Category Trend Localizer

How to use it

1. 1Paste the prompt into ChatGPT, Claude or Gemini.
2. 2Fill the bracketed inputs (trends, retailer, region, category, shopper notes).
3. 3Answer its clarifying questions about the shopper base.
4. 4Ask it to build the buyer-facing slide for the strongest trend.

See it in action

Localization read for Bayou Best — fermented heat at a Texas grocer:

Trend-fit screen
- Heat itself needs no selling here — this shopper base already lives in chili formats. The localization question is the fermentation layer: frame it as depth of flavor and craft, not as a wellness abstraction.
- Fit verdict: adapt, don't transplant. Lead with familiar peppers (habanero, chile de arbol) in fermented form; hold the gochujang-forward SKUs for a later phase.

Local proof points to gather
- Store-level sales of adjacent fermented items (chili crisp, kimchi) at their locations.
- Local restaurant menus featuring fermented heat — bring examples from their trade area, not coastal ones.
- Social conversation from Texas metros; label anything national-only as an assumption to validate locally.

Ranged expression
- A 3-SKU fermented line anchored on familiar peppers, one accessible entry price point.

Merchandised expression
- An adjacency block next to established Mexican-heritage sauces, not a standalone trend section; recipe signage pairing with grilling occasions.

Timing
- Follow-fast posture: land it ahead of grilling season.

Want the one-slide buyer story with the coastal-thing objection answered?

The prompt

Here's the start of the prompt. Download the free bundle for the full, ready-to-paste version — plus the installable Claude Skill and Custom-GPT instructions.

# Role
You are a senior category consultant who localizes national food and beverage trends for regional retailers. You believe a trend without a local proof point is a rumor, and a trend without a ranged and merchandised expression is a slide — you refuse to present either.

# Context I'll provide
- The trend or trends: [TRENDS — name each one]
- Category: [CATEGORY]
- Retailer, region, and banner positioning: [RETAILER + REGION]
- What I know about their shopper base: [SHOPPER BASE e.g. demographics, price posture, missions]
- My brand's relevant range (optional): [YOUR SKUS]
- The meeting or decision this feeds: [DECISION CONTEXT e.g. line review, trend day, reset]

# Your task

Frequently asked questions

What is trend localization in category management?

Trend localization is the work of translating a national or global food trend into one retailer's reality: screening it against the banner's shopper base, gathering local proof points, and expressing it as concrete range and merchandising changes. This skill runs that translation so a trend arrives as a shoppable plan rather than an inspiration slide.

How is this different from the Trend Report Summarizer?

The Trend Report Summarizer condenses trend publications into the signals that matter for your business. This skill starts where that ends: you already believe the trend, and the job is landing it at one retailer — fit screening for their shoppers, local evidence, and the specific range and merchandising expression. Summarize nationally, then localize here.

Which AI models can I use it with?

Any capable chat model — ChatGPT, Claude, or Google Gemini — because the prompt is plain text and model-agnostic. Teams that manage many banners often save it as a Custom GPT or Claude Skill and rerun the same trend list per retailer to get differentiated local plans.

What local proof points count as evidence?

The strongest: sales of adjacent or precursor items in that retailer's own stores, trend items on menus in their trade area, and regional social or search conversation. The weakest: national statistics and coastal anecdotes. The skill builds the list per trend and flags must-have evidence, so you walk into the buyer meeting with local receipts.