# SKILL: Product Feedback Synthesiser

## Purpose
Cluster messy product feedback into themes, evidence, customer segments, severity, and roadmap implications.

## When to Use
Use this when the user needs to: Cluster messy product feedback into themes, evidence, customer segments, severity, and roadmap implications. It is designed for repeatable agent or automation work, not one-off fluffy prompting.

## Inputs Required
- Feedback dataset
- Product area
- User segment field
- Time period
- Decision needed

## Workflow
1. Deduplicate similar feedback
2. Cluster by customer need rather than wording
3. Estimate severity and reach from evidence
4. Separate bugs, requests, confusion, and praise
5. Recommend next research or roadmap action

## Output Format
Feedback synthesis table with themes, evidence, impact, confidence, 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 Product Feedback Synthesiser and return the expected output structure plus any missing inputs.