Our HubSpot portal is a mess and we do not know where to start

You cannot prioritize what you have not measured. The audit runs read-only API queries across the marketing side (deliverability, completeness, engagement, lists and workflows) and the sales side (pipeline configuration, deal quality, stale deals, ownership, follow-up), grades each dimension A–F, and prescribes the exact skill to run for every finding.

Fix it with one command

The hubspot-audit skill walks Claude Code through the entire fix — audit, CSV baseline, execution, and verification. Ready-to-run Python scripts included.

/plugin marketplace add tomgranot/hubspot-admin-skills
/plugin install hubspot-admin@hubspot-admin-skills
/hubspot-audit

See the full hubspot-audit skill

Frequently asked questions

Is the audit safe to run on production?

Yes — it is read-only: searches and counts, no writes. It produces a markdown report and an ordered cleanup prescription.

How long does a HubSpot portal audit take?

The scripted audit typically runs in minutes even on six-figure databases; the Search API’s 10,000-result cap is handled by segmented queries.

More audit & planning skills

/audit-api-usage

Inventory the integrations, service keys, legacy private apps, and internal tooling that call HubSpot APIs, and flag anything on legacy v1-v4 endpoints or legacy app architecture ahead of HubSpot's 2027 cutoffs. Produces a migration checklist to date-based API versions and service keys.

/connect-hubspot-agent-cli

Install and connect HubSpot's Agent CLI so Claude Code can run bulk and administrative HubSpot operations directly from the terminal: JSONL bulk writes, deletes, property and pipeline management, and workflow CRUD, with dry runs. Covers user versus service key mode, safe-use rules, and how the CLI fits beside MCP and this repo's scripts.

/connect-hubspot-mcp

Connect Claude to HubSpot's official remote MCP server for conversational CRM lookups, spot-checks, and small confirmed edits. Covers the MCP connector setup with OAuth and PKCE, what the server's tools can and cannot do, and when to use MCP versus the Agent CLI versus this repo's scripts.