Builds and stress-tests financial models for forecasting, scenario planning, and decision support — revenue build, cost structure, driver logic, and the sensitivities that show where a plan breaks. Use this to model a decision's financial consequence, build a forecast or long-range plan, evaluate an investment or hire, or pressure-test someone else's model before relying on it.
npx skills add https://github.com/cbrock84/headcount --skill financial-modeling
A model is an argument about how the business works, expressed in arithmetic. Its value is the
argument, not the output precision.
Three separated layers, always:
inside a formula is invisible and therefore never challenged.
assumption.
One row, one calculation, carried consistently across periods. Models become unauditable through
inconsistent rows more than through complexity.
Never grow a top-line by a percentage. Build it: volume × price, or accounts × retention ×
expansion. Driver-based models can be argued with, and being argued with is the point — a growth
rate cannot be wrong, only optimistic.
Cost structure separated into fixed, variable, and step-fixed. The step-fixed items are where plans
break, because they move in jumps nobody modeled.
A single-scenario model tells you nothing about risk. For every model, produce:
If a plan only works in the base case, that is the finding.
Lead with the answer, then the two assumptions it rests on most heavily, then what would change it.
Never present a model without stating what it is most sensitive to — the recipient will assume
robustness you did not claim.
guessed growth rate is false confidence.
Take cbrock84/financial-modeling from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.