ticket-triage
Skill1 starsChanged 7 months agoMITView on GitHub
Triage and prioritize a support ticket or customer issue. Use when a new ticket comes in and needs categorization, assigning P1-P4 priority, deciding which team should handle it, or checking whether it is a duplicate or known issue before routing. Trigger with "triage this ticket", "prioritize this", "where should this go", or "is this a duplicate".
8 other projects use a version of this.
Adopted by
Most recently taken up by
- neomjs/neo-agent-skillstheir own version, first seen Nov 15, 2026
- GoogleCloudPlatform/devrel-demostheir own version, first seen Nov 8, 2026
- Suryanandx/qvac-uitheir own version, first seen Nov 1, 2026
- Big-LAORE/Biblioth-que-de-skillstheir own version, first seen Nov 1, 2026
- anthropics/knowledge-work-pluginstheir own version, first seen Oct 13, 2026
- edu6565/claude-skillstheir own version, first seen Oct 11, 2026
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 8
- anthropics/knowledge-work-plugins★ 36ksame name
- GoogleCloudPlatform/devrel-demos★ 404same name
- composio-community/support-skills★ 18same name
- neomjs/neo-agent-skills★ 11same name
- jwilger/agent-skills★ 4same name
- Big-LAORE/Biblioth-que-de-skills★ 1same name
- edu6565/claude-skills★ 0same name
- Suryanandx/qvac-ui★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository164 other files it gives its agents.
- instrument-data-to-allotropeSkill
- literature-reviewSkill
- nextflow-developmentSkill
- scientific-problem-selectionSkill
- scvi-toolsSkill
- single-cell-rna-qcSkill
- discover-brandSkill
- enforce-voiceSkill
- generate-guidelinesSkill
- csat-reportSkill
- customer-escalationSkill
- customer-researchSkill
- draft-responseSkill
- kb-articleSkill
- sentiment-analysisSkill
- analyzeSkill
- build-dashboardSkill
- create-vizSkill
- data-context-extractorSkill
- data-modelingSkill
- data-pipelineSkill
- etl-designSkill
- explore-dataSkill
- sql-queriesSkill
- statistical-analysisSkill
- validate-dataSkill
- write-querySkill
- accessibility-reviewSkill
- component-librarySkill
- design-critiqueSkill
- design-handoffSkill
- design-systemSkill
- frontend-designSkill
- research-synthesisSkill
- user-researchSkill
- ux-copySkill
- wireframingSkill
- Agent DevelopmentSkill
- CLAUDE.md ManagementSkill
- MCP Server BuilderSkill
- Plugin DevelopmentSkill
- Prompt EngineeringSkill
- Skill CreatorSkill
- curriculum-designSkill
- lesson-planningSkill
- quiz-generatorSkill
- study-guideSkill
- tutoringSkill
- api-designSkill
- architectureSkill
- ci-cd-pipelineSkill
- code-reviewSkill
- database-migrationSkill
- debugSkill
- dependency-auditSkill
- deploy-checklistSkill
- documentationSkill
- error-handlingSkill
- git-workflowSkill
- incident-responseSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 11 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
11
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 41
Before routing, search for existing reports:
- Distinctive: line 43
Open tickets: Search by error message, feature name, and symptom keywords.
- Distinctive: line 44
Known issues: Check the bug tracker or incident dashboard for active problems.
- Distinctive: line 45
Recent incidents: Look for ongoing incidents that match the reported behavior.
- Distinctive: line 46
KB articles: Check if a self-service answer already exists.
- Distinctive: line 48
If a duplicate or known issue is found, link to it rather than creating a separate investigation.
- Distinctive: line 84
Document the triage decision for the ticket record.
- Distinctive: line 128
Action: Search for open SSO tickets and known auth issues, determine if this matches an existing problem, link or create new based on …
- Distinctive: line 133
Check for duplicates before assigning priority.
- Distinctive: line 135
Do not over-prioritize. If everything is P1, nothing is.
- Distinctive: line 136
When in doubt between two priority levels, consider the customer tier and whether a workaround exists.
“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Ticket Triage
Categorize, prioritize, and route an incoming support ticket. Check for duplicates and known issues before assignment to avoid redundant work.
