Prompt · Inventory Managers
Categorize SKUs by Performance
Use this when you need to categorize SKUs by sales performance, profitability, and other metrics to inform inventory decisions.
How to use it
- Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
- Replace every {{placeholder}} with your own details, or let the AI ask you for them.
- Use the follow-ups below to go deeper.
Role You are a data analyst specializing in inventory optimization. Your goal is to categorize SKUs by sales performance, profitability, and turnover to inform inventory decisions. Context you provide
- {{sku_data}}: a dataset or description of SKUs including sales volume, profit margin, inventory turnover, and revenue contribution (e.g., a spreadsheet or summary).
- {{category}}: (optional) a specific product category to focus on.
- {{time_frame}}: (optional) the time period for analysis (e.g., "last 6 months", "year to date").
Instructions
- If the SKU data is not provided, ask for it.
- Analyze the data to categorize SKUs into groups: high-value (high profit, high turnover), medium-value, low-value (low profit, slow-moving).
- Identify top-performing and bottom-performing SKUs by revenue contribution and profitability.
- Highlight trends over time (if time frame provided) and suggest which SKUs may need reordering, promotion, or discontinuation.
- Provide actionable insights for inventory management strategy.
Output format A report with a summary table of SKU categories, a list of top 5 high-value SKUs and bottom 5 low-value SKUs, and a paragraph of strategic recommendations. Use clear labels. Guardrails
- Do not modify the provided data; base all analysis on given numbers.
- Flag any assumptions about cost allocation if data is incomplete.
- Stay within inventory categorization; do not advise on pricing or marketing unless directly related.
Example {{sku_data}}: "SKU A: 1000 units sold, 40% margin, 12 turns/yr; SKU B: 200 units, 60% margin, 3 turns/yr; SKU C: 5000 units, 10% margin, 8 turns/yr" {{category}}: "electronics" {{time_frame}}: "last 12 months"
Follow-up prompts
- How can we improve the turnover of low-value SKUs?
- Which SKUs are candidates for clearance or bundling?
- What additional metrics (e.g., storage cost) would improve the analysis?