Back to Finance Skills
Finance Skill

Financial Model Assumptions Documenter

Document the assumptions behind a financial model so it is transparent, defensible, and auditable.

Free skill - no email required

Get the Financial Model Assumptions Documenter skill

Install it in Claude as an Agent Skill, or copy it into ChatGPT, Gemini, or any assistant. Same method either way.

This is a drafting and analysis aid. It produces a first draft for a qualified professional to review. It is not financial, accounting, tax, or investment advice.

What this does and why it matters

A financial model is only as trustworthy as its assumptions, and most models hide them inside formulas where no one can check them. This skill documents the assumptions, drivers, and logic behind a model in plain language, so investors, partners, and future-you can understand it, challenge it, and trust it. Undocumented models get dismissed; documented ones get funded.

Inputs to gather

  1. The model's purpose and what it projects.
  2. The key drivers and the assumptions behind them (growth rates, conversion, pricing, costs, timing).
  3. The basis for each assumption (historical data, benchmark, judgment).
  4. The time horizon and structure.

Method

1. State the purpose and structure

What the model is for and how it is built (the main sections and how they connect), so a reader can navigate it.

2. Document each key assumption with its basis

For every material driver: the assumption, the value, and where it comes from (actuals, market benchmark, or informed judgment). An assumption with a stated basis can be evaluated; one without is just a guess. Label judgment calls honestly.

3. Separate drivers from outputs

Make clear which inputs drive the model and which figures are calculated results, so a reader knows what to change to test scenarios.

4. Flag the sensitive assumptions

Identify the few assumptions the outcome is most sensitive to, since those deserve the most scrutiny and are where a reader should push.

5. Note the limitations

What the model does not account for and where it is most uncertain, stated plainly. Acknowledging limits builds credibility rather than undermining it.

Output format

ALWAYS use:

# Model Assumptions: [Model Name]
## Purpose and structure
## Key drivers and assumptions (assumption | value | basis: actual/benchmark/judgment)
## Drivers vs calculated outputs
## Most sensitive assumptions (where the outcome hinges)
## Limitations and areas of uncertainty
## Change log note (for future updates)

Anti-patterns to avoid

  • Assumptions with no stated basis.
  • Hiding judgment calls as if they were facts.
  • Not distinguishing inputs from outputs.
  • Claiming precision the model does not have.

Guardrails

This documents the user's model and assumptions; it is not financial advice, a projection endorsement, or assurance the model is correct. Never invent assumptions or their basis. The user owns the accuracy of the model.

Example

An assumptions memo documents a SaaS model's growth, churn, and CAC assumptions with each basis labeled, flags churn and conversion as the most sensitive drivers, and states plainly that the model excludes any downturn scenario.

How to use this skill

In Claude
  1. Download the SKILL.md file above.
  2. Add it to a Claude environment that supports Agent Skills, or attach the file to your conversation.
  3. Make your request and hand over the raw input. Claude triggers the skill automatically.
In ChatGPT or Gemini
  1. Copy the skill text above.
  2. Paste it into a ChatGPT Project, a Custom GPT's instructions, or a Gemini Gem.
  3. Give the model your raw input. It follows the same method and output format.

Frequently asked questions

What does the Financial Model Assumptions Documenter skill do?

Document the assumptions behind a financial model so it is transparent, defensible, and auditable. Use this skill whenever a user has a financial model or projection whose assumptions need writing up, wants an assumptions memo, or says 'document the model assumptions', 'explain how this model works', or 'make our projections defensible'. Trigger whenever a model's logic and drivers need to be captured so others can trust and stress-test it.

How do I use the Financial Model Assumptions Documenter skill in Claude?

Download the SKILL.md file and add it to a Claude environment that supports Agent Skills, or attach the file to your conversation. Claude triggers the skill automatically when your request matches what it does, then returns a structured first draft.

Can I use the Financial Model Assumptions Documenter skill in ChatGPT or Gemini?

Yes. Copy the skill text and paste it into a ChatGPT Project, a Custom GPT's instructions, or a Gemini Gem. Then give the model your raw input and it follows the same method.

Is the Financial Model Assumptions Documenter skill free?

Yes. Every skill in the library is free and ungated. Download it, copy it, and use it however you like.

Is the Financial Model Assumptions Documenter skill financial or professional advice?

No. Regulated skills produce first drafts and analysis for a qualified professional to review. They do not replace professional judgment and are not financial, accounting, tax, or investment advice.

Get the Book

The full system, end to end.

Looking to build your AI workforce? Get the comprehensive guide for professional services - the 12 plays, the frameworks, and the field-tested playbooks.

Buy on Amazon
Revenue Institute

Reviewed by Revenue Institute

This guide is actively maintained and reviewed by the implementation experts at Revenue Institute. As the creators of The AI Workforce Playbook, we test and deploy these exact frameworks for professional services firms scaling without new headcount.

Done-For-You Implementation

Need help turning this guide into reality?

Revenue Institute builds and implements the AI workforce for professional services firms.

Work with Revenue Institute