CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
hubspot avatar

Ticket Resolution

hubspot/agent-cli-skills
1.3k installs18 stars
Summary

A complete workflow for managing HubSpot support tickets through the CLI, from creation through triage to resolution. It walks you through pipeline discovery (critical, since stage IDs differ per portal), bulk ticket creation from JSONL queues, filtering by priority and assignment status, and moving tickets between stages with dry run protection. The enum probing technique is clever: send an invalid value to get HubSpot to return the valid options list, since the properties API won't give them to you. Most useful when you need to process tickets at scale or automate common triage patterns like bulk reassignment or stage advancement based on category filters.

Install to Claude Code

npx -y skills add hubspot/agent-cli-skills --skill ticket-resolution --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Files
SKILL.mdView on GitHub

Read bulk-operations/SKILL.md first — JSONL piping, batch read, pagination, dry-run/digest/confirm, and hubspot history recovery live there. hubspot <command> --help is authoritative. Tickets use the tickets object type (plural, e.g. tickets:45123).

1. Discover pipeline + stages (portal-specific, run every session)

Stage IDs differ in every portal — never hard-code them.

hubspot pipelines list --type tickets --format table
hubspot pipelines stages --type tickets --pipeline <pipeline_id> --format table

The stage table prints each stage's ID and Label ("New", "Waiting on contact", "Closed", etc.).

2. Verify enum option values for THIS portal

hs_ticket_priority, hs_ticket_category, and hs_resolution are all enumeration properties — option values are portal-configurable and hubspot properties get does NOT return them. Discover by probing or by reading live records:

# Probe: send an invalid value; the 400 error lists the allowed options.
hubspot objects update --type tickets <some_ticket_id> --property hs_resolution=__probe__
# error: "was not one of the allowed options: [ISSUE_FIXED, FEATURE_REQUEST_TRACKED, ...]"

# Or read values already in use:
hubspot objects list --type tickets --limit 10 \
  --properties hs_ticket_priority,hs_ticket_category,hs_resolution

Do NOT assume HubSpot defaults — read the portal.

3. Create a ticket and associate it

subject is the only practically-required property. Skipping hs_pipeline/hs_pipeline_stage lands the ticket in the default pipeline's first stage.

hubspot objects create --type tickets \
  --property subject="Login error on mobile app" \
  --property content="User reports 401 since v3.2 release." \
  --property hs_pipeline=<pipeline_id> \
  --property hs_pipeline_stage=<new_stage_id> \
  --property hs_ticket_priority=<value_from_step_2> \
  --property hs_ticket_category=<value_from_step_2>
# Capture the "id" from the output JSON.

hubspot associations create --from tickets:<ticket_id> --to contacts:<contact_id>
hubspot associations create --from tickets:<ticket_id> --to companies:<company_id>

Bulk intake from a JSONL queue (see bulk-operations/resources/json-patterns.md for reshape patterns):

cat support_requests.jsonl \
| jq -c '{properties:{subject:.subject, content:.description,
    hs_pipeline:"<pipeline_id>", hs_pipeline_stage:"<new_stage_id>",
    hs_ticket_priority:"<priority>", hs_ticket_category:"<category>"}}' \
| hubspot objects create --type tickets

4. Triage queries

# Open tickets by priority
hubspot objects search --type tickets \
  --filter "hs_pipeline_stage=<open_stage_id> AND hs_ticket_priority=HIGH" \
  --properties subject,hubspot_owner_id,createdate

# Unassigned
hubspot objects search --type tickets \
  --filter "!hubspot_owner_id AND hs_pipeline_stage=<open_stage_id>" \
  --properties subject,hs_ticket_priority,createdate

Filter by owner with hubspot_owner_id=<id> (find IDs via hubspot owners list --format table).

