# SKILL: Ticket Summariser Agent Skill

## Purpose
Summarise long customer threads into issue, customer impact, steps tried, evidence, current blocker, and next action.

## When to Use
Use this when the user needs to: Summarise long customer threads into issue, customer impact, steps tried, evidence, current blocker, and next action. It is designed for repeatable agent or automation work, not one-off fluffy prompting.

## Inputs Required
- Ticket thread
- Customer account notes
- Internal comments
- Known incidents

## Workflow
1. Separate customer statements from internal notes
2. Extract timeline and reproduction steps
3. Identify unresolved question
4. List action owner and next step
5. Flag sensitive or emotional content

## Output Format
Support handover summary with impact, evidence, blocker, and next action.

## Quality Rules
- Ground every claim in supplied inputs or clearly mark it as an assumption.
- Prefer specific fields, examples, and decision points over generic advice.
- Include a test command and pass criteria so the skill can be evaluated.
- Keep the output usable by a human first and automation-ready second.

## Guardrails
- Do not send emails, publish posts, contact leads, change calendars, spend money, delete data, or alter production systems without explicit human approval.
- Do not invent facts, private details, legal claims, prices, or external data.
- For web or profile research, use current sources and separate evidence from inference.
- For connected tools, use the minimum permission needed and log the action taken.

## Test Command
Run this skill on a simple example for Ticket Summariser Agent Skill and return the expected output structure plus any missing inputs.