- Home
- Skills
- Anthropics
- Knowledge Work Plugins
- Ticket Triage
ticket-triage_skill
- Python
- Official
7.4k
GitHub Stars
1
Bundled Files
2 months ago
Catalog Refreshed
4 months ago
First Indexed
Readme & install
Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.
Installation
Preview and clipboard use veilstrat where the catalogue uses aiagentskills.
npx veilstrat add skill anthropics/knowledge-work-plugins --skill ticket-triage- SKILL.md8.0 KB
Overview
This skill triages incoming support tickets by categorizing issues, assigning priority (P1–P4), and recommending routing so tickets reach the right team quickly. It applies a clear taxonomy and priority framework to assess urgency, impact, and escalation triggers. The goal is fast, consistent decisions that reduce time-to-response and prevent missed SLAs.
How this skill works
The skill reads the ticket text, identifies signal words and root cause, and assigns a primary (and optional secondary) category such as Bug, How-to, Billing, or Security. It then maps impact and scope to a P1–P4 priority using defined criteria and escalation triggers, checks for duplicates or known issues, and recommends the correct routing (Tier 1, Tier 2, Engineering, Product, Security, or Billing). It also suggests initial response text and whether to bump priority.
When to use it
- When a new ticket or customer issue arrives
- When assessing severity and business impact of an incident
- Before routing a ticket to engineering or product
- When deciding whether to escalate or bump priority
- When checking for duplicates or known issues
Best practices
- Read the full ticket and any follow-up messages before finalizing category or priority
- Categorize by root cause, not just the symptom described
- Err on the side of higher priority if unsure — easier to de-escalate than to recover from missed SLAs
- Always search for duplicates and link to existing tickets when found
- Document what you checked and any temporary workarounds in internal notes
Example use cases
- Customer reports "API returning 500" — categorize as Bug, likely P1/P2 depending on scope, route to Engineering
- User asks "How do I configure SSO?" — categorize as How-to, P4, route to Tier 1 or Tier 2 for guided setup
- Multiple customers report slow response times — flag Performance, escalate priority due to pattern, route to Engineering
- Feature suggestion from a major account — categorize as Feature request, route to Product and document demand and business impact
- User reports unauthorized data access — categorize as Security, set P1 or P2 depending on exposure, escalate to Security team immediately
FAQ
Make the bug the primary category; root-cause issues take precedence for investigation.
When should I bump priority automatically?
Bump when SLAs are missed, multiple reports emerge, a workaround fails, the scope expands, or the customer escalates.