AI-skillTriage Zendesk ticketsCustomer Success
Turn Zendesk tickets into prioritized support work with owners, replies, and SLA escalations. — Claude Skill
En Claude-skill för Claude Code av Claude Office — kör /zendesk-automation i Claude·Uppdaterad 12 juni 2026·vclaude-office-skills/skills@zendesk-automation
Turns a Zendesk queue into a prioritized support plan: incident clusters, SLA risk, assignees, macros, escalation notes, and customer replies.
- Reads Zendesk ticket exports, queue summaries, customer notes, and priority rules.
- Groups duplicate tickets into incidents, how-to requests, billing issues, product signals, and normal queue work.
- Recommends priority, assignee or group, tags, macro replies, internal notes, and escalation path.
- Flags SLA risk, enterprise customer impact, and decisions that need a human before bulk updates.
DuIdag
A support lead scans Zendesk one ticket at a time, guesses urgency, asks in Slack who owns the issue, and writes replies from scratch while the SLA clock keeps running.
Med /zendesk-automation
Run /zendesk-automation with the Zendesk export and support rules. The skill returns priority groups, owner suggestions, macros, escalation notes, and human-review warnings.
1 Paste Zendesk queue export2 Add SLA and routing rules3 Group duplicates and incidents4 Review owners, macros, and escalations5 Update Zendesk after human approval
För vem
Vad det gör
Morning Zendesk queue triage
Turn overnight tickets into a clear queue order with priority, owner, reply type, and what must be handled before the SLA slips.
Incident and duplicate detection
Spot when many tickets describe one customer-facing problem, group them under one incident, and prepare the internal escalation note.
Macro and reply preparation
Choose which tickets can use a saved reply, which need a personal response, and which need more information before support replies.
Product feedback from support
Group repeated requests into product themes without treating every feature request as an urgent support incident.
Så fungerar det
1
Paste a Zendesk queue export, ticket summaries, or copied ticket text with customer tier, status, tags, and message body.
2
Add the routing rules that matter: SLA, customer tier, product area, incident threshold, billing policy, or escalation channel.
3
The skill clusters related tickets, separates incidents from routine requests, and proposes Zendesk fields, owners, replies, and escalation notes.
4
A support lead reviews the recommendations before updating Zendesk, sending customer replies, or notifying Product and Engineering.
Indatametoder
Zendesk ticket export
Ticket ID, requester, company, customer tier, subject, status, tags, SLA clock, assignee, and latest customer message.
Exempel
What the user pastes
Zendesk queue, Monday 09:00: ZD-1842 | Acme Corp | Enterprise | 42 min to first-response SLA | tag: checkout | Safari users time out after card entry. 11 customers added similar replies. ZD-1845 | Northwind | Enterprise | 1h 20m to SLA | tag: invoice_export | Finance admin cannot export April invoices before close. ZD-1850 | 14 Standard customers | tag: 2fa_reset | Users need help moving two-factor authentication to a new phone. ZD-1857 | 3 Business admins | tag: bulk_user_upload | Asking whether CSV user import exists. ZD-1862 | Beta customer | tag: bug_report | Settings page flashes once, then works after refresh. Priority rules: - Checkout/payment blockers become P1 when more than 5 customers report the same failure. - Enterprise billing or invoice export tickets require a response within 2 hours. - How-to requests can use an approved macro unless the customer is Enterprise. - Product requests should be grouped for weekly product review, not escalated as incidents. Need: Zendesk priority, owner group, customer reply, internal note, and escalation list.
Useful result
P1 incident: checkout timeout on Safari
Why: 11 linked replies plus more than 5 affected customers crosses the payment-blocker threshold. Zendesk: set priority urgent, tag incident_checkout_safari, assign Support Lead, link related tickets. Escalate to Payments Engineering and #support-incidents. Customer reply: 'We are investigating a Safari checkout issue and will update this ticket within 30 minutes.'
High priority: enterprise invoice export
Why: Enterprise billing issue with less than 2 hours to SLA. Zendesk: assign Billing Support, set priority high, add tag enterprise_billing, send acknowledgement now. Internal note: check whether exports fail for all April invoices or only Northwind.
