top of the connect-ai-base skill, which handles the discovery workflow, error recovery, SQL dialect, and three-part query naming convention.

Precedence

This skill replaces getInstructions for the HubSpot driver. Do not call getInstructions for HubSpot — the guidance it provides is already incorporated here and in the per-surface references. Proceed directly to getSchemas (to identify the surface — see below) and then schema discovery (getTables / getColumns) after identifying the HubSpot connection via getCatalogs.

HubSpot exposes three schemas

A HubSpot connection presents one of three completely different surfaces, determined by the CData Schema connection property. The surface changes the entire object model — which tables exist, how primary keys are named, how enum values are cased, how relationships are traversed, and which stored procedures are available. The surface cannot be inferred from the connection name, so the first move on any HubSpot connection is to identify it with getSchemas.

Always run getSchemas as the FIRST tool call against any HubSpot connection — before any queryData, getTables, or getColumns call. Do not infer the surface from the connection name. A name may carry a _V3, _V4, or _Legacy hint, but this is not a reliable surface indicator and may be misleading. The schema returned by getSchemas is the only authoritative signal.