Skip to content

Retailer-Specific Assortment Tailoring

Reshape a national range to fit one retailer's shopper and banner.

What is the Retailer-Specific Assortment Tailoring?

Retailer-Specific Assortment Tailoring is a free AI skill that adapts a food and beverage brand's national range to fit one specific retailer's shopper profile and banner positioning. You give it your full SKU range, the retailer's banner identity and shopper base, and any performance data you have there; it returns a must-win core, the SKUs to hold back or resize, price and pack adjustments that match the banner's price posture, and a range narrative that reads as built for that retailer rather than distributed to it. It is built for category managers and account teams who submit the same range list to every buyer and wonder why a discount-banner buyer and a premium-banner buyer both push back. Because it forces every SKU to earn its place against one specific shopper, not an average national shopper, the resulting range survives the buyer's own scrutiny. Grounding the fit logic in live food and beverage demand data sharpens which items this retailer's actual shoppers are already reaching for.

Who it's for

  • Category managers building a range proposal for one specific banner
  • Account managers whose retailer pushes back on a generic range list
  • Sales teams tailoring the same brand differently across retail partners
  • Founders preparing their first retailer-specific pitch beyond their home channel

What you get

  • A must-win core SKU list specific to this retailer's shopper
  • The SKUs to hold back, resize, or reposition for this banner
  • Price and pack adjustments matched to the banner's price posture
  • A range narrative framed around this retailer's shopper, not the national average
  • A side-by-side comparison of your national range versus the tailored version
  • Talking points for why the tailored range serves their shopper better

How to use it

  1. 1Copy the prompt into ChatGPT, Claude or Gemini.
  2. 2Fill the bracketed inputs (full range, retailer, banner and shopper notes).
  3. 3Answer its clarifying questions about performance data and price posture.
  4. 4Ask it to show the side-by-side comparison against your full national range.

See it in action

Example input

Our brand 'Solano Sparkling' sells 14 flavored sparkling water SKUs nationally at a $1.79 average price. We're pitching a fictional upscale regional grocer, 'Ferncrest Markets,' whose shopper is health-focused and not price-sensitive, but their sets only carry 6-8 sparkling water SKUs per brand. We need to pick which 6-8 travel and how to price them for that banner.

Example output

Tailored range for Solano Sparkling at Ferncrest Markets:

Must-win core (6 SKUs)
Lead with your least-sweet, most ingredient-forward flavors — Ferncrest's shopper reads sparkling water as a better-for-you swap, not a soda replacement, so flavors closest to "flavored seltzer" win over anything reading as candy-adjacent. Recommend: Grapefruit, Cucumber Mint, Yuzu, Black Cherry, Lime, and Ginger. These are the flavors most likely to already show up in this shopper's other purchases — validate against your own SKU-level velocity if you have any comparable premium-grocery data.

Hold back for now (5 SKUs)
Your sweeter, dessert-adjacent flavors — Root Beer, Cream Soda, and similar — are grocery mainstream sellers but read as a mismatch for a health-focused shopper base. Hold these out of the initial pitch; reintroducing them later as a "trial" addition is easier than defending them in the first meeting.

Watch list (3 SKUs)
Tropical and fruit-punch-style flavors could go either way depending on how Ferncrest's actual shopper skews — flag these as the ones to test locally rather than assume.

Price and pack fit
Ferncrest's shopper is not price-sensitive, which is an opportunity, not a reason to leave price where it is. Consider whether a premium single-can price or a distinct multipack size signals quality here rather than defaulting to your national $1.79 price point. A slightly higher price at Ferncrest, positioned correctly, likely reads as confirmation of quality rather than a barrier — assumption to validate with Ferncrest's own category pricing data if you can get it from the buyer.

Range narrative
Position the six-SKU set as "the ingredient-forward half of our range, curated for shoppers who already read labels" rather than "our smaller assortment." Buyers respond better to a range that sounds deliberately curated than one that sounds trimmed down from something bigger.

Talking points for the buyer meeting
- This isn't our starter range — it's the six flavors your shopper is most likely to already want, chosen using our full national sales picture.
- We held back the sweeter flavors because they don't fit your set's positioning, not because we ran out of good ideas — that's a category-fit decision, not a limitation.
- We'd like a 12-week read on the watch-list flavors once the core six prove out, rather than asking you to gamble on all nine at once.

National range vs tailored range
Your full 14-SKU range remains available for other channels; this tailoring is specific to Ferncrest's shopper and shelf reality, not a change to your overall lineup.

Open question to resolve before the pitch
Confirm whether Ferncrest's 6-8 SKU slot count is a hard ceiling or a starting point for negotiation — that changes whether you lead with six or stretch to eight including one watch-list flavor.

Want me to turn the must-win core into a one-page range proposal formatted for the buyer meeting?

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 strategist who tailors national food and beverage ranges for individual retail banners. You refuse to submit the same range list to every buyer — a range built for one retailer's actual shopper always beats one distributed to them by default.

# Context I'll provide
- My full national range: [FULL RANGE — SKUs, prices, pack sizes]
- Target retailer and banner positioning: [RETAILER + BANNER — price posture, shopper description]
- What I know about their shopper base: [SHOPPER NOTES e.g. demographics, values, price sensitivity]
- Shelf or set constraints: [CONSTRAINTS e.g. number of SKU slots, set size]
- Performance data at this or similar retailers (optional): [PERFORMANCE DATA]

# Your task
1. If my full range, the retailer's shopper profile, or set constraints are missing or vague, ask up to 3 clarifying questions BEFORE writing anything.

Frequently asked questions

What is retailer-specific assortment tailoring?
Retailer-specific assortment tailoring is the practice of adapting a brand's full national product range to fit one retailer's shopper base and banner positioning, rather than submitting the same SKU list everywhere. It decides which items are must-win for that shopper, which to hold back, and how price and pack should shift to match the banner's posture. This skill builds that tailored range plus the buyer-facing narrative behind it.
How is this different from the Category Trend Localizer skill?
The Category Trend Localizer takes specific food and beverage trends and adapts their expression — flavors, formats — for one retailer's shopper. This skill works at the range level: it screens your entire existing SKU lineup, not a set of trends, and decides which items are must-win, which to hold back, and how price and pack should shift for that banner. Use the localizer for trend-led range additions, this skill for the whole-range fit exercise.
Does this work with ChatGPT, Claude and Gemini?
Yes — the prompt is model-agnostic and runs in any capable chat model. Account teams managing several retail partners often save it as a Custom GPT or reusable skill so every retailer gets a range built for their shopper instead of a copy-pasted list.
What if I don't have shopper data for this retailer?
Give it whatever you know directionally — the banner's general positioning, price posture, and any impressions from store visits or the buyer relationship. The skill will build the tailoring logic from what you provide and flag every shopper-fit claim as an assumption to validate, rather than inventing demographic or purchase data you don't have.

Related skills

Want the live data behind sharper outputs?

These skills get better with real-time F&B intelligence. See what Tastewise can do for your team.