Macro queue: two-factor reset
Why: routine how-to requests from Standard customers. Zendesk: use the approved 2FA reset macro, keep status pending after reply, and route only failed-reset follow-ups back to Support.
Product signal: bulk user upload
Why: repeated feature request, not an active incident. Zendesk: tag product_feedback_bulk_upload, send expectation-setting reply, and add the theme to the weekly Product review list.
Human review before update
Confirm the checkout incident severity, customer-facing wording, and whether Support is allowed to mention the public status page before applying bulk updates.
Förbättrade mätvärden
Ticket Cycle Time
-10-25%
Customer SuccessIssue Hygiene
+20-35%
Customer SuccessFungerar med
Slack
manuellNotify support incident channels and share escalation context that should not be sent to customers.
Jira
manuellCreate or link engineering follow-up when a support cluster becomes a product bug or incident.
Zendesk
manuellUse ticket exports, tags, status, SLA clocks, customer tier, assignee, and message body as the queue source.
Fungerar överallt
Fristående
Ingen installation krävs
Paste the notes, exports, screenshots, or summaries you already have. The skill works without a connected system.
Ansluten
CRM + verktyg integrerade
Connect the relevant support, analytics, CRM, or data tool when you want fresher source evidence.
Vill du använda Zendesk Support Automation?
Välj hur du vill komma igång.
Kör i Claude Code
Gratis. Open source.
Installera och kör denna skill lokalt på din dator.
1
Installera Claude Code
Öppna en terminal på din dator och klistra in detta kommando:
2
Installera skillen
Detta laddar ner skillen med alla filer till din dator:
Lägg till -g i slutet för att göra den tillgänglig i alla dina projekt.
3
Visa källkod på GitHub Kör den
Starta Claude Code och skriv kommandot:
sedan
Zendesk Automation
Comprehensive skill for automating Zendesk support workflows and ticket management.
Core Workflows
1. Ticket Triage Pipeline
INCOMING TICKET FLOW:
┌─────────────────┐
│ New Ticket │
└────────┬────────┘
▼
┌─────────────────┐
│ AI Analysis │
│ - Intent │
│ - Sentiment │
│ - Urgency │
└────────┬────────┘
▼
┌─────────────────┐
│ Categorize │
│ - Type │
│ - Product │
│ - Skill needed │
└────────┬────────┘
▼
┌─────────────────┐
│ Route & Assign │
│ - Team │
│ - Agent │
│ - Priority │
└────────┬────────┘
▼
┌─────────────────┐
│ Auto-Response │
│ (if applicable)│
└─────────────────┘
2. Routing Rules
routing_rules:
- name: billing_issues
conditions:
- field: subject
contains: ["billing", "invoice", "charge", "refund", "payment"]
- field: tags
includes: ["billing"]
actions:
- set_group: billing_team
- set_priority: high
- add_tags: ["billing_routed"]
- name: technical_support
conditions:
- field: subject
contains: ["error", "bug", "not working", "crash"]
- field: product
equals: "software"
actions:
- set_group: tech_support
- set_priority: normal
- add_tags: ["technical"]
- name: enterprise_escalation
conditions:
- field: organization
tier: enterprise
- field: priority
equals: urgent
actions:
- set_group: enterprise_team
- set_priority: urgent
- notify: slack_channel
3. Priority Matrix
| Customer Tier | Issue Type | Response SLA | Resolution SLA |
|---|---|---|---|
| Enterprise | Critical | 15 minutes | 4 hours |
| Enterprise | High | 1 hour | 8 hours |
| Business | Critical | 1 hour | 8 hours |
| Business | Normal | 4 hours | 24 hours |
| Standard | All | 8 hours | 48 hours |
Auto-Response Templates
Common Issue Responses
auto_responses:
password_reset:
trigger:
keywords: ["password", "reset", "forgot", "login"]
response: |
Hi {{ticket.requester.name}},
I understand you're having trouble accessing your account.
