Agent skill

gt-hubspot-admin

Comprehensive HubSpot CRM administration toolkit by Growth Today (growthtoday.co).

activeNeeds a keyActs undeclared467 words

From Growth-Today/claude-skills · 12 skills · 3 · pushed 2026-09-11

What it does when it runs

Comprehensive HubSpot CRM administration toolkit by Growth Today (growthtoday.co). Use when the user asks about auditing a HubSpot portal, CRM cleanup or data hygiene, RevOps maintenance, suppressing bounced or unsubscribed contacts, improving deliverability, enriching contact or company data, fixing lifecycle stages, building smart lists or lead scoring, classifying ICP tiers, deduplicating contacts or companies, reassigning owners, building deal pipelines, reporting and dashboards, users and permissions, or bounce, engagement, and lifecycle automation workflows. Also triggers on "hubspot audit", "hubspot cleanup", "ghost contacts", "hard bounce suppression", "fix lifecycle stage", "lead scoring", "smart lists", "ICP tiers", "duplicate contacts", "deal pipeline", "custom objects", "hubspot reporting", "user permissions", "hubspot workflow", "quarterly database cleanup". Do NOT use for non-HubSpot CRMs (Salesforce, Pipedrive) — HubSpot portal administration only.

Read from the skill and the 116 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: HUBSPOT_ACCESS_TOKEN
Hosts it reaches: api.hubapi.com
www.growthtoday.co
www.linkedin.com
Tool permissions it declares: No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.
Actions present in the files: shellwrites filesnetwork

Ask about gt-hubspot-admin

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?Claude ChatGPT

Adapt it to my stackClaude ChatGPT

What else do I need for it to workClaude ChatGPT

Rather ask a human? Talk to Cheetah

Install it

View source on GitHub ↗

git clone --depth 1 --filter=blob:none --sparse https://github.com/Growth-Today/claude-skills.git /tmp/claude-skills
git -C /tmp/claude-skills sparse-checkout set "gt-hubspot-admin"
mkdir -p ~/.claude/skills/gt-hubspot-admin
cp -R "/tmp/claude-skills/gt-hubspot-admin/." ~/.claude/skills/gt-hubspot-admin/

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 ↗

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.

Before you install: this skill will not complete its job on a bare agent. It needs HUBSPOT_ACCESS_TOKEN, which you have to obtain separately.

The skill

Source on GitHub ↗

Reproduced in full from Growth-Today/claude-skills/blob/506d174be93e8e3d53d7b93908b2439ff3e996cd/gt-hubspot-admin/SKILL.md, which is licensed MIT (skill frontmatter). 467 words, 7 headings.

GT HubSpot Admin — Master Router

Master orchestrator for HubSpot CRM administration & RevOps: 68 playbooks across 7 sub-skills covering audit, data hygiene, data model, segmentation, pipelines & deals, automation, reporting, and governance.

Setup (run once per session)

Before loading any sub-skill or playbook, resolve this skill's install directory:

Use Glob to find **/gt-hubspot-admin/SKILL.md.
The directory containing it is SKILL_BASE.
Sub-skills live at {SKILL_BASE}/.claude/skills/<sub-skill>/gt-SKILL.md.
Playbooks live at {SKILL_BASE}/playbooks/<name>/playbook.md (shared — sub-skills route to them).

Always resolve SKILL_BASE dynamically — never hardcode a path.

How routing works

Read the user's request.
Match it to ONE OR MORE sub-skills below.
Read that sub-skill's gt-SKILL.md — it holds the playbook index and guidance for that domain.
Read the specific {SKILL_BASE}/playbooks/<name>/playbook.md in full before acting.
If a playbook has a scripts/ folder, those are runnable Python files (requests + python-dotenv) reading HUBSPOT_ACCESS_TOKEN from a .env in the playbook folder.
Full-portal or recurring requests → use the cross-cutting playbooks below.

Sub-skill routing

User intent	Sub-skill	Path
Dedup, suppression, deliverability, enrichment, cleanup routines	hubspot-data-hygiene	`{SKILL_BASE}/.claude/skills/hubspot-data-hygiene/gt-SKILL.md`
Properties, custom objects, associations, validation, imports	hubspot-data-model	`{SKILL_BASE}/.claude/skills/hubspot-data-model/gt-SKILL.md`
Lists, ICP tiers, lead scoring, lead status, marketing contacts	hubspot-segmentation	`{SKILL_BASE}/.claude/skills/hubspot-segmentation/gt-SKILL.md`
Deal pipelines, stages, forecasting, renewals	hubspot-pipelines-deals	`{SKILL_BASE}/.claude/skills/hubspot-pipelines-deals/gt-SKILL.md`
Workflows, lead routing, lifecycle & notification automation	hubspot-automation	`{SKILL_BASE}/.claude/skills/hubspot-automation/gt-SKILL.md`
Dashboards, custom reports, attribution, SLA/KPIs	hubspot-reporting	`{SKILL_BASE}/.claude/skills/hubspot-reporting/gt-SKILL.md`
Users, teams, permissions, security, privacy, integrations	hubspot-governance	`{SKILL_BASE}/.claude/skills/hubspot-governance/gt-SKILL.md`

Cross-cutting playbooks (full-portal / recurring)

Use these directly for whole-portal engagements; each references playbooks across multiple sub-skills.

hubspot-audit — full diagnostic audit across 8 dimensions with grades. Read {SKILL_BASE}/playbooks/hubspot-audit/playbook.md
hubspot-implementation-plan — phased plan from an audit report. Read {SKILL_BASE}/playbooks/hubspot-implementation-plan/playbook.md
weekly-cleanup-routine — 5-minute weekly health check. Read {SKILL_BASE}/playbooks/weekly-cleanup-routine/playbook.md
quarterly-database-cleanup — comprehensive quarterly audit with QoQ trends. Read {SKILL_BASE}/playbooks/quarterly-database-cleanup/playbook.md

Prerequisites (apply to most playbooks)

HubSpot private app API token as HUBSPOT_ACCESS_TOKEN=pat-na1-xxxx. Scripts load it from a .env in their own playbook folder (playbooks/<name>/.env) via python-dotenv — copy .env.example there. See requirements.txt at the skill root.
Python 3.10+ with requests, python-dotenv, and hubspot-api-client (pip install -r requirements.txt). requests + python-dotenv power the scripts; hubspot-api-client powers the SDK examples in the playbooks.
Read access to the relevant HubSpot scopes (varies by playbook).

Notes

All playbooks are company-agnostic — no customer data, credentials, or proprietary references.
Some playbooks are fully API-automated; others are hybrid (API discovery + manual UI) due to HubSpot API limits. Each playbook states its automation level.

Created by Growth Today — AI-native GTM engineering firm. Maintained and updated by Brigitta Ruha. More open Claude Skills for go-to-market teams: https://www.growthtoday.co/claude-skills

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

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 · 691
revops-hubspot by NEON-Rutger · 48
hubspot-lead-enrichment by composio-community · 2
hubspot-plg-sync by warpdotdev · 1

Need help setting it up?

This page tells you what gt-hubspot-admin 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.