Hubspot logo

Hubspot

Organization
OpenClaudia
hubspot

Manage HubSpot CRM contacts, companies, deals, and CMS content via API. Use when the user says "add contact to HubSpot", "create deal", "search CRM", "HubSpot contacts", "update deal stage", "CRM report", "HubSpot pages", or asks about managing their sales pipeline, CRM data, or HubSpot content.

Overview

PublisherOpenClaudia
Repositoryopenclaudia-skills
Skill namehubspot
Stars
714
Forks
60
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by OpenClaudia on GitHub. Read the source before you install it.

Installation

Install the Hubspot AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/OpenClaudia/openclaudia-skills/tree/main/skills/hubspot
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/OpenClaudia/openclaudia-skills.git /tmp/openclaudia-skills
mkdir -p .claude/skills
cp -r /tmp/openclaudia-skills/skills/hubspot .claude/skills/hubspot
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Hubspot in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Hubspot on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Hubspot is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

HubSpot CRM & CMS Skill

You are a HubSpot CRM and CMS automation expert. Use the HubSpot API to manage contacts, companies, deals, owners, associations, properties, CMS pages, and files.

Prerequisites

This skill requires HUBSPOT_ACCESS_TOKEN (Private App token). Check for it in environment variables or ~/.claude/.env.global. If not found, inform the user:

This skill requires a HubSpot Private App access token. Set it via:
  export HUBSPOT_ACCESS_TOKEN=your_token_here
Or add it to ~/.claude/.env.global

Create a Private App at: Settings > Integrations > Private Apps
Required scopes: crm.objects.contacts, crm.objects.companies, crm.objects.deals, content

API Reference

Base URL: https://api.hubapi.com Auth header: Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN} Rate limit: 100 requests per 10 seconds for private apps.

Contacts

List contacts:

bash
curl -s "https://api.hubapi.com/crm/v3/objects/contacts?limit=10&properties=firstname,lastname,email,company,phone" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}"

Search contacts:

bash
curl -s -X POST "https://api.hubapi.com/crm/v3/objects/contacts/search" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "filterGroups": [{
      "filters": [{
        "propertyName": "email",
        "operator": "CONTAINS_TOKEN",
        "value": "example.com"
      }]
    }],
    "properties": ["firstname", "lastname", "email", "company"],
    "limit": 10
  }'

Create contact:

bash
curl -s -X POST "https://api.hubapi.com/crm/v3/objects/contacts" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "properties": {
      "firstname": "John",
      "lastname": "Doe",
      "email": "john@example.com",
      "company": "Acme Inc",
      "phone": "+1234567890"
    }
  }'

Get contact by email:

bash
curl -s -X POST "https://api.hubapi.com/crm/v3/objects/contacts/search" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "filterGroups": [{
      "filters": [{
        "propertyName": "email",
        "operator": "EQ",
        "value": "john@example.com"
      }]
    }],
    "properties": ["firstname", "lastname", "email", "company", "phone", "lifecyclestage"]
  }'

Companies

List companies:

bash
curl -s "https://api.hubapi.com/crm/v3/objects/companies?limit=10&properties=name,domain,industry,numberofemployees" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}"

Search companies by domain:

bash
curl -s -X POST "https://api.hubapi.com/crm/v3/objects/companies/search" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "filterGroups": [{
      "filters": [{
        "propertyName": "domain",
        "operator": "EQ",
        "value": "example.com"
      }]
    }],
    "properties": ["name", "domain", "industry", "numberofemployees", "annualrevenue"]
  }'

Deals

Create deal:

bash
curl -s -X POST "https://api.hubapi.com/crm/v3/objects/deals" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "properties": {
      "dealname": "New Enterprise Deal",
      "dealstage": "appointmentscheduled",
      "pipeline": "default",
      "amount": "50000",
      "closedate": "2026-06-30"
    }
  }'

List deals:

bash
curl -s "https://api.hubapi.com/crm/v3/objects/deals?limit=10&properties=dealname,dealstage,amount,closedate,pipeline" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}"

Update deal stage:

bash
curl -s -X PATCH "https://api.hubapi.com/crm/v3/objects/deals/{dealId}" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{"properties": {"dealstage": "closedwon"}}'

Owners

List owners (sales reps):

bash
curl -s "https://api.hubapi.com/crm/v3/owners/" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}"

Associations

Associate contacts with companies or deals:

bash
# Associate deal with contact (type 3)
curl -s -X PUT "https://api.hubapi.com/crm/v3/objects/deals/{dealId}/associations/contacts/{contactId}/3" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}"

# Associate deal with company (type 5)
curl -s -X PUT "https://api.hubapi.com/crm/v3/objects/deals/{dealId}/associations/companies/{companyId}/5" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}"

# Associate contact with company (type 1)
curl -s -X PUT "https://api.hubapi.com/crm/v3/objects/contacts/{contactId}/associations/companies/{companyId}/1" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}"

Get associated contacts for a deal:

bash
curl -s "https://api.hubapi.com/crm/v3/objects/deals/{dealId}/associations/contacts" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}"

Properties

List all contact properties:

bash
curl -s "https://api.hubapi.com/crm/v3/properties/contacts" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}"

CMS Pages

List site pages:

bash
curl -s "https://api.hubapi.com/cms/v3/pages/site-pages?limit=10" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}"

List landing pages:

bash
curl -s "https://api.hubapi.com/cms/v3/pages/landing-pages?limit=10" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}"

Search Operators

OperatorDescription
EQEqual to
NEQNot equal to
LT / LTELess than / Less than or equal
GT / GTEGreater than / Greater than or equal
CONTAINS_TOKENContains word
NOT_CONTAINS_TOKENDoes not contain word
HAS_PROPERTYProperty exists
NOT_HAS_PROPERTYProperty does not exist

Pagination

All list endpoints support pagination via the after parameter:

bash
curl -s "https://api.hubapi.com/crm/v3/objects/contacts?limit=100&after={next_cursor}" \
  -H "Authorization: Bearer ${HUBSPOT_ACCESS_TOKEN}"

The after value comes from paging.next.after in the response.

Common Workflows

Pipeline Report

  1. List all deals with dealstage, amount, closedate
  2. Group by stage
  3. Sum amounts per stage
  4. Present as pipeline summary table

Contact Enrichment

  1. Search contacts missing key properties (NOT_HAS_PROPERTY)
  2. For each, check if company domain exists
  3. Pull company data and update contact

Deal Health Check

  1. List deals in active stages
  2. Flag deals with no activity in 14+ days
  3. Flag deals past expected close date
  4. Present prioritized action list

Important Notes

  • Always use pagination for large datasets. Default limit is 10, max is 100.
  • HubSpot property names are lowercase with no spaces (e.g., firstname, dealstage, closedate).
  • Deal stages vary by pipeline. List pipeline stages via the Pipelines API if needed.
  • Rate limit: 100 requests per 10 seconds. Batch operations when possible.

Frequently asked questions

What does the Hubspot AI skill do?

Manage HubSpot CRM contacts, companies, deals, and CMS content via API. Use when the user says "add contact to HubSpot", "create deal", "search CRM", "HubSpot contacts", "update deal stage", "CRM report", "HubSpot pages", or asks about managing their sales pipeline, CRM data, or HubSpot content.

Why use Hubspot on TypingMind?

Because you install it once and use it with any model. Hubspot is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Hubspot in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/OpenClaudia/openclaudia-skills/tree/main/skills/hubspot. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Hubspot?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Hubspot?

As many as you like. As long as a model supports skills, you can use Hubspot with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Hubspot AI skill free?

Yes. It is published on GitHub by OpenClaudia under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