100 Best Claude Excel Data Analysis Prompts for Fashion Boutiques

Direct Answer

The best Claude prompts for Excel data analysis for fashion boutiques are designed to extract actionable insights from sales, inventory, pricing, and promotion data. They cover categories, SKUs, seasons, channels, and vendor performance, delivering structured outputs ready to paste into Excel tables or charts.

Introduction

This page curates a practical prompt library of Claude prompts focused on Excel data analysis for fashion boutiques. It helps owners, merchandisers, and analysts extract precise metrics, optimize inventory, and improve merchandising decisions.

Use these prompts to standardize analysis, accelerate reporting, and scale data-driven decisions across a small boutique or a growing fashion brand.

How to Use These Claude Prompts

• Replace placeholders like [season], [store], or [vendor] with your actual data ranges and labels.
• Add constraints such as date ranges, currency, or margin thresholds to tailor outputs.
• Request specific formats like tables, CSV-ready blocks, or bullet-point summaries to fit your workflow.
• Ask Claude to provide validation steps or checkpoints to verify outputs against your data.
• When needed, pair prompts to compare scenarios, such as promotions vs baseline periods, to quantify impact.

100 Best Claude Excel Data Analysis Prompts for Fashion Boutiques

1. Sales by item category: You are a data analyst for a fashion boutique. Analyze the Excel dataset of sales transactions to determine annual revenue by item category. Use filters for date range, and group by category with the following outputs: total units sold, total revenue, average price, and top 5 best selling SKUs. Output in a clean table with header row and clear footnotes.
2. Best selling SKUs by season: Act as an Excel data analyst for a fashion retailer. From the sales table with fields date, SKU, category, price, and quantity, compute top 10 SKUs by revenue per season. Include season definitions, seasonal delta versus previous year, and a chart-friendly summary in a markdown-like table with columns: SKU, season, units, revenue, price, decline/gain.
3. Inventory turnover ratio: In the role of a fashion boutique data analyst, calculate inventory turnover ratio by SKU using current stock and last 12 months cost of goods sold from the provided Excel workbook. Deliver a ranking of SKUs by turnover, identify slow movers, and propose action steps. Provide the final results in a sortable CSV-ready block.
4. Gross margin by vendor: You are an analytics assistant for vendor profitability. Using Excel data for sales by vendor, cost of goods sold, and discounts, compute gross margin by vendor for the last fiscal year. Include margin percentage, revenue, and recommended pricing adjustments. Present as a compact table and a one-line executive summary.
5. Price elasticity proxy: As an Excel analyst for a fashion boutique, estimate price elasticity using historical price changes and quantity sold by SKU. Compute elasticity for each SKU over the last 24 months, flag SKUs with elasticity magnitude greater than 1, and suggest pricing experiments. Deliver results as a table with SKU, elasticity, and suggested price ranges.
6. Markdown optimization plan: Act as a data analyst for merchandising. Given current markdown data, seasonality, and sell-through rates, create an optimization plan to reduce markdown depth by 15 percent while maintaining margin. Provide a prioritized list of SKUs with proposed markdown timing, expected impact, and risk notes in a table.
7. Store performance comparison: You are an analytics consultant for multi-store fashion brand. Compare monthly sales, unit volume, and average order value across all stores for the last year. Normalize by store size, identify top performing stores, and highlight outliers. Output a comparative chart-ready summary and a quick bullet list of factors driving performance.
8. Seasonal demand forecast: As an Excel analyst, generate a 12-week demand forecast for the upcoming fashion season using historical weekly sales, promotions, and holidays. Use a simple moving average and exponential smoothing approach, provide confidence intervals, and present forecast by week in a clean table.
9. AOV uplift by segment: Act as a data analyst. Segment customers by loyalty tier and vehicle of purchase, then compute average order value by segment for the last 12 months. Identify segments with highest AOV and propose targeted offers. Deliver a ready-to-paste Excel section with labeled columns.
10. Stockout risk heatmap: You are an inventory analyst. Build a risk heatmap showing stockout probability by SKU based on lead time, demand variability, and current on-hand. Include color-coded risk levels and recommended replenishment actions. Output as a grid with SKU, risk, and action.
11. Vendor lead time insights: As a procurement analyst, analyze vendor lead times using a dataset of purchase orders. Compute average lead time by vendor, median, and variability. Flag vendors with consistently long lead times and propose mitigation actions. Present results in a concise table and a one-line takeaway.
12. SKU profitability drilldown: Act as a fashion retailer data analyst. For each SKU, compute gross profit, gross margin, and contribution margin using sales, cost, discounts, and freight data. Rank SKUs by profitability, flag outliers, and suggest optimization opportunities. Output as a tabular report.
13. Open-to-buy planning: You are an inventory planner. Based on current inventory levels, forecasted demand, and season length, calculate open-to-buy for the next quarter. Provide a step-by-step calculation with assumptions, and deliver a ready-to-use Excel-ready worksheet.
14. Promotions impact analysis: As a promotions analyst, evaluate the impact of recent marketing promotions on revenue and units sold. Compare pre-promo, promo, and post-promo periods, control for seasonality, and deliver a summarized impact with actionable recommendations. Output as a compact table and a bullet list.
