Space Productivity Analyzer

What you need to provide

The prompt asks for 6 inputs. Have these ready before you paste it in:

1. 1Category + Set Size — 12-foot refrigerated dressing set
2. 2Your Facings/Space + Sales/Velocity Notes
3. 3Section Performance — paste any productivity data you have
4. 4Margin Notes — directional is fine
5. 5The Ask — 8 more facings, eye-level move, second placement
6. 6Retailer + Reset Date

How to use it

1. 1Copy the prompt into ChatGPT, Claude or Gemini.
2. 2Fill the bracketed inputs (your space, sales, margin, category context).
3. 3Answer its clarifying questions about fixture and data availability.
4. 4Ask it to pre-empt the buyer's three likeliest objections.

See it in action

Space case for Zest & Zing — refrigerated dressings:

Productivity framing
- Lead with the ratio: your share of section sales versus your 4-of-48 share of facings. If sales share runs meaningfully higher, every under-faced SKU is money the fixture leaves on the table. Pull the exact figures from your velocity data before the meeting.

Elasticity logic, buyer language
- 'Our facings run out before the weekend — added facings capture sales currently lost to gaps; they don't just move volume sideways.' Out-of-stock timing evidence makes this concrete.

Scenario builds
1. Eight facings from the section's bottom-decile performers — the full ask, backed by a transfer-of-space productivity comparison.
2. Four facings plus an eye-level relocation — smaller footprint, similar impact, easier yes.
3. A 12-week test in 20 stores — the risk-reversal option that converts a hesitant buyer.

Where the space comes from
- Name donor SKUs by productivity rank, not by competitor grudge; the buyer must see category logic.

Buyer economics
- Frame each scenario as section dollars per foot, before and after — label projections as assumptions to validate in the test.

Want the one-page version formatted for the reset meeting?

The prompt

This is the actual prompt, not a teaser. Read the opening below, then unlock the free bundle with your email for the full version plus the installable Claude Skill and Custom-GPT instructions.

# Role
You are a senior space-planning strategist who has argued shelf-space cases through hundreds of resets. You think in sales and profit per linear foot — the buyer's currency — and you refuse to bring a space ask that does not name where the space comes from.

# Context I'll provide
- Category and set: [CATEGORY + SET SIZE e.g. 12-foot refrigerated dressing set]
- My brand's current space and performance: [YOUR FACINGS/SPACE + SALES/VELOCITY NOTES]
- Category and competitor context: [SECTION PERFORMANCE — paste any productivity data you have]
- Margin picture, mine and the category's (optional): [MARGIN NOTES — directional is fine]
- The ask I want to make: [THE ASK e.g. 8 more facings, eye-level move, second placement]
- Retailer and reset timing: [RETAILER + RESET DATE]

# Your task
1. If my current space, performance evidence, or the ask itself is missing or vague, ask up to 3 clarifying questions BEFORE writing anything.
2. Build the productivity framing: my share of section sales and profit versus my share of space, and what that gap means in fixture dollars.

What's in the free download

Frequently asked questions

What is space productivity in retail?

Space productivity measures the sales and profit a product or brand generates per unit of shelf space — usually per linear foot or per facing — compared with the section average. When your share of sales exceeds your share of space, you have an under-spaced case. This skill turns that gap into scenarios and buyer economics for a reset conversation.

What data do I need before using it?

At minimum: your facings count, the section size, and your sales or velocity versus the section. Better still: margins and out-of-stock timing. The skill builds the argument structure with placeholders wherever a real number belongs, so you can see exactly which figures to pull rather than guessing at the math.

Which AI chatbots support this skill?

All the major ones — the prompt is model-agnostic and runs in ChatGPT, Claude, or Google Gemini without changes. If your sales team makes space asks often, save it as a Custom GPT or Claude Skill so every reset argument arrives in buyer currency.

What mistakes does this help avoid?

The big ones: asking for space without naming donor items, arguing brand merit instead of fixture economics, quoting velocity without converting it to per-foot terms, and bringing only the maximal ask. Each pattern hands the buyer an easy no. The skill forces donor logic, buyer currency, and a testable fallback into every space case.