agentleFS
Natan-MohartNatan-Mohart/24-strategy-skills-for-claude/skills/business-case-builder/SKILL.md

business-case-builder

Skill41 starsChanged 3 months agoMITView on GitHub

Builds a driver-based economic model — NPV, IRR, payback, and a real sensitivity grid — using a bundled calculator, then states the specific conditions required for the case to hold. Use whenever the user wants to build, check, or challenge a business case, ROI, or investment case, is deciding whether to fund an initiative, or has a business case that's just a single-point revenue projection with no sensitivity analysis.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use whenever an initiative needs a funding decision and the "case" so far is a single optimistic revenue line with no downside scenario, no …

    line 9

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Business Case Builder

When to use

Use whenever an initiative needs a funding decision and the "case" so far is a single optimistic revenue line with no downside scenario, no discount rate, and no stated conditions for success. Also use to stress-test someone else's business case before approving it.

What it does

Builds a driver-based (not top-line-only) economic model: revenue, cost structure, and investment broken into their actual drivers, run through the bundled NPV/IRR calculator, and stress-tested with a real sensitivity grid across revenue and discount-rate assumptions — producing not just a number, but the conditions under which that number holds.

Method

  1. Decompose revenue into real drivers, not a single top-line growth assumption: volume × price, or customers × ARPU × retention — whichever actually governs this business. A one-line revenue forecast is not a model, it's a guess with decimals.
  2. Decompose cost into COGS (variable, scales with revenue) and opex (largely fixed in the near term) by year, and be explicit about which costs actually scale and which don't — this is where most hand-built cases quietly overstate margin improvement.
  3. State the initial investment fully: capex, working capital, and one-time launch costs, not just the visible capex line.
  4. Run the bundled calculator (scripts/npv_case.py) with a JSON config of discount rate, initial investment, and per-year revenue/COGS%/opex. It returns annual cash flows, NPV, IRR (via bisection, no external dependencies), and payback period.
  5. Generate the sensitivity grid (built into the same script): NPV across a range of revenue swings and discount-rate swings. This is the step that turns a single confident number into an honest range.
  6. Read the grid for the breakeven condition: find the combination of revenue shortfall and discount rate at which NPV turns negative — that is the real risk boundary of the case, and it should be stated explicitly, not buried in an appendix.
  7. State the conditions required for the case to hold in plain language: "this case requires revenue to reach at least X% of plan by year 2, and holds at discount rates up to Y%" — tied directly to the sensitivity grid, not a vague "assumptions may vary" disclaimer.

Inputs

  • Revenue drivers (volume, price, or customers/ARPU/retention) by year
  • COGS % and opex by year
  • Initial investment (capex + working capital + one-time costs)
  • Discount rate (company's cost of capital or hurdle rate)
  • Config saved as JSON matching the format documented at the top of scripts/npv_case.py

Output format

Annual cash flow table; NPV, IRR, payback period; the revenue × discount-rate NPV sensitivity grid; a plain-language statement of the conditions required for the case to hold, anchored to where the grid turns negative.

Example

An initiative shows a headline NPV of $3.35M at a 10% discount rate. The sensitivity grid shows NPV stays positive even at -20% revenue and +2pt discount rate — a genuinely robust case. A second initiative shows a similar headline NPV but turns negative at -10% revenue, meaning it only works if the plan is hit almost exactly — a much weaker case that looked identical before the grid was run.

Common pitfalls

  • Presenting a single-point NPV with no sensitivity, which hides how fragile the case actually is.
  • Modeling revenue as one growth-rate line instead of real volume/price or customer/ARPU drivers.
  • Leaving out working capital or one-time costs from the initial investment, overstating the return.
  • Choosing a discount rate that flatters the case instead of using the company's actual cost of capital.

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.