officecli-financial-model
Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value', 'LBO', 'debt schedule', 'cash sweep', 'MOIC', 'IRR / XIRR', 'sensitivity table', 'scenario analysis', 'ARR model', 'unit economics', 'CAC / LTV', 'cap table forecast'. Output is a single formula-driven .xlsx. This skill is a scene layer on top of officecli-xlsx — it inherits ever
npx skills add iOfficeAI/OfficeCLI --skill officecli-financial-model --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill provides a structured workflow to build a formula-driven financial model in Excel, focusing on three-zone architecture (Inputs, Calc, Outputs) and three model types (3-statement, DCF, LBO). It enforces disciplined references to assumptions, a calc balance of statements, and a separate outputs sheet for KPIs and sensitivity grids. It includes steps to create sheets, set tab colors, freeze panes, declare named ranges, and populate P&L, Balance Sheet, and Cash Flow with formulas anchored to assumptions, plus a Summary. It also defines balance checks, cash reconciliation, and a cache-refresh format pass as part of the delivery gates, and prescribes a batch mechanism for cross-sheet formulas and formatting. It mandates a print pipeline when needed and reiterates three-zone discipline and audit checks.
How it works
- Inherits the xlsx v2 rules (shell quoting, incremental execution, color coding, number formats, cache-drift guidance, delivery gates) and adds model-specific requirements.
- Implements a three-zone architecture: Inputs (Assumptions, Drivers), Calc (P&L, Balance Sheet, Cash Flow, DCF/Debt/ARR), Outputs (Summary, Dashboard, Sensitivity, Returns).
- Provides a recipe set with steps to create sheets, apply tab colors, freeze panes, and set up year columns.
- Requires defining named ranges for drivers and using references like StartingARR, TaxRate, OpeningCash, GrowthRate, GrossMargin to ensure consistency across rows.
- Guides building P&L, Balance Sheet, and Cash Flow via formulas that reference Assumptions and prior period data, with cross-sheet links and live Retained Earnings calculations.
- Includes steps for Balance Sheet reconciliation, cash reconciliation, and a Gate 4 audit to catch imbalances, plus a cache-refresh pass to ensure valuation cells load cached results.
- Describes a batch procedure to set formulas and a print-pipeline mode that isolates the Outputs zone for board/investor communications.
When to use it
Use when the user asks for a financial model in Excel that can be 3-statement, DCF, or LBO, including debt schedules, cap table projections, sensitivity/scenario analysis, and fundraising projections. Trigger on phrases like 'financial model', '3-statement model', 'DCF', 'LBO', 'IRR / XIRR', 'sensitivity table', 'scenario analysis', 'unit economics', 'cap table forecast'.
What it can touch
- Sheets: Assumptions, P&L, Balance Sheet, Cash Flow, Summary, and potentially DCF/ Debt/ ARR or other calc/outputs sheets as defined by the three-zone layout.
- Elements: named ranges (e.g., StartingARR, TaxRate, OpeningCash, GrowthRate, GrossMargin) used in formulas; cross-sheet references; batch commands to set formulas; formatting and color rules for inputs and outputs.
Caveats
- The skill relies on the OfficeCLI xlsx v2 framework and inherits its Known Issues, Delivery Gate minimum cycle, and 4-color code rules. It requires strict adherence to three-zone architecture and named-range discipline. It prohibits delivering non-model sheets like simple budgets or CSV dumps via this skill. It uses a Gate 4 balance check that rejects imbalanced models. It uses a cache-drift mechanism and a non-resident batch execution model for cross-sheet formulas. The example steps include placeholders and placeholder paths that must be replaced with actual layout in implementation. All numbers and references must be drawn from the described steps and not added beyond those present in the model recipe in the skill.
# OfficeCLI Financial-Model Skill **This skill is a scene layer on top of `officecli-xlsx`.** Every xlsx hard rule — shell quoting, incremental execution, Help-First Rule, visual delivery floor, CFO 4-color code (blue input / black formula / green cross-sheet / yellow-fill assumption), number-format standards (years as text, zero as `-`, `%` one decimal, negatives in parens), assumption-cell discipline, CSV batch import, chart data-feed forms (a/b/c), the 5-gate Delivery cycle, cache-drift guidance, Known Issues (the cross-sheet `!` trap, batch + resident for formulas, renderer caveats) — is **inherited, not re-taught**. This file adds only what a **financial model** requires on top: three-zone architecture, 3 model-type recipes (3-statement / DCF / LBO), sensitivity + scenario protocols, financial-function patterns, circular-reference discipline, and model-specific Delivery Gates 4–6. When the xlsx base rules cover it, the text here says `→ see xlsx v2 §X`. Read `skills/officecli-xlsx/SKILL.md` first if you have not. ## Setup If `officecli` is missing: - **macOS / Linux**: `curl -fsSL https://d.officecli.ai/install.sh | bash` - **Windows (PowerShell)**: `irm https://d.officecli.ai
- Setup
- Help-First Rule
- Mental Model & Inheritance
- Shell & Execution Discipline
- Core Principles (identity)
- Reverse handoff — when to go BACK to xlsx base
- Three-zone architecture (hard rule)
- Print delivery (board / IC / LP)
- Build-order & cache-drift rule (critical for 3-statement)
- Recipes — three model types
- Recipe A — 3-statement model (P&L + BS + CF)
- Recipe B — DCF valuation
- Recipe C — LBO model
- Sensitivity & scenarios
Calc zone: zero numeric hardcodes allowed. `cell:not(:has(formula))` selects the literal (non-formula) cells; `cell:has(formula)` selects the formula cells. Assumptions zone: should be non-zero. officecli add "$FILE" / --type namedrange --prop name=_xlnm.Print_Area --prop scope=Summary --prop 'refersTo=Summary!$A$1:$H$40' for S in Assumptions 'P&L' 'Balance Sheet' 'Cash Flow' DCF WACC Debt FCF 'S&U' Exit Returns; do officecli raw-set "$FILE" /workbook --xpath "//x:sheet[@name='$S']" --action setattr --xml "state=hidden" || true done officecli add "$FILE" / --type sheet --prop name=Assumptions --prop tabColor=FFC000 officecli add "$FILE" / --type sheet --prop name=P&L --prop tabColor=4472C4 officecli add "$FILE" / --type sheet --prop name='Balance Sheet' --prop tabColor=4472C4 officecli add "$FILE" / --type sheet --prop name='Cash Flow' --prop tabColor=4472C4
What does the officecli-financial-model skill do?
Use this skill when the user wants to build a financial model — 3-statement model, DCF valuation, LBO, SaaS unit economics, sensitivity / scenario analysis, debt schedule, or fundraising projections — in Excel. Trigger on: 'financial model', '3-statement model', 'P&L + BS + CF', 'DCF', 'WACC', 'NPV', 'terminal value', 'LBO', 'debt schedule', 'cash sweep', 'MOIC', 'IRR / XIRR', 'sensitivity table', 'scenario analysis', 'ARR model', 'unit economics', 'CAC / LTV', 'cap table forecast'. Output is a single formula-driven .xlsx. This skill is a scene layer on top of officecli-xlsx — it inherits ever
How do I install it?
Run `npx skills add iOfficeAI/OfficeCLI --skill officecli-financial-model --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From iOfficeAI/OfficeCLI, a repository with 25,311 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.