agentleFS
teodstrteodstr/garage/skills/financial-forecast/SKILL.md

financial-forecast

Skill0 starsChanged 2 days agoMITView on GitHub

Build a startup financial forecast from explicit assumptions: revenue drivers, costs, hiring, a monthly profit and cash plan for the first year, burn rate, runway, break-even and three scenarios, in a table that pastes into a spreadsheet. Use for business plans, loan or grant applications, pitch decks, or to know how long the money will last. Triggers: "financial forecast", "financial model", "runway", "burn rate", "cash flow", "business plan financials", "prévisionnel financier", "plan de trésorerie", "budget prévisionnel", "seuil de rentabilité", "plan financiero", "previsión de tesorería", "proyecciones financieras".

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Not to value a company. For the economics of one customer, use unit-economics from boardroom if it is installed.

    line 23
  2. Distinctive:

    Build the cash plan separately: when customers really pay, when suppliers are paid, VAT timing, loan repayments, money raised.

    line 37
  3. Distinctive:

    Every figure comes from a driver with a source or a labeled assumption.

    line 69

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Financial forecast

A forecast is a model of the business: its value lies in the assumptions it makes visible. This skill builds it from drivers the founder can defend, month by month for the first year, and shows how long the cash will last.

When to use

  • For a business plan, a loan, grant or incubator application, or the financial slide of a pitch-deck.
  • To plan cash every month and decide when to raise money (funding-options).
  • Not to value a company. For the economics of one customer, use unit-economics from boardroom if it is installed.

Inputs

  1. The business model and the prices.
  2. Sales assumptions (volumes, conversion, cancellations) and their evidence.
  3. Costs: fixed (rent, tools, salaries), variable (per unit sold), one-off investments.
  4. Planned funding (shares, loans, grants) and its dates.
  5. The country: employer contributions and VAT are checked on official sources.

Method

  1. List the drivers, not the totals: revenue = customers × price × purchase frequency; new customers = leads × conversion rate; costs split into fixed, variable per unit and one-off. Each driver has a source or is labeled as an assumption, with its reason.
  2. Build the first twelve months month by month, then years two and three by year: revenue, variable costs, gross margin, fixed costs (salaries with employer contributions taken from official simulators), and the result before tax.
  3. Build the cash plan separately: when customers really pay, when suppliers are paid, VAT timing, loan repayments, money raised. Startups run out of cash before they run out of profit, so this plan matters most.
  4. Compute the key numbers and show the formulas:
    • net burn = cash out − cash in, per month;
    • runway (months) = cash available ÷ net burn;
    • break-even volume = fixed costs ÷ contribution margin per unit;
    • funding need = the lowest cash balance of the plan, plus a safety buffer chosen with the founder.
  5. Run three scenarios (low, base, high) by changing the two or three drivers that matter most, and show the runway in each one.
  6. Sanity-check: growth against comparable companies or the founder's own data, salaries against market sources, conversion rates against cited benchmarks. Flag the assumptions that carry the whole forecast.
  7. Deliver it ready to use: a table in CSV or Markdown that pastes into a spreadsheet, the formulas explained, and the list of assumptions to compare with real figures every month.

Output

### Assumptions
| Driver | Value | Source or reason |
|---|---|---|

### Year 1, month by month
| Month | Customers | Revenue | Variable costs | Fixed costs | Result | Cash in | Cash out | Cash balance |
|---|---|---|---|---|---|---|---|---|

### Key numbers
Net burn: … per month | Runway: … months | Break-even: month … | Funding need: …

### Scenarios
| | Low | Base | High |
|---|---|---|---|
| Runway | | | |

Quality bar

  • Every figure comes from a driver with a source or a labeled assumption; no growth curve without an explanation.
  • Profit and cash are shown separately, with VAT and payment delays where they apply.
  • Tax and contribution rates come from official sources or simulators, with the date; none from memory.
  • Formulas are shown, and the table pastes into a spreadsheet.
  • The forecast is presented as an estimate, with the list of figures to monitor every month.
  • Written in the user's language, with the terms below.

Terminology

EnglishFrançaisEspañol
Financial forecastPrévisionnel financierPrevisión financiera, plan financiero
Cash flow planPlan de trésoreriePrevisión de tesorería
Burn rateConsommation de trésorerie (burn rate)Consumo de caja (burn rate)
RunwayAutonomie financièreAutonomía financiera
Break-even pointSeuil de rentabilité, point mortPunto de equilibrio
Gross marginMarge bruteMargen bruto

Sources

  • Rogers, S., & Makonnen, R. (2014). Entrepreneurial Finance: Finance and Business Strategies for the Serious Entrepreneur (3rd ed.). McGraw-Hill Education.
  • URSSAF simulators (France): https://www.urssaf.fr

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.