# Skill Brief — Marketing

## Your Mission

Build a custom skill that automates the task you did manually in Workshop 1 or 3. Study the example skill in `example-skill/SKILL.md` first, then create your own.

## What to Build

**Skill name:** `campaign-review`
**Trigger words:** "campaign review", "campaign performance", "campaign report"

**Input:** CSV with campaign_id, channel, sent_count, open_rate, click_rate by country
**Output:** .docx performance report with recommendations

## Steps to Create

1. Run `/skill-creator` in Cowork
2. When asked for a name, enter: `campaign-review`
3. When asked what it does, describe: "Read content-pile data and produce a  report with priority categorisation"
4. When asked for constraints, include:
   - "Never fabricate data"
   - "Flag items with missing fields as NEEDS MANUAL REVIEW"
   - "Include a disclaimer that output requires human review"
5. Test against `test-input.xlsx` in this folder

## Helper Script

A helper script (`helper-script.ts`) is included. Your skill can call it for calculations:
- **What it does:** Takes open_rate + benchmark → outputs performance rating (above/below/at benchmark)
- **How to use:** `bun run helper-script.ts <arg1> <arg2>`

## Success Criteria

Your skill passes if:
1. It processes `test-input.xlsx` without errors
2. Output contains a summary table with correct counts
3. Priority categorisation matches the thresholds in the example skill
4. It handles the edge cases in `edge-cases.csv` gracefully (no crashes, flags issues)