Here's how to reset your password:
1. Go to {{settings.login_url}}/forgot-password
2. Enter your email address
3. Check your inbox for the reset link
4. Create a new password
If you don't receive the email within 5 minutes,
please check your spam folder.
Let me know if you need any further assistance!
actions:
- add_tags: ["auto_replied", "password_reset"]
- set_status: pending
shipping_inquiry:
trigger:
keywords: ["shipping", "tracking", "delivery", "order status"]
response: |
Hi {{ticket.requester.name}},
Thanks for reaching out about your order!
I've looked up your recent order and here's the status:
{{#if order.tracking_number}}
- Order #: {{order.id}}
- Status: {{order.status}}
- Tracking: {{order.tracking_number}}
- Estimated Delivery: {{order.estimated_delivery}}
{{else}}
Your order is being processed and tracking information
will be available within 24 hours.
{{/if}}
Is there anything else I can help with?
Ticket Management
Macro Library
macros:
- name: request_more_info
actions:
- add_comment: |
Thank you for contacting us. To better assist you,
could you please provide:
1. Your account email
2. Steps to reproduce the issue
3. Any error messages you're seeing
4. Screenshots if possible
- set_status: pending
- add_tags: ["awaiting_info"]
- name: escalate_to_engineering
actions:
- add_internal_note: "Escalated to engineering team"
- set_group: engineering
- set_priority: high
- add_tags: ["escalated", "engineering"]
- notify: engineering_slack
- name: close_resolved
actions:
- add_comment: |
I'm glad we could resolve this for you!
If you have any other questions, feel free to
reach out anytime. We're here to help.
Have a great day!
- set_status: solved
- add_tags: ["resolved"]
Bulk Operations
bulk_actions:
- name: close_stale_tickets
schedule: "0 0 * * *" # Daily
conditions:
- status: pending
- last_update_days: 7
actions:
- add_comment: "Closing due to no response. Please reopen if needed."
- set_status: solved
- add_tags: ["auto_closed"]
- name: escalate_breaching_sla
schedule: "*/15 * * * *" # Every 15 min
conditions:
- sla_breach_in_minutes: 30
actions:
- set_priority: urgent
- notify: team_lead
- add_tags: ["sla_at_risk"]
SLA Management
SLA Policies
sla_policies:
- name: enterprise_sla
conditions:
organization_tag: enterprise
targets:
first_reply:
urgent: 15 # minutes
high: 60
normal: 240
resolution:
urgent: 240
high: 480
normal: 1440
- name: standard_sla
conditions:
default: true
targets:
first_reply:
urgent: 60
high: 240
normal: 480
resolution:
urgent: 480
high: 1440
normal: 2880
SLA Dashboard
SLA PERFORMANCE - THIS WEEK
═══════════════════════════════════════
First Reply SLA:
Enterprise ████████████████████ 98% ✓
Business ██████████████████░░ 94% ✓
Standard █████████████████░░░ 89% ⚠
Resolution SLA:
Enterprise ████████████████████ 96% ✓
Business █████████████████░░░ 91% ✓
Standard ████████████████░░░░ 85% ⚠
TICKETS AT RISK:
┌──────────┬──────────┬───────────┐
│ Ticket │ Customer │ Time Left │
├──────────┼──────────┼───────────┤
│ #45231 │ Acme Corp│ 12 min │
│ #45198 │ TechStart│ 28 min │
│ #45156 │ DataFlow │ 45 min │
└──────────┴──────────┴───────────┘
AI-Powered Features
Sentiment Analysis
sentiment_analysis:
enabled: true
actions:
negative:
- add_tags: ["negative_sentiment"]
