mcpField
S
support-ticket-triage

support-ticket-triage

github.com/composio-communityProductivity17.1k570 installsUpdated 14w ago
Repository

About support-ticket-triage

Support Ticket Triage is a workflow for consistently classifying and responding to incoming support tickets. It guides ticket analysis, priority assignment, optional reply drafting, and internal follow-up notes.

Key features

  1. 01Parse issue and impact
  2. 02Assign categories and priority
  3. 03Draft replies on request
  4. 04Suggest internal follow-up
  5. 05Flag uncertainty and needed evidence

Use cases

  1. 01Classify incoming support tickets
  2. 02Prioritize tickets by severity
  3. 03Prepare customer reply drafts
  4. 04Route suspected issues for investigation

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/composio-community/awesome-codex-skills --skill support-ticket-triage

After installing, type/support-ticket-triagein Claude Code to confirm it loaded.

Details

From the project README

Support Ticket Triage

Standardize how to classify and respond to incoming tickets.

Inputs to gather

  • Ticket text (include attachments/links), product area, customer plan/tier if known.
  • Desired outputs: category taxonomy, priority levels, SLA hints, tone/brand voice, whether to draft a reply.

Workflow

  1. Parse context: identify issue type, product surface, severity, customer impact, reproduction hints, and blockers.
  2. Categorize: assign category and subcategory; set priority (e.g., P0–P3) with short justification.
  3. Draft response (if asked): concise acknowledgment, empathy, restate issue, next steps, and ask for missing info; include reproduction checklist when uncertain.
  4. Internal notes: suspected root cause, logs to pull, teams to loop, and tracking IDs to create/attach.
  5. Output: tabular or bullet summary with Category, Priority, Summary, Proposed Fix/Next Steps, Reply Draft.

Quality checks

  • Avoid promises; give ranges not exact ETAs unless provided.
  • Mask PII if copying to public channels.
  • If signal is weak, present 2–3 likely categories and what evidence would disambiguate.

Comments

Markdown supported