Claude for financial forecasting, done properly.
The tested prompt, the codes that help, and the setup finance pros run. Copy, adapt, ship.
Financial forecasts are either too optimistic (hockey stick projections) or too conservative (just last year +5%). Building a credible, assumption-driven model takes expertise.
Three reasons this actually lands.
The prompt, the codes, the fit. Each one on its own is a nice-to-have. Together, they change the workflow.
One tested prompt, copy-paste ready. Rules baked in, placeholders marked, tone locked down. No prompt-engineering trial runs, no back-and-forth.
Prefix with REASON, V=2, REFINE for compound effects. Each code is a documented technique, not a magic word.
Tuned for finance workflows. Not a generic template, and not another "you are a helpful assistant" hack.
Without the pattern vs with it.
What the day looks like when you keep winging the prompt, and what it looks like when you stop.
Generic prompt. Claude writes something that could be about anyone, in any industry, from anywhere. Sounds like a template because it is one.
The CLSkills prompt with placeholders for your context. Claude writes it like a specialist who actually knows the work. Publishable after one edit pass.
You paste, Claude answers, you rewrite, you paste again. Ten minutes of back-and-forth per output. Three hours across a batch of five.
Prompt loaded once. You feed the specifics, Claude returns the finished output. Two minutes per, twenty across five. Same tone, same structure, every time.
Middle-of-the-road copy that reads AI-flavoured. Recipients notice. Response rates stay low. You end up rewriting most of it anyway.
An assumption-driven financial forecast with three scenarios and sensitivity analysis. Every number traces back to a stated assumption, making it easy to update and credible to present.
Copy this, replace the placeholders, ship.
Build a financial forecast for [COMPANY/PROJECT]. Type: [REVENUE FORECAST / BUDGET / CASH FLOW PROJECTION / FULL P&L] Period: [MONTHS/QUARTERS/YEARS AHEAD] Historical data: [PASTE LAST 6-12 MONTHS OF ACTUALS] Known changes: [NEW PRODUCTS, HIRES, CONTRACTS, SEASONALITY] Build: 1. **Assumptions**: List every assumption explicitly (growth rate, churn, pricing, headcount) 2. **Revenue model**: Bottom-up build (customers × ARPU × retention) 3. **Cost model**: Fixed vs. variable costs, step functions 4. **Three scenarios**: Conservative, base case, optimistic — with the assumption that differs 5. **Monthly/quarterly projections**: In table format 6. **Key drivers**: Which 3 assumptions have the most impact on the outcome? 7. **Sensitivity analysis**: What happens if each key driver changes by ±20%? Rules: - Bottom-up is more credible than top-down - Show your math for every line - Flag where you're estimating vs. using data - Include cash flow timing, not just P&L
Replace the [BRACKETED] placeholders with your context.
Stack these prefixes for compound gains.
Prepend one or more of these to the prompt above. Each code is documented on its own page with before and after examples.
Every prompt, once.
The Cheat Sheet is every tested code, with a before and an after.
Nearby prompts for the same role.
Financial analysis requires synthesizing numbers into narrative. Most people can pull data but struggle to tell the story — what the numbers…
CLAUDE FORBudget-to-actual variance reports are tedious but critical. Most analyses stop at 'we were over budget' without explaining why or recommendi…
CLAUDE FORAudit prep is stressful and time-consuming. Missing documentation, inconsistent records, and last-minute scrambles make audits worse than th…