15. SKU assortment gap: Act as a merchandising analyst. Using current assortment and sales data, identify gaps where high-potential categories lack breadth of SKUs. Propose new SKUs with expected impact and rationale in a prioritized list. Provide an Excel-ready row for each SKU.
16. Cost per unit trending: You are a cost analyst for a boutique. Track cost per unit across suppliers over the last 12 months, compute trend lines, and identify increasing cost risks. Deliver a table with SKU, supplier, current cost, trend, and recommended action.
17. Sell-through by channel: As an analytics assistant, break down sell-through by channel (online, in-store, wholesale) for the last season. Compute sell-through rate by channel, highlight underperforming channels, and suggest optimization steps. Present results in a compact table.
18. Customer lifetime value: Act as a data scientist for a boutique. Using purchase history, recency, frequency, and monetary value, estimate customer lifetime value segments over the next 12 months. Provide a table of CLV by segment and recommended retention tactics.
19. Seasonal markdown timing: You are a merchandising analyst. Determine optimal markdown timing by season to maximize margin and minimize leftover stock. Use sell-through data and lead times to propose a markdown calendar. Output as an ordered list of SKUs with timing windows.
20. Price tier mapping: As a pricing analyst, map SKUs to price tiers based on historical price bands and demand. Produce a tier map with thresholds, sample SKUs per tier, and recommended pricing guardrails. Deliver an Excel-ready mapping table.
21. Stock cover period: Act as an inventory planner. Calculate stock cover period by SKU using current on-hand and average daily demand. Rank SKUs by longest cover and propose reorder priorities. Output as a simple table.
22. Discount saturation risk: You are a data analyst. Measure discount depth and frequency over the last year by channel. Identify diminishing returns on discounts and provide alternative promotions. Deliver a table and a one-line conclusion.
23. Return rate drivers: As a boutique analyst, analyze return rates by category and reason code. Identify top drivers of returns, quantify financial impact, and suggest mitigation actions. Provide a dashboard-ready table and a short executive note.
24. Inventory aging analysis: Act as an inventory analyst. Classify on-hand inventory by aging bins (0-30, 31-90, 91-180, 181+ days). Highlight stale stock and propose clearance actions with a prioritized list. Output as a table.
25. Seasonal risk scoring: You are a risk analyst for merchandise. Create a seasonal risk score by product line based on historical volatility, supplier risk, and demand variability. Rank lines by risk and suggest contingency steps. Provide a compact scoring table.
26. Profitability by category: As a category analyst, compute profit contribution by category for the last fiscal year using sales, cost of goods sold, discounts, and transfers. Rank categories by profit and propose mix adjustments. Provide a neat table.
27. Forecast accuracy check: Act as a forecast analyst. Compare actuals vs forecast for the last six months by product line. Compute accuracy metrics (MAPE, bias) and recommend improvements. Output a small table and a one-line summary.
28. Vendor performance score: You are a vendor analyst. Create a performance scorecard by vendor using on-time delivery, defect rate, and pricing compliance. Deliver a concise table and a short recommendation paragraph.
29. Payback period estimates: As a financial analyst, estimate payback period for inventory replenishment projects using expected margin uplift and investment cost. Provide per-SKU calculations and a summary.
30. Customer segmentation map: Act as a data strategist. Build a segmentation map from purchase history for clustering by RFM. Output segment labels, key traits, and recommended targeting actions in a ready-to-use table.
31. Sales funnel leakage: You are a performance analyst. Identify where in the funnel customers drop off (visits to purchases) from channel data. Quantify leakage by stage and propose conversion tactics. Present results in a short table.
32. Promotional lift by SKU: As a promotions analyst, calculate lift per SKU during promotions compared to non-promo periods. Normalize for seasonality and visibility. Provide a table of SKU, promo period, lift, and percentile rank.
33. Product life cycle signals: Act as a product analyst. Identify life cycle signals for fashion items based on sell-through, time since launch, and replenishment history. Deliver a list of SKUs with life-cycle stage and recommended actions.
34. Channel mix optimization: You are a channel strategist. Compute revenue share by channel and optimize mix to hit targets. Include scenario analysis for shifting 5 percent from one channel to another. Output a compact plan.
35. Loyalty impact analysis: As a loyalty analyst, quantify how loyalty program enrollment correlates with average order value and repeat purchases. Provide a CSV-ready table of cohorts and recommended program tweaks.
36. SKU restock frequency: Act as an inventory planner. Determine optimal restock frequency per SKU to balance stockouts and carrying costs. Deliver a table with SKU, suggested frequency, and rationale.
37. Seasonal inventory balance: You are an inventory analyst. Build a balance sheet-style view of inventory by season, showing old season carryover and new season forecast. Propose transfer or markdown actions with a prioritized list.
38. Cost-to-serve analysis: As a profitability analyst, compute cost-to-serve by customer channel and fulfillment option. Include picking, packaging, and shipping costs. Provide a brief actionable table and a rationale.
39. SKU clustering for merchandising: Act as a merchandising scientist. Cluster SKUs by sales velocity, margin, and seasonality. Produce cluster labels and recommended assortments per cluster in a table.
