New Item Ranging Recommendation
Recommend the exact new SKUs to add for your next reset, with rationale.
What is the New Item Ranging Recommendation?
The New Item Ranging Recommendation skill is a free AI skill that recommends specific new SKUs to add to a category range ahead of an upcoming reset. You give it your current range, the reset's goals, the candidate items or gaps under consideration, and any shopper or trend context you have; it returns a ranked shortlist of SKUs to add, a rationale for each covering fit, incrementality, and risk, and a view of which existing items each new SKU pairs with or could pressure. It is built for category managers and buyers who already know a reset is coming and need to move from open range questions to a defensible, specific ranging call. Because every recommendation states its incrementality case and its risk to the existing range, the shortlist survives a buyer's first hard question instead of reading as a wish list. Pairing the shortlist with live food and beverage demand data confirms which candidate SKUs are riding real, current demand rather than a trend that already peaked.
Who it's for
- Category managers finalizing which SKUs to add at an upcoming reset
- Buyers evaluating supplier ranging proposals against a set of gaps
- Suppliers building the specific SKU ask for a category review
- Assortment planners converting whitespace findings into a ranging decision
What you get
- A ranked shortlist of specific SKUs to add
- A fit and incrementality rationale for each recommended SKU
- A risk read: cannibalization or halo effect on existing items
- Suggested facings or space allocation per new SKU
- A backup list of near-miss candidates and why they didn't make the cut
- A one-paragraph ranging rationale for the buyer meeting
How to use it
- 1Paste the prompt into ChatGPT, Claude or Gemini.
- 2Fill the bracketed inputs (current range, reset goals, candidate SKUs or gaps).
- 3Answer its clarifying questions about space available and must-protect items.
- 4Ask it to build the buyer-facing one-pager for the top recommendation.
See it in action
Example input
Category: frozen plant-based entrees at Meadow Market, 9-foot freezer set. Brand: fictional 'Solstice Foods' has a 9-SKU portfolio and can add up to 3 new SKUs at the January reset. Candidates under consideration: a spicy noodle bowl, a breakfast burrito, and a family-size lasagna. We know bowls are our best-performing format and breakfast is underdeveloped in the set.
Example output
Ranging recommendation — Solstice Foods, 3 new SKUs for the Meadow Market January reset: Recommended #1: Spicy Noodle Bowl Fit: extends your best-performing format (bowls) into a flavor territory — spicy/Asian-inspired — that is thin in Meadow Market's current plant-based set. Incrementality: high. This is a new occasion (spicy craving) more than a new format, which limits cannibalization of your existing bowl SKUs. Risk: modest overlap with your existing Teriyaki Bowl on the shelf edge; recommend facings that keep them visually separated by flavor cue, not size. Space: 2 facings, positioned next to the existing bowl block. Recommended #2: Breakfast Burrito Fit: breakfast is the gap you named, and it is a genuine white space in the set today — no plant-based breakfast item currently ranges here. Incrementality: high, because it opens a new day-part rather than competing within dinner occasions. Risk: lowest of the three candidates; nothing in your current 9-SKU range serves this day-part, so there is no internal SKU to cannibalize. Space: 2 facings, placed near any existing frozen breakfast set if Meadow Market carries one, or at the entrance to your block if not. Recommended #3: Family-Size Lasagna Fit: adds a sharing/family occasion your bowl-and-single-serve-heavy range doesn't currently serve, which supports basket size and multi-person households. Incrementality: medium — some of this demand may currently go to your existing single-serve lasagna-adjacent SKU if you have one; treat this as a genuine open question rather than a settled fact. Risk: family-size formats carry higher price points and slower velocity per unit; recommend a 12-week sales check-in before assuming permanence. Space: 2 facings. Not recommended this cycle: none of the three above were dropped, since all three fit within your 3-SKU allowance — but if forced to cut one, drop the Family-Size Lasagna first. Its incrementality case is the least certain of the three, and it carries the most execution risk (price point, velocity). Facing and space allocation Total ask: 6 new facings across 3 SKUs, which should come from consolidating your two lowest-velocity existing SKUs to single facings rather than from Meadow Market's total freezer footage — bring the donor-space logic into the same conversation as the ranging ask. Backup candidates None were in your original list beyond the three considered, but if Meadow Market pushes back on the Lasagna, a smaller sharing-format side dish would be the next best test of the family occasion without the price-point risk. Buyer rationale, one paragraph Solstice Foods is proposing three additions for the January reset: a Spicy Noodle Bowl that extends our strongest format into an underserved flavor space, a Breakfast Burrito that opens a genuine white-space day-part in your plant-based set, and a Family-Size Lasagna that tests the sharing occasion. All three are designed to grow the category rather than reshuffle it — the Breakfast Burrito in particular has no internal competitor to cannibalize. We're proposing the six new facings come from consolidating our two slowest current SKUs, not from your total freezer footage. Want me to build the one-page version of this for the January reset meeting, with a facings diagram?
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 and assortment strategist who recommends specific new SKUs for retail resets, not general range advice. You rank every candidate on fit, incrementality, and risk, and refuse to recommend an item just because it is available or trending. # Context I'll provide - Category and current range: [CATEGORY + CURRENT SKUS] - Retailer, fixture size, and reset timing: [RETAILER + FIXTURE + RESET DATE] - How many new SKUs can realistically be added: [SKU ALLOWANCE] - Candidate SKUs or known gaps under consideration: [CANDIDATES / GAPS] - What you already know about demand or shopper need (optional): [DEMAND NOTES] - Must-protect existing SKUs (optional): [PROTECTED SKUS] # Your task
Frequently asked questions
- What is a new item ranging recommendation?
- A new item ranging recommendation is a specific, per-SKU decision about which new products to add to a category's range at an upcoming reset — as opposed to a general range strategy. This skill evaluates candidate SKUs on fit, incrementality, and cannibalization risk, then returns a ranked shortlist with the rationale and space allocation a buyer can act on directly.
- How is this different from the Assortment Gap Finder skill?
- The Assortment Gap Finder identifies the whitespace in a range — the gaps, missing formats, or underserved occasions a category should address, without naming specific products. This skill goes a step further: it takes candidate SKUs or known gaps and recommends the actual items to add for a specific upcoming reset, ranked with a rationale and space allocation. Use the gap finder to find the whitespace, then this skill to decide exactly what fills it.
- Which AI tools can run this prompt?
- Any capable chat model — ChatGPT, Claude, or Google Gemini. It's model-agnostic plain text, so paste it directly, save it as a Custom GPT, or store it as a reusable skill so every reset cycle produces ranging recommendations in the same structured format.
- What if I don't have hard data on the candidate SKUs yet?
- Give it whatever you have — even directional notes on which candidates you suspect are strongest — and it will build the fit and incrementality case around that, flagging every claim it cannot support as an assumption to validate. It will not invent trial rates, sales projections, or market sizing on your behalf; the ranking logic works even with thin data, but the confidence of each recommendation will reflect what you actually provided.
Related skills
Allergen-Free Adaptation Planner
Plan a free-from adaptation that survives QA and labeling review.
Get it freeAssortment Gap Finder
Find the SKUs your shelf is missing before a buyer does.
Get it freeBrand Architecture & Portfolio Strategy
Structure a master brand, sub-brands and endorsements across your portfolio.
Get it freeWant the live data behind sharper outputs?
These skills get better with real-time F&B intelligence. See what Tastewise can do for your team.