- set_priority: +1 # Increase priority
- notify: team_lead
frustrated:
- add_tags: ["frustrated_customer"]
- route_to: senior_agents
- add_internal_note: "Customer appears frustrated"
Intent Detection
intent_detection:
categories:
- name: billing_inquiry
keywords: ["charge", "invoice", "refund", "bill"]
confidence_threshold: 0.8
- name: technical_issue
keywords: ["error", "bug", "broken", "crash"]
confidence_threshold: 0.75
- name: feature_request
keywords: ["wish", "would be nice", "suggest", "feature"]
confidence_threshold: 0.7
- name: cancellation
keywords: ["cancel", "stop", "end subscription"]
confidence_threshold: 0.85
actions:
- route_to: retention_team
- set_priority: high
Integration Workflows
Slack Integration
slack_integration:
notifications:
- trigger: new_urgent_ticket
channel: "#support-urgent"
message: "🚨 New urgent ticket: {{ticket.subject}}"
- trigger: sla_warning
channel: "#support-alerts"
message: "⚠️ Ticket #{{ticket.id}} approaching SLA breach"
- trigger: negative_csat
channel: "#support-feedback"
message: "📉 Low CSAT received for ticket #{{ticket.id}}"
JIRA Integration
jira_integration:
sync_rules:
- zendesk_tag: bug_confirmed
create_jira:
project: DEV
issue_type: Bug
priority_map:
urgent: Highest
high: High
normal: Medium
sync_fields:
- description
- attachments
link_back: true
Analytics & Reporting
Key Metrics
SUPPORT METRICS DASHBOARD
═══════════════════════════════════════
Volume:
Today's Tickets: 156 (+12% vs avg)
Open Tickets: 234
Backlog: 45
Performance:
Avg First Reply: 42 min (target: 60 min) ✓
Avg Resolution: 4.2 hrs (target: 8 hrs) ✓
One-Touch Resolution: 34%
Satisfaction:
CSAT Score: 4.6/5.0 ⭐
NPS: +45
Response Quality: 92%
Agent Performance:
┌────────────┬────────┬──────────┬──────┐
│ Agent │ Solved │ Avg Time │ CSAT │
├────────────┼────────┼──────────┼──────┤
│ Sarah │ 28 │ 3.1 hrs │ 4.8 │
│ Mike │ 25 │ 3.5 hrs │ 4.7 │
│ Lisa │ 22 │ 4.0 hrs │ 4.6 │
└────────────┴────────┴──────────┴──────┘
Best Practices
- Quick First Response: Acknowledge tickets quickly, even if resolution takes longer
- Use Macros Wisely: Personalize templated responses
- Tag Consistently: Enable better routing and reporting
- Monitor SLAs: Set up alerts before breaches
- Capture Feedback: Send CSAT surveys after resolution
- Regular Training: Update agents on common issues
Referensdokument
name: Zendesk Automation description: Automate customer support workflows with Zendesk ticket management, routing, and analytics version: 1.0.0 author: Claude Office Skills category: support tags:
- zendesk
- helpdesk
- tickets
- customer-support
- automation department: support models:
- claude-3-opus
- claude-3-sonnet
- gpt-4
mcp:
server: helpdesk-mcp
tools:
- zendesk_create_ticket
- zendesk_update_ticket
- zendesk_search
- zendesk_macros capabilities:
- Ticket creation and routing
- Auto-response generation
- SLA monitoring
- Agent assignment input:
- Support requests
- Ticket data
- Customer information
- Priority criteria output:
- Ticket responses
- Routing decisions
- Performance reports
- SLA dashboards languages:
- en
- zh related_skills:
- slack-workflows
- customer-success
- intercom-automation
Zendesk Automation
Comprehensive skill for automating Zendesk support workflows and ticket management.