40. Basket analysis: You are a retail data analyst. Run a market basket analysis on transaction data to identify common SKU combinations. Output top 5 bundles with expected uplift and recommended cross-sell actions.
41. Competitive benchmarking: As a competitive analyst, compare your boutique’s key metrics to a peer group (revenue per store, AOV, sell-through). Provide a table of gaps and actionable benchmarking steps.
42. Markdown optimization scenarios: Act as a merchandising analyst. Create three markdown scenarios with different depth, timing, and product focus. For each scenario, forecast revenue impact and margin. Present as a compact comparison table.
43. New product viability: You are a product analyst. Assess the viability of a new product line using projected demand, margin, and cannibalization risk. Deliver a decision-ready summary with a data-backed go/no-go recommendation.
44. Returns cost analysis: As an operations analyst, quantify the total cost impact of returns by product and channel. Include restocking, processing, and loss. Propose reduction strategies and present as a table.
45. Store-level heatmap: Act as a data visualization assistant. Create a store-level performance heatmap showing revenue, units, and AOV. Include a short interpretation and recommended actions.
46. SKU attribute impact: You are a product analytics specialist. Analyze how core SKU attributes (color, size, material) influence sales velocity. Deliver a table of attributes with lift and confidence estimates.
47. Inventory write-off risk: As an inventory controller, identify items at high risk of write-off due to age, damage, or obsolescence. Propose action steps and a liquidation plan in a brief table.
48. Pricing sensitivity map: Act as a pricing analyst. Build a map showing price bands versus demand levels and elasticity for top 50 SKUs. Provide recommended price zones and guardrails in a compact table.
49. Cash flow impact: You are a financial analyst. Model how inventory levels influence monthly cash flow, including payable timing and carrying costs. Output a short table and a one-line takeaway.
50. Seasonal buy plan: As an inventory planner, create a seasonal buy plan for the next season using forecasted demand, safety stock, and lead times. Deliver a structured Excel-ready worksheet with calculations.
51. Wastage and overstock analysis: Act as a stock controller. Identify overstock risks leading to obsolescence and propose actions to minimize waste. Provide a table with items and recommended actions.
52. Promotions scheduling: You are a promotions planner. Create a promotions calendar aligned with seasonal peaks, ensuring non-conflicting campaigns. Provide timing, target SKUs, and expected impact in a table.
53. SKU deselection risk: As an assortment analyst, flag low-performing SKUs for potential removal. Provide rationale, expected impact on margins, and a transition plan. Output a concise list with data-backed notes.
54. Sales seasonality index: Act as a data analyst. Compute a seasonality index by product category to compare year-over-year performance. Deliver a table with seasonality score and recommended actions.
55. Gift card impact: You are a revenue analyst. Estimate the impact of gift card promotions on revenue and churn. Provide a table with incremental revenue and suggested strategies.
56. Product return reasons: As a customer insight analyst, categorize return reasons by product type and reason code. Quantify financial impact and propose design or sizing improvements. Output a table and short notes.
57. Sales by price tier: Act as a pricing analyst. Break down sales and revenue by price tier (low, mid, premium) for the last season. Identify tier performance and make recommendations. Deliver a clean table.
58. Foot traffic vs sales: You are a store performance analyst. Correlate foot traffic data with sales by hour and day for in-store. Provide insights and a table with correlation metrics.
59. Productivity by staff: As an operations analyst, measure sales per employee by store for the last quarter. Normalize for hours worked and staffing levels. Deliver a table and a short optimization plan.
60. Discount to margin bridge: Act as a finance analyst. Create a discount-to-margin bridge showing how each percentage point of discount affects gross margin. Provide a table with scenarios and recommendations.
61. Seasonal vendor mix: You are a procurement analyst. Analyze vendor mix by season and suggest adjustments to reduce risk and improve margins. Output a table with vendor share and recommended changes.
62. Channel ROI analysis: As a channel analyst, estimate return on investment by channel for marketing spend. Include attribution assumptions and a concise summary of top-performing channels.
63. Product launch forecast: Act as a product analytics lead. Forecast initial sales for a new product launch using simulating scenarios and baseline growth. Deliver a table with scenarios and projected week-by-week sales.
64. Stock replenishment rules: You are an inventory planner. Define simple restock rules based on safety stock, reorder point, and demand variability. Provide a ready-to-use Excel rule sheet.
65. Profit leakage audit: As a profitability auditor, identify areas where margins shrink across channels, seasons, or SKUs. Provide a prioritized list of fixes with expected impact.
66. Seasonal promotion sequencing: Act as a merchandising planner. Schedule promotions to optimize reader attention and avoid clustering. Provide a sequence with timing, channel, and SKUs in a table.
67. SKU replacement planning: You are a product planner. For aging or underperforming SKUs, propose replacement candidates with rationale and forecasted impact. Output as a list with data-backed notes.
68. Warehousing cost snapshot: As an operations analyst, summarize warehousing costs by SKU or product line and identify cost-saving opportunities. Deliver a compact table and a brief recommendation.
69. SKU health score: Act as a data scientist for merchandising. Compute a health score for each SKU based on velocity, margin, and age. Provide a ranked list and recommended actions per score.
