Finance Ops has two tools. The CFO Briefing Generator reads QuickBooks exports (CSV, XLSX or XLS) from a folder, detects each report type by its headers, computes KPIs, compares them with the prior month from a saved history, and prints an executive summary with green, yellow and red indicators. A second script models 12-month base, bull and bear scenarios.
The Codebase Cost Estimator reads a codebase, counts code by type, applies productivity rates and overhead multipliers, researches current market rates on the web, and converts hours into calendar time and full team cost across company stages. It always shows low, average and high ranges and can add an AI return-on-investment analysis using git history.
What You Get
- A formatted executive briefing with KPIs, status indicators and month-over-month comparison
- A saved history of each period for later comparison
- Twelve-month base, bull and bear scenario projections
- A codebase cost estimate with metrics, hours, calendar time, market rates, engineering cost, team cost, a grand total and assumptions
- A confidence level and low, average and high ranges, with the highest-complexity areas called out
- An optional AI ROI view with speed multiplier and savings
Common Use Cases
- Prepare a monthly financial summary from P&L and balance sheet exports
- Model what happens if top clients leave or growth targets are met
- Produce a stakeholder-ready estimate of what a repository would cost to build
- Compare solo, startup and enterprise team costs for the same codebase
- Quantify the value of AI-assisted development from git history
What Makes It Unique
Both tools favor ranges and stated assumptions. The briefing runs entirely on local files with no API keys, and the estimator requires current-year market rates from a web search and a confidence level, so the output is suitable for stakeholders without false precision.
Under The Hood
It combines two Python scripts with prompt-led steps. The CFO scripts read the export files you place in a folder, write period history and scenario JSON on disk, and print the briefing to the terminal. The estimator has the agent read your whole codebase, search the web for current rates, and optionally read git history. On start, the instructions also call two telemetry scripts that log usage locally, with remote telemetry only by opt-in; those scripts are not in this skill folder.