Core Workflows
1. Ticket Triage Pipeline
INCOMING TICKET FLOW:
┌─────────────────┐
│ New Ticket │
└────────┬────────┘
▼
┌─────────────────┐
│ AI Analysis │
│ - Intent │
│ - Sentiment │
│ - Urgency │
└────────┬────────┘
▼
┌─────────────────┐
│ Categorize │
│ - Type │
│ - Product │
│ - Skill needed │
└────────┬────────┘
▼
┌─────────────────┐
│ Route & Assign │
│ - Team │
│ - Agent │
│ - Priority │
└────────┬────────┘
▼
┌─────────────────┐
│ Auto-Response │
│ (if applicable)│
└─────────────────┘
2. Routing Rules
routing_rules:
- name: billing_issues
conditions:
- field: subject
contains: ["billing", "invoice", "charge", "refund", "payment"]
- field: tags
includes: ["billing"]
actions:
- set_group: billing_team
- set_priority: high
- add_tags: ["billing_routed"]
- name: technical_support
conditions:
- field: subject
contains: ["error", "bug", "not working", "crash"]
- field: product
equals: "software"
actions:
- set_group: tech_support
- set_priority: normal
- add_tags: ["technical"]
- name: enterprise_escalation
conditions:
- field: organization
tier: enterprise
- field: priority
equals: urgent
actions:
- set_group: enterprise_team
- set_priority: urgent
- notify: slack_channel
3. Priority Matrix
| Customer Tier | Issue Type | Response SLA | Resolution SLA |
|---|---|---|---|
| Enterprise | Critical | 15 minutes | 4 hours |
| Enterprise | High | 1 hour | 8 hours |
| Business | Critical | 1 hour | 8 hours |
| Business | Normal | 4 hours | 24 hours |
| Standard | All | 8 hours | 48 hours |
Auto-Response Templates
Common Issue Responses
auto_responses:
password_reset:
trigger:
keywords: ["password", "reset", "forgot", "login"]
response: |
Hi {{ticket.requester.name}},
I understand you're having trouble accessing your account.
Here's how to reset your password:
1. Go to {{settings.login_url}}/forgot-password
2. Enter your email address
3. Check your inbox for the reset link
4. Create a new password
If you don't receive the email within 5 minutes,
please check your spam folder.
Let me know if you need any further assistance!
actions:
- add_tags: ["auto_replied", "password_reset"]
- set_status: pending
shipping_inquiry:
trigger:
keywords: ["shipping", "tracking", "delivery", "order status"]
response: |
Hi {{ticket.requester.name}},
Thanks for reaching out about your order!
I've looked up your recent order and here's the status:
{{#if order.tracking_number}}
- Order #: {{order.id}}
- Status: {{order.status}}
- Tracking: {{order.tracking_number}}
- Estimated Delivery: {{order.estimated_delivery}}
{{else}}
Your order is being processed and tracking information
will be available within 24 hours.
{{/if}}
Is there anything else I can help with?
Ticket Management
Macro Library
macros:
- name: request_more_info
actions:
- add_comment: |
Thank you for contacting us. To better assist you,
could you please provide:
1. Your account email
2. Steps to reproduce the issue
3. Any error messages you're seeing
4. Screenshots if possible
- set_status: pending
- add_tags: ["awaiting_info"]
- name: escalate_to_engineering
actions:
- add_internal_note: "Escalated to engineering team"
- set_group: engineering
- set_priority: high
- add_tags: ["escalated", "engineering"]
- notify: engineering_slack
- name: close_resolved
actions:
- add_comment: |
I'm glad we could resolve this for you!
If you have any other questions, feel free to
reach out anytime. We're here to help.
Have a great day!
- set_status: solved
- add_tags: ["resolved"]
Bulk Operations
bulk_actions:
- name: close_stale_tickets
schedule: "0 0 * * *" # Daily
conditions:
- status: pending
- last_update_days: 7
actions:
- add_comment: "Closing due to no response. Please reopen if needed."