70. A/B testing plan: You are a testing strategist. Design an A/B test for promotions or pricing with control and treatment groups, success metrics, and sample sizes. Provide a template you can paste into Excel.
71. Inventory risk dashboard: As a BI analyst, design a dashboard idea for inventory risk across categories. List metrics, data sources, and a sample layout in bullet form.
72. Cost saving opportunities: Act as a cost analyst. Identify potential cost reductions in sourcing, packaging, and shipping without harming product quality. Provide a prioritized list with expected impact.
73. Dynamic pricing cues: You are a pricing strategist. Propose dynamic pricing triggers based on stock level, demand, and seasonality. Outline rules and a sample calculation block for Excel.
74. SKU sleeve parity: As an assortment analyst, ensure size color parity across SKUs. Detect gaps where sizes or colors are missing and propose replenishment jobs. Output a concise corrective plan.
75. Low stock alert: Act as an inventory monitor. Create a low stock alert list for SKUs falling below a threshold, including reorder quantities and supplier contact notes. Deliver as a ready-to-import Excel sheet.
76. Seasonal revenue ladder: You are a revenue planner. Build a ladder of seasonal revenue milestones with targets and triggers. Provide a table mapping weeks to targets and actions.
77. Markdown vs. velocity: As a merchandising analyst, compare markdown depth against sales velocity to determine optimal markdown levels. Deliver a table with SKU, velocity, markdown, and recommended action.
78. Promotions risk gates: Act as a promotions risk manager. Define gates to approve promotions based on margin, lift, and cannibalization risk. Provide a decision checklist in a table.
79. Wasteful SKUs cleanup: You are a stock controller. Identify SKUs that incur high carrying costs but low turnover and propose removal or consolidation. Output a short list with rationale.
80. Cross-sell opportunities: As a customer analytics analyst, find cross-sell opportunities from transaction data. List top 5 bundles with expected incremental revenue and suggested merchandising placement.
81. Cost allocation by store: Act as a finance analyst. Allocate shared costs to stores proportionally and present a store-level net profitability table. Include a short commentary.
82. Sustainability impact: You are a sustainability analytics lead. Quantify the environmental impact of stock decisions (leftovers, markdowns) and propose greener actions. Provide a table of options and impact.
83. Promotions fatigue detection: As a marketing analyst, detect promotions fatigue by tracking discount frequency and redemption over time. Provide a table and recommended pacing strategy.
84. Store shadow analytics: Act as a store operations analyst. Compare on-paper store targets with actuals, flag gaps, and suggest corrective steps. Deliver a concise table.
85. SKU lifecycle reminders: You are a merchandiser. Create reminders for reordering, markdown, and phase-out based on lifecycle stage. Output as a calendar-ready list.
86. Regional demand mapping: As a regional analyst, map demand by geographic region and propose tailored assortments. Provide a table with region, demand, and recommended SKUs.
87. Pricing forecast accuracy: Act as a pricing forecast analyst. Compare price forecast accuracy over the last six months and identify drivers of error. Deliver a compact table and action items.
88. SKU cannibalization check: You are a product analyst. Analyze cannibalization between new SKUs and existing ones using sales data. Provide a table of overlaps and recommended assortment adjustments.
89. Productivity by category: As an operations analyst, measure output per hour by category and store. Normalize for staff and space. Deliver a table and optimization ideas.
90. Cash conversion cycle: Act as a financial analyst. Compute days inventory outstanding, days sales outstanding, and days payable outstanding for the last year. Provide a concise CCC table and recommendations.
91. Fleet merchandising plan: You are a merchandiser for a small boutique. Propose a 6-week merchandise plan focused on a subset of SKUs with high velocity and margin. Output a plan with weekly allocations.
92. Acquisition cost per customer: As a customer acquisition analyst, estimate cost to acquire customer by channel and compare to lifetime value. Provide a table and top optimization actions.
93. Returns refund policy impact: Act as a policy analyst. Model how different returns refund policies affect revenue and returns volume. Deliver a short table and recommended policy approach.
94. Sales anomaly detection: You are a data scientist. Implement a simple anomaly detection on weekly sales using z-scores, flag anomalies, and propose follow-up checks. Provide a result list and a sample Excel output.
95. Stock reallocation plan: As a stock planner, propose reallocating stock between stores to balance performance. Provide a transfer plan with quantities and timing.
96. Lifecycle promotions plan: Act as a merchandising planner. Tie promotions to lifecycle stages of products with a calendar and expected lift per stage. Output a table.
97. Vendor cost comparison: You are a procurement analyst. Compare vendor costs for similar SKUs and identify the best value options. Provide a decision-ready table and recommendation.
98. Return forecasting: As a forecasting analyst, predict monthly return volume for the next quarter using past seasonality and promotions. Deliver a table with forecast and confidence interval.
99. Data cleanliness checklist: Act as a data governance advisor. Provide a checklist to ensure Excel data quality for fashion boutique analytics, covering fields, formats, and validation rules. Output as a concise bulleted list.
100. Executive dashboard summary: You are a reporting analyst. Create an executive-ready dashboard summary outline for Excel data analysis in fashion retail, including key metrics, visuals, and storytelling notes. Provide a compact outline with sections and KPIs.

