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
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by @mertduzgun

Independent project, not affiliated with Anthropic

Ticket Resolution

hubspot/agent-cli-skills
851 installs8 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 →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
AI notepad for back-to-back meetings
AI notepad for back-to-back meetings
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Email for Agents: Free tier availableEmail for Agents: Free tier available
Email for Agents: Free tier available
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
AI notepad for back-to-back meetings
AI notepad for back-to-back meetings
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Email for Agents: Free tier availableEmail for Agents: Free tier available
Email for Agents: Free tier available
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
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 →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
AI notepad for back-to-back meetings
AI notepad for back-to-back meetings
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
Keep your Mac awake
Keep your Mac awake
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Email for Agents: Free tier availableEmail for Agents: Free tier available
Email for Agents: Free tier available
Give your AI agent a complete email layer—sending, inbound inboxes, and sandbox testing.
Get 4K emails/month free →
Context.devContext.dev
Context.dev
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Categories
AI & Agent BuildingSales & MarketingCLI & Terminal
First SeenJul 14, 2026
View on GitHub

Recommended

More AI & Agent Building →
agent-memory-mcp

sickn33/antigravity-awesome-skills

agent memory mcp
1.2k
43.1k
agent-memory-mcp

davila7/claude-code-templates

agent memory mcp
569
29.4k
llm-application-dev-langchain-agent

sickn33/antigravity-awesome-skills

llm application dev langchain agent
306
39.4k
llm-application-dev

moizibnyousaf/ai-agent-skills

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
1.1k
ai-prompt-engineering-safety-review

github/awesome-copilot

Comprehensive safety analysis and improvement framework for AI prompts with detailed assessment methodologies.
9.8k
36.5k
emblem-ai-prompt-examples

emblemcompany/agent-skills

emblem ai prompt examples
8.8k
12