5. Advance tickets through stages (bulk update from search)

hubspot objects search --type tickets \
  --filter "hs_ticket_category=BILLING_ISSUE AND hs_pipeline_stage=<new_stage_id>" \
| jq -c '{id, properties:{hs_pipeline_stage:"<waiting_stage_id>"}}' \
| hubspot objects update --type tickets --dry-run

Re-pipe the same search without --dry-run to execute. For >100 rows, follow the --digest/--confirm flow in bulk-operations/SKILL.md ("Safe destructive workflow"). Reassign in bulk works identically with {hubspot_owner_id:"<new>"}.

6. Log a resolution note

Activity creation lives in sales-execution/SKILL.md (notes/calls/meetings/tasks). After creating the note there, link it: hubspot associations create --from notes:<note_id> --to tickets:<ticket_id>.

7. Close the ticket

hs_resolution is an enumeration — pass an allowed option value from Step 2, not free text. HubSpot then computes hs_is_closed=true, closed_date, and time_to_close.

hubspot objects update --type tickets <ticket_id> \
  --property hs_pipeline_stage=<closed_stage_id> \
  --property hs_resolution=<allowed_resolution_value>

Known limitations

  • properties get/list do not return enum options — probe via update error or read live records (CLI ask logged).
  • No Conversations/Inbox API surface — chat threads and inbox emails are not CLI-accessible.
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Categories
DevOps & CI/CDAI & Agent BuildingProductivity & PlanningSales & MarketingCLI & Terminal
First SeenJul 14, 2026
View on GitHub

More from hubspot/agent-cli-skills

All 15 skills →
  • Crm Lookup1.1k
  • Bulk Operations1.1k
  • Crm Data Quality1.1k
  • Workflow Automation1.1k
  • Data Enrichment1k
  • Communication History1k
  • Custom Object Management1k
  • Deal Management1k
  • Sales Reporting1k
  • Sales Execution1k
  • Team Ownership1k
  • Customer Retention1k
  • Audience Targeting1k
  • Quote To Cash1k

Recommended

More DevOps & CI/CD →
vitorpamplona avatar
kotlin-multiplatform

vitorpamplona/amethyst

Platform abstraction decision-making for Amethyst KMP project. Guides when to abstract vs keep platform-specific, source set placement (commonMain, jvmAndroid, platform-specific), expect/actual patterns. Covers primary targets (Android, JVM/Desktop, iOS — all mature) with web/wasm as possible future targets. Integrates with gradle-expert for dependency issues. Triggers on: abstraction decisions ("should I share this?"), source set placement questions, expect/actual creation, build.gradle.kts work, incorrect placement detection, KMP dependency suggestions.
1.3k
1.6k
getsentry avatar
prompt-optimizer

getsentry/skills

Creates, optimizes, and iteratively refines agent prompts, system prompts, developer prompts, and reusable prompt templates. Use when asked to improve a prompt, optimize a system prompt, rewrite an agent prompt, tune prompt wording, make a prompt more reliable, port prompts between OpenAI, Claude, or Gemini, or build prompt evals.
1.3k
904
jezweb avatar
cloudflare-worker-builder

jezweb/claude-skills

Scaffold and deploy Cloudflare Workers with Hono routing, Vite plugin, and Static Assets. Describe project, scaffold structure, configure bindings, deploy. Use whenever the user wants to create a Worker project, set up Hono on Cloudflare, configure D1 / R2 / KV / Queues bindings, or troubleshoot Worker export syntax, API route conflicts, HMR issues, or deployment failures.
1.3k
960
vercel-labs avatar
frontend-design

vercel-labs/agent-eval

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
1.3k
234
customware-ai avatar
crm-builder

customware-ai/skills

Customer Relationship Management (CRM) vertical skill for the Customware SPA. Defines the section layout, entity views, and mapping rules for transforming a DOMAIN.md into a CRM tool. Use this skill when the Builder Agent classifies a customer's domain as contact management, sales pipeline, deal tracking, or customer relationship workflows. Trigger signals: contacts, leads, deals, pipeline, follow-ups, opportunities, accounts, customer data everywhere, can't track who talked to whom, sales process, referrals.
1.3k
2
nvidia avatar
cuopt-server-common

nvidia/skills

cuOpt REST server — what it does and how requests flow. Domain concepts; no deploy or client code.
1.3k
2.8k