Agent skill
hubspot
Use when reading or syncing HubSpot CRM accounts through the GTM OS HubSpot connector; inspect the connector skill before changing CRM data.
Filed under CRM and RevOps.
From ay-automate/gtmos-skills · 107 skill entries · 0 · pushed 2026-11-02
What it does when it runs
Use when reading or syncing HubSpot CRM accounts through the GTM OS HubSpot connector; inspect the connector skill before changing CRM data.
Automated analysis of the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- developers.hubspot.com
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It only issues instructions, so there is nothing to bound. - Actions present in the files
- None. Instructions only.
Ask about hubspot
Opens your assistant with this page's recorded context. Check the linked sources before relying on it.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/ay-automate/gtmos-skills.git /tmp/gtmos-skills git -C /tmp/gtmos-skills sparse-checkout set "skills/hubspot" mkdir -p ~/.claude/skills/hubspot cp -R "/tmp/gtmos-skills/skills/hubspot/." ~/.claude/skills/hubspot/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
Or take the whole library
This repo ships a .claude-plugin manifest, so Claude Code can install all 107 skills at once. Plugin skills are invoked as /<plugin>:<skill>, so they never collide with your own.
/plugin marketplace add ay-automate/gtmos-skills /plugin
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗Reproduced in full from ay-automate/gtmos-skills/blob/86780d2f545cdc0a1de971917aa04b41bb0b3ccd/skills/hubspot/SKILL.md, which is licensed MIT (repository). 646 words, 10 headings.
hubspot with GTM OS
When to use this skill
Use when reading or syncing HubSpot CRM accounts through the GTM OS HubSpot connector; inspect the connector skill before changing CRM data.
What GTM OS uses it for
Native CRM sync/read primitive, with a typed HubSpot adapter and writeback implementation.
Capabilities and operation names are listed below as they appear in the connector package and
coverage map. Discover the live input and output schema with gtm describe before invocation;
the registry for the current organization is authoritative if it differs from this static guide.
- The connector's account-read capability reads account/company data (
crm.syncruns it). - The package declares the
gtm.accountmapping; writeback is part of the connector (a governed, approval-gated write). - It is a capability connector, not a promise that arbitrary HubSpot objects are mapped.
Connect it
Create an org-scoped HubSpot connection in the console Connections settings (or the provider-specific gtm connect flow). The connector uses the HubSpot API host api.hubapi.com. The required credential is the sealed HubSpot connection; no platform HubSpot secret is listed in .env.example.
Use the exact scopes surfaced by the HubSpot OAuth/connection flow and connector configuration. The connector package does not declare a scope list in its manifest; do not copy scopes from another app or broaden grants speculatively.
Use the console Connections/settings page for the provider when present. For CLI setup, inspect
gtm connect --help and use the provider name supported by the installed CLI; do not guess
flags or paste credentials into command history. Restart/reload the configured instance only
through its documented operator workflow.
Canonical data
- Reads HubSpot companies/accounts through the connector's account-read capability, run by
crm.sync. - Maps canonical output to
gtm.account. - Writeback is connector-specific; verify its current source and live operation schema before proposing a change.
Read and write records through registered operations and gtm.* objects only. A vendor-side
record is not automatically a canonical GTM OS record; use the connector's declared mapping and
retain source provenance. Do not infer fields from the vendor API.
Governance and safety
Treat account writeback as a governed GTM OS write. Use registered operations so the approval gate, authorization, audit, and provenance remain in force. Respect opt-outs for contacts even when the immediate record is an account.
- E-class/customer-facing writes are proposed for approval; a different human approves them.
- Respect consent, suppression, unsubscribe, and do-not-contact state before any person-level action.
- Honor configured spend/budget caps. Do not retry a billable request blindly after timeout.
- Keep connection secrets in the sealed connection or server environment. Never print or commit them.
Common errors and recovery
-
Authentication/401: refresh or reconnect the org's HubSpot connection.
-
403: check the installed grant scopes and HubSpot user permissions.
-
Missing company fields: inspect adapter mapping and source payload; do not fabricate values.
-
Rate limit: back off according to the provider response.
-
Check the connection state and provider health before retrying; use the connector's fixture mode only for development.
-
Read the operation error and lineage/receipt before changing inputs or repeating a write.
-
If the provider is not registered, stop and report that limitation; do not call the vendor directly as a workaround.
Do
- Read the connector entry in
docs/gtmos/reference/connections.mdand the currentgtm describeschema before a new integration action. - Start with a read or one narrowly scoped test, confirm provenance, then scale within the approved budget.
- Ask a human to resolve missing consent, expired credentials, or approval-required actions.
Don't
- Don't invent endpoints, scopes, operation names, or object fields.
- Don't bypass GTM OS governance with direct vendor writes or direct database edits.
- Don't send messages, change campaigns, or publish content without the operation's approval path.
Official vendor documentation
https://developers.hubspot.com/docs/api/overview
GTM OS reference: docs/gtmos/reference/connections.md (installed by gtm init) and the live gtm describe schema.
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- hubspot by OpenClaudia · 724
- hubspot-enrichment-scoring by explorium-ai · 348
- vibe-prospecting-hubspot by explorium-ai · 291
- hubspot-follow-email by getaero-io · 72
- revops-hubspot by NEON-Rutger · 58
- gt-hubspot-admin by Growth-Today · 6
- hubspot-plg-sync by warpdotdev · 3
- hubspot-lead-enrichment by composio-community · 2
Need help setting it up?
This page tells you what hubspot does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.