Best Practices

• Define a consistent data schema before running prompts to ensure outputs align across analyses.
• Limit outputs to a single, well-scoped task per prompt to maximize accuracy and reproducibility.
• Use versioned prompts and save successful configurations for reuse and auditing.
• Review Claude outputs for edge cases in seasonality or stockouts and iterate prompts accordingly.
• Combine multiple prompts to build a mini-analytics workflow that updates as your data evolves.

Common Mistakes to Avoid

• Using vague prompts that lack clear data fields or time ranges, causing ambiguous results.
• Overloading prompts with too many objectives, leading to partial or unfocused outputs.
• Ignoring data quality issues in your Excel sheets, which contaminates results.
• Not specifying output format or delivery style, making it hard to copy into dashboards.
• Relying on a single prompt for complex analyses that require multiple steps or checks.

FAQ

What is the purpose of these Claude prompts for fashion data analysis?

They provide clear, copyable instructions for Claude to analyze Excel data specific to fashion boutiques, delivering structured results you can paste into reports.

How do I adapt prompts to my data?

Replace placeholders like [date], [store], [SKU], and [vendor] with your actual column names and data ranges, and specify your desired outputs.

Can these prompts handle multi-store data?

Yes. Several prompts are designed to aggregate and compare data across multiple stores, channels, and time periods.

Do prompts require any special Excel features?

Most prompts rely on standard Excel features such as tables, pivot analysis, filtering, and basic formulas; complex charts can be added after producing the table.

How do I verify Claude outputs?

Cross-check results against a small, manual calculation or a lightweight Excel pivot to validate totals, ratios, and rankings.

Are these prompts suitable for beginners?

Yes, prompts include explicit steps and output formats, making them usable by beginners with basic Excel and Claude access.