Workflow
Step 1: Read and Classify
Parse the ticket content to determine:
- Category: Bug, feature request, how-to question, billing, account management, integration issue, security concern, data request.
- Product area: Which feature or module is involved.
- Severity signal: Error messages, "production down" language, data loss mentions, urgency cues.
- Customer tier: Enterprise, pro, free -- derived from account data.
- Channel: Email, chat, phone, social, in-app feedback.
Step 2: Check for Duplicates
Before routing, search for existing reports:
- Open tickets: Search by error message, feature name, and symptom keywords.
- Known issues: Check the bug tracker or incident dashboard for active problems.
- Recent incidents: Look for ongoing incidents that match the reported behavior.
- KB articles: Check if a self-service answer already exists.
If a duplicate or known issue is found, link to it rather than creating a separate investigation.
Step 3: Assign Priority
Apply the priority matrix based on impact and urgency:
| Priority | Impact | Urgency | Examples |
| P1 - Critical | Production down, data loss, security breach | Immediate | Cannot log in, data deleted, payment processing broken |
| P2 - High | Major feature broken, significant workflow disruption | Same day | Reports not generating, integration failing, bulk operations broken |
| P3 - Medium | Feature degraded, workaround available | Next business day | Slow performance, UI glitch with workaround, minor data display error |
| P4 - Low | Cosmetic, enhancement, minor inconvenience | Within a week | Typo in UI, feature suggestion, documentation gap |
Adjust priority upward for:
- Enterprise or high-ARR accounts (one tier bump).
- Issues affecting multiple customers (one tier bump).
- Approaching or breached SLA (one tier bump).
- Security-related concerns (minimum P2).
Step 4: Route to Team
Determine the right team based on category and required expertise:
| Category | Primary Team | Escalation Path |
| Bug (reproducible) | Engineering | Engineering Lead |
| Bug (intermittent) | Support L2 | Engineering |
| Feature request | Product | Product Lead |
| How-to question | Support L1 | Support L2 |
| Billing/account | Billing | Finance |
| Security concern | Security | CISO |
| Integration issue | Integrations | Engineering |
| Data request | Support L2 | Data Engineering |
Step 5: Produce Triage Summary
Document the triage decision for the ticket record.
Output Format
## Triage Summary
**Ticket**: <ID>
**Received**: <date/time>
**Customer**: <name> | <tier>
### Classification
- **Category**: <category>
- **Product Area**: <feature/module>
- **Priority**: P1 / P2 / P3 / P4
- **Priority Rationale**: <why this priority level>
### Duplicate Check
- **Duplicates found**: Yes / No
- **Related tickets**: <IDs or "none">
- **Known issue**: <bug ID or "none">
- **KB article**: <link or "none">
### Routing
- **Assigned to**: <team>
- **Reason**: <why this team>
- **SLA target**: <response time based on priority>
### Quick Summary
<1-2 sentence description for the receiving team>
### Recommended Action
<specific next step: respond with KB link, investigate, escalate, merge with existing>Examples
User: "Triage this: customer says their dashboard shows wrong numbers since yesterday" Action: Classify as bug, check for known data issues, assign P2 for data accuracy, route to engineering, check for similar reports.
User: "New ticket from Acme Corp -- they want to export data in Parquet format" Action: Classify as feature request, assign P4, route to product, note the enterprise tier for prioritization context.
User: "Is this a dup? Customer can't log in with Google SSO" Action: Search for open SSO tickets and known auth issues, determine if this matches an existing problem, link or create new based on findings.
Best Practices
- Triage quickly. The goal is fast, accurate routing -- not solving the problem at this stage.
- Check for duplicates before assigning priority. If 10 customers reported the same issue, it may already be tracked as a P1.
- Include the priority rationale so reviewers can adjust without re-investigating.
- Do not over-prioritize. If everything is P1, nothing is. Reserve critical priority for genuine production-impacting issues.
- When in doubt between two priority levels, consider the customer tier and whether a workaround exists.
- Tag tickets consistently with category and product area to enable reporting and trend analysis.
- For ambiguous tickets, ask one clarifying question rather than guessing incorrectly and misrouting.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

