# Find what drove my store's weekly sales result

Breaks a store's sales variance into traffic, conversion, ATV, and UPT, then gives specific actions for next week.

- Topic: Data & Analysis
- Framework: Few-Shot
- Level: Standard
- Tags: Sales, Analyze, Plan, Fill-in Template
- Source: https://www.thinkwithprompt.com/prompts/find-what-drove-my-store-s-weekly-sales-result

## Prompt

```text
Help me review my store's weekly sales performance.

**Store(s) and week:** [STORE NAME/NUMBER, WEEK ENDING]
**This week vs. last year and vs. plan:** [PASTE: net sales, traffic (door count), transactions, conversion %, average transaction value (ATV), units per transaction (UPT), returns, payroll hours]
**Category or department sales:** [IF AVAILABLE]
**Daily data:** [IF AVAILABLE - sales, traffic, and hours by day]
**What happened this week:** [weather, local events, promotions, staffing gaps, out-of-stocks, construction, competitor openings]
**Comp notes:** [e.g. "store remodeled last year - not comparable"]

Do this:
1. Break the sales variance into its drivers: traffic x conversion x ATV, and ATV into UPT x average unit retail. Show how much of the gap each driver explains.
2. Say which drivers the store team mainly controls (conversion, UPT, recovery, in-stock) and which it mostly does not (traffic, weather).
3. Calculate sales per labor hour and, with daily data, whether staffing matched traffic by day.
4. Flag anything odd: a return spike, a category far off trend, a day that broke pattern.
5. Recommend 2-3 specific actions for next week, each tied to a driver (e.g. "add a floor associate 4-7pm Saturday, where conversion dropped").

Return:
- A 5-line summary for my district manager.
- A driver table (driver, this year, last year, plan, impact on sales).
- The actions.
- Questions to ask my team.

Use only the numbers I provide. If something is missing, say what it would tell us.
```

## What to fill in

- STORE NAME/NUMBER, WEEK ENDING
- IF AVAILABLE
- IF AVAILABLE - sales, traffic, and hours by day
- e.g. "store remodeled last year - not comparable"

Free to copy and use. From ThinkWithPrompt (https://www.thinkwithprompt.com/), a library of 2,663 curated AI prompts.