Skip to content

Category Financial Forecast Narrative

Turn a category sales and margin forecast into a story buyers approve.

What is the Category Financial Forecast Narrative?

The Category Financial Forecast Narrative skill is a free AI skill that translates a food and beverage category's sales and margin forecast model into a narrative a retail buyer can actually approve. You paste your forecast numbers or model outputs, the time horizon, and the decision the forecast supports; it returns the story behind the numbers in plain language, the assumptions the forecast rests on stated explicitly, best-case and conservative scenarios with what separates them, the risks that could break the forecast, and the specific ask the narrative should end on. It is built for category managers and account leads who hand a buyer a spreadsheet and watch the meeting stall because nobody can explain why the numbers say what they say. Because a forecast a buyer doesn't trust gets discounted before it's even reviewed, this skill treats the story around the model as equally important as the model itself. Pairing the narrative with live food and beverage demand data helps sense-check whether the forecast's underlying growth assumption still holds.

Who it's for

  • Category managers presenting a sales and margin forecast to a buyer
  • Account leads translating a finance model into buyer-ready language
  • Revenue and category planning teams building the assumptions narrative
  • Suppliers pitching a multi-year category investment based on a forecast

What you get

  • The forecast's story stated in plain, non-technical language
  • Every key assumption named explicitly, not buried in the model
  • Best-case and conservative scenarios with what separates them
  • The risks that could break the forecast, named honestly
  • A specific, answerable ask for the buyer to approve
  • A one-page executive version for a time-limited meeting

How to use it

  1. 1Paste the prompt into ChatGPT, Claude or Gemini.
  2. 2Paste your forecast numbers or summary and fill the bracketed inputs.
  3. 3Answer its clarifying questions about assumptions and time horizon.
  4. 4Ask it to build the shorter executive-summary version for a rushed meeting.

See it in action

Example input

We're a supplier, fictional brand 'Tumbleweed Pizza Co.,' presenting a 3-year category sales and margin forecast for frozen pizza to a fictional retailer, 'Marigold Grocery Group.' Our model shows category sales growing 4% annually if two new premium SKUs are ranged, versus flat growth if the set stays as-is. We need the narrative that makes a skeptical buyer trust these numbers enough to approve the two new listings.

Example output

Forecast narrative — frozen pizza category at Marigold Grocery Group:

The story behind the numbers
The model isn't predicting general category growth — it's predicting that growth depends specifically on adding two premium SKUs to the set. Without them, the forecast shows the category holding flat. That's the headline: this isn't "the category will grow," it's "the category grows if the set changes, and stays flat if it doesn't." Lead with that distinction; it's the difference between a forecast and a request.

Assumptions stated explicitly
1. The two proposed premium SKUs perform at least in line with premium frozen pizza's category-average velocity once ranged — this is the single largest assumption the whole 4% figure rests on. Validate this against comparable premium launches at similar-sized retailers if you have that data.
2. No existing SKU in the set gets cannibalized enough to offset the new SKUs' contribution — a real risk in any reset, flagged here rather than assumed away.
3. Shelf space for the two new items comes from the set's actual bottom performers, not from shrinking your own core range.

Best-case scenario
Both new SKUs perform above category-average velocity, driven by continued premium-segment growth in frozen pizza; category sales approach or exceed the 4% figure, and margin improves because premium SKUs typically carry a better margin rate than the core range.

Conservative scenario
One new SKU underperforms while the other meets expectations; category growth lands closer to 2%, still ahead of the flat no-change baseline, and still margin-accretive versus the current set, just less dramatically.

What separates the two scenarios
Distribution execution (are both SKUs ranged and in-stock on day one) and marketing support (is there launch-window sampling or promotion) are the two levers most likely to determine whether Marigold lands closer to best-case or conservative — both are things the buyer partly controls, which is a useful thing to say out loud.

Risks that could break the forecast
- A competitor launches a comparable premium item in the same window, splitting the incremental demand the model assumes is available.
- Input cost inflation compresses the margin assumption even if the volume assumption holds.
- The two bottom-performing SKUs being replaced turn out to have a small but loyal following that complains loudly, creating pressure to reverse the reset before it has time to prove out.

The ask
Approve both premium SKUs for the next reset with a 6-month review checkpoint against the forecast's own conservative-scenario numbers — not the best case. Asking the buyer to be judged against the conservative scenario, not the optimistic one, makes the ask easier to say yes to and gives Tumbleweed a fair goalpost.

One-page executive version
"Frozen pizza category growth in your stores depends on ranging two new premium SKUs — flat without them, up to 4% with them. We're asking for a 6-month test against our conservative 2% scenario, funded by replacing the set's two weakest performers, not by expanding total facings."

Want me to build the slide version of this narrative for the Marigold category review?

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 finance translator who turns sales and margin forecasts into narratives buyers approve. A forecast nobody trusts is worthless regardless of its math — you separate what the model assumes from what it predicts, and never let best-case stand in for the honest range.

# Context I'll provide
- Forecast summary: [FORECAST — paste your numbers, model outputs, or summary]
- Time horizon: [HORIZON e.g. 12 months, 3 years]
- Key drivers, if known: [KEY DRIVERS e.g. new SKUs, price change, distribution gain]
- Decision this supports: [DECISION e.g. approve new listings, fund a reset, justify investment]
- Retailer/audience: [RETAILER + AUDIENCE e.g. category buyer, leadership]

# Your task
1. If the forecast numbers, key drivers, or the decision it supports are missing or vague, ask up to 3 clarifying questions BEFORE writing anything.

Frequently asked questions

What is a category financial forecast narrative?
A category financial forecast narrative is the plain-language story that explains a sales and margin forecast model to a retail buyer — what the numbers assume, what has to happen for them to hold, the best-case and conservative scenarios, and the risks that could break them. This skill builds that narrative from your forecast numbers so a buyer can evaluate and approve it, not just read a spreadsheet.
How is this different from the Syndicated Data Storyteller skill?
The Syndicated Data Storyteller turns historical market-measurement data — share, velocity, distribution — into a narrative about what already happened. This skill works on forward-looking forecast models instead: sales and margin projections, their assumptions, and the scenarios and risks around them. Use the storyteller to explain the past, and this skill to make a forecast about the future credible enough for a buyer to fund.
What AI models can run this prompt?
Any capable chat model — ChatGPT, Claude, or Google Gemini. It's model-agnostic, so paste your forecast into whichever tool you use, or save the prompt as a Custom GPT or reusable skill so every forecast presentation in your business explains its assumptions the same disciplined way.
What if I only have rough forecast numbers, not a full model?
That's enough to start. Paste whatever you have — even a single growth percentage and its driver — and the skill will build the narrative structure around it, explicitly flagging where a fuller model or more precise assumption would strengthen the story. It will not invent the missing precision for you; it will tell you what to go get instead.

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.