- set_status: solved
- add_tags: ["auto_closed"]
- name: escalate_breaching_sla
schedule: "*/15 * * * *" # Every 15 min
conditions:
- sla_breach_in_minutes: 30
actions:
- set_priority: urgent
- notify: team_lead
- add_tags: ["sla_at_risk"]
SLA Management
SLA Policies
sla_policies:
- name: enterprise_sla
conditions:
organization_tag: enterprise
targets:
first_reply:
urgent: 15 # minutes
high: 60
normal: 240
resolution:
urgent: 240
high: 480
normal: 1440
- name: standard_sla
conditions:
default: true
targets:
first_reply:
urgent: 60
high: 240
normal: 480
resolution:
urgent: 480
high: 1440
normal: 2880
SLA Dashboard
SLA PERFORMANCE - THIS WEEK
═══════════════════════════════════════
First Reply SLA:
Enterprise ████████████████████ 98% ✓
Business ██████████████████░░ 94% ✓
Standard █████████████████░░░ 89% ⚠
Resolution SLA:
Enterprise ████████████████████ 96% ✓
Business █████████████████░░░ 91% ✓
Standard ████████████████░░░░ 85% ⚠
TICKETS AT RISK:
┌──────────┬──────────┬───────────┐
│ Ticket │ Customer │ Time Left │
├──────────┼──────────┼───────────┤
│ #45231 │ Acme Corp│ 12 min │
│ #45198 │ TechStart│ 28 min │
│ #45156 │ DataFlow │ 45 min │
└──────────┴──────────┴───────────┘
AI-Powered Features
Sentiment Analysis
sentiment_analysis:
enabled: true
actions:
negative:
- add_tags: ["negative_sentiment"]
- set_priority: +1 # Increase priority
- notify: team_lead
frustrated:
- add_tags: ["frustrated_customer"]
- route_to: senior_agents
- add_internal_note: "Customer appears frustrated"
Intent Detection
intent_detection:
categories:
- name: billing_inquiry
keywords: ["charge", "invoice", "refund", "bill"]
confidence_threshold: 0.8
- name: technical_issue
keywords: ["error", "bug", "broken", "crash"]
confidence_threshold: 0.75
- name: feature_request
keywords: ["wish", "would be nice", "suggest", "feature"]
confidence_threshold: 0.7
- name: cancellation
keywords: ["cancel", "stop", "end subscription"]
confidence_threshold: 0.85
actions:
- route_to: retention_team
- set_priority: high
Integration Workflows
Slack Integration
slack_integration:
notifications:
- trigger: new_urgent_ticket
channel: "#support-urgent"
message: "🚨 New urgent ticket: {{ticket.subject}}"
- trigger: sla_warning
channel: "#support-alerts"
message: "⚠️ Ticket #{{ticket.id}} approaching SLA breach"
- trigger: negative_csat
channel: "#support-feedback"
message: "📉 Low CSAT received for ticket #{{ticket.id}}"
JIRA Integration
jira_integration:
sync_rules:
- zendesk_tag: bug_confirmed
create_jira:
project: DEV
issue_type: Bug
priority_map:
urgent: Highest
high: High
normal: Medium
sync_fields:
- description
- attachments
link_back: true
Analytics & Reporting
Key Metrics
SUPPORT METRICS DASHBOARD
═══════════════════════════════════════
Volume:
Today's Tickets: 156 (+12% vs avg)
Open Tickets: 234
Backlog: 45
Performance:
Avg First Reply: 42 min (target: 60 min) ✓
Avg Resolution: 4.2 hrs (target: 8 hrs) ✓
One-Touch Resolution: 34%
Satisfaction:
CSAT Score: 4.6/5.0 ⭐
NPS: +45
Response Quality: 92%
Agent Performance:
┌────────────┬────────┬──────────┬──────┐
│ Agent │ Solved │ Avg Time │ CSAT │
├────────────┼────────┼──────────┼──────┤
│ Sarah │ 28 │ 3.1 hrs │ 4.8 │
│ Mike │ 25 │ 3.5 hrs │ 4.7 │
│ Lisa │ 22 │ 4.0 hrs │ 4.6 │
└────────────┴────────┴──────────┴──────┘
Best Practices
- Quick First Response: Acknowledge tickets quickly, even if resolution takes longer
- Use Macros Wisely: Personalize templated responses
- Tag Consistently: Enable better routing and reporting
- Monitor SLAs: Set up alerts before breaches
- Capture Feedback: Send CSAT surveys after resolution
- Regular Training: Update agents on common issues
Source marketplace page: https://github.com/claude-office-skills/skills/blob/HEAD/zendesk-automation/SKILL.md
Install command: npx skills add claude-office-skills/skills@zendesk-automation