Excel Author: Headless Financial Workbooks with openpyxl | Neura Marke

Excel Author produces an .xlsx file on disk using openpyxl, following banker-grade conventions so the model is auditable, flexible, and reviewable by someone other than the person who built it. It is adapted from Anthropic's xlsx-author and audit-xls skills, dropping the MCP / Office-JS / Cowork-specific branches in favor of headless Python. You would reach for this when you need to generate a financial model programmatically, without a live Excel session, and you want the output to pass a reviewer's smell test on first glance.

What it does

Excel Author writes a complete, formula-driven Excel workbook to disk. Every calculation cell is a live Excel formula string, not a Python-computed value pasted in. Hardcoded numbers are limited to raw historical inputs, assumption drivers the user is meant to flex, and current market data (with a cell comment documenting source and date). The skill enforces a color convention: blue for hardcoded inputs, black for formulas, green for cross-sheet or external links. A reviewer can scan the sheet and immediately see what is an assumption versus what is computed.

The output lands in ./out/.xlsx. The skill creates ./out/ if it does not exist. It returns the relative path in the final message so downstream tools can pick it up. One logical model per file. Do not append to an existing workbook unless explicitly asked.

Before you start

Python environment with pip.
Install openpyxl (version 3.0 or later):

pip install "openpyxl>=3.0"

Platforms: linux, macos, windows.
No live Excel session required. This skill assumes headless Python. If you are in a live Excel session with an Office MCP available, drive their live workbook instead.
For recalculating formulas before delivery, you need LibreOffice installed (headless mode) or a Python recalc helper (see scripts/recalc.py in this skill). openpyxl writes formula strings but does not compute them. Excel recalculates on open, but downstream consumers (auto-check scripts, CI) need computed values.

Core conventions (non-negotiable)

Blue / black / green cell color

Blue (Font(color="0000FF")), hardcoded input a human entered. Revenue drivers, WACC inputs, terminal growth, market data.
Black (default), formula. Every derived cell is a live Excel formula.
Green (Font(color="006100")), link to another sheet or external file.

A reviewer can then scan the sheet and immediately see what's an assumption vs. what's computed.

Formulas over hardcodes

Every calculation cell MUST be a formula string, never a number computed in Python and pasted as a value.

# WRONG — silent bug waiting to happen
ws["D20"] = revenue_prior_year * (1 + growth)

# CORRECT — flexes when the user changes the assumption
ws["D20"] = "=D19*(1+$B$8)"

The only hardcoded numbers permitted:

Raw historical inputs (actual revenues, reported EBITDA, etc.)
Assumption drivers the user is meant to flex (growth rates, WACC inputs, terminal g)
Current market data (share price, debt balance), with a cell comment documenting source + date

If you catch yourself computing a value in Python and writing the result, stop.

Named ranges for cross-sheet references

Use named ranges for any figure referenced from another sheet, a deck, or a memo.

from openpyxl.workbook.defined_name import DefinedName
wb.defined_names["WACC"] = DefinedName("WACC", attr_text="Inputs!$C$8")
# then elsewhere:
calc["D30"] = "=D29/WACC"

Balance checks tab

Include a Checks tab that ties everything and surfaces TRUE/FALSE:

Balance sheet balances (assets = liabilities + equity)
Cash flow ties to period-over-period cash change on the BS
Sum-of-parts ties to consolidated totals
No rogue hardcodes inside calc ranges

Example:

checks = wb.create_sheet("Checks")
checks["A2"] = "BS balances"
checks["B2"] = "=IS!D20-IS!D21-IS!D22"
checks["C2"] = "=ABS(B2)<0.01"  # TRUE/FALSE

Cell comments on every hardcoded input

Add the comment AS you create the cell, not later.

from openpyxl.comments import Comment
ws["C2"] = 1_250_000_000
ws["C2"].font = Font(color="0000FF")
ws["C2"].comment = Comment("Source: 10-K FY2024, p.47, revenue line", "analyst")

Format: Source: [System/Document], [Date], [Reference], [URL if applicable].

Never defer sourcing. Never write TODO: add source.

Skeleton: typical financial model

from openpyxl import Workbook
from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
from openpyxl.comments import Comment
from openpyxl.utils import get_column_letter
from pathlib import Path

BLUE = Font(color="0000FF")
BLACK = Font(color="000000")
GREEN = Font(color="006100")
BOLD = Font(bold=True)
HEADER_FILL = PatternFill("solid", fgColor="1F4E79")
HEADER_FONT = Font(color="FFFFFF", bold=True)

wb = Workbook()

# --- Inputs tab ---
inp = wb.active
inp.title = "Inputs"
inp["A1"] = "MARKET DATA & KEY INPUTS"
inp["A1"].font = HEADER_FONT
inp["A1"].fill = HEADER_FILL
inp.merge_cells("A1:C1")

inp["B3"] = "Revenue FY2024"
inp["C3"] = 1_250_000_000
inp["C3"].font = BLUE
inp["C3"].comment = Comment("Source: 10-K FY2024 p.47", "model")

inp["B4"] = "Growth Rate"
inp["C4"] = 0.12
inp["C4"].font = BLUE

# --- Calc tab ---
calc = wb.create_sheet("DCF")
calc["B2"] = "Projected Revenue"
calc["C2"] = "=Inputs!C3*(1+Inputs!C4)"   # formula, black

# --- Checks tab ---
chk = wb.create_sheet("Checks")
chk["A2"] = "BS balances"
chk["B2"] = "=ABS(BS!D20-BS!D21-BS!D22)<0.01"

Path("./out").mkdir(exist_ok=True)
wb.save("./out/model.xlsx")

Section headers with merged cells

openpyxl quirk: when you merge, set the value on the top-left cell and style the full range separately.

ws["A7"] = "CASH FLOW PROJECTION"
ws["A7"].font = HEADER_FONT
ws.merge_cells("A7:H7")
for col in range(1, 9):  # A..H
    ws.cell(row=7, column=col).fill = HEADER_FILL

Sensitivity tables

Build with loops, not hardcoded formulas per cell. Rules:

Odd number of rows/cols (5×5 or 7×7), guarantees a true center cell.
Center cell = base case. The middle row/col header must equal the model's actual WACC and terminal g so the center output equals the base-case implied share price. That's the sanity check.
Highlight the center cell with medium-blue fill ("BDD7EE") and bold.
Populate every cell with a full recalculation formula, never an approximation.

# 5x5 WACC (rows) x terminal growth (cols) sensitivity
wacc_axis = [0.08, 0.085, 0.09, 0.095, 0.10]        # center row = base 9.0%
term_axis = [0.02, 0.025, 0.03, 0.035, 0.04]        # center col = base 3.0%

start_row = 40
ws.cell(row=start_row, column=1).value = "Implied Share Price ($)"
ws.cell(row=start_row, column=1).font = BOLD

for j, g in enumerate(term_axis):
    ws.cell(row=start_row+1, column=2+j).value = g
    ws.cell(row=start_row+1, column=2+j).font = BLUE

for i, w in enumerate(wacc_axis):
    r = start_row + 2 + i
    ws.cell(row=r, column=1).value = w
    ws.cell(row=r, column=1).font = BLUE
    for j, g in enumerate(term_axis):
        c = 2 + j
        # Full DCF recalc formula (simplified for illustration).
        # In a real model this references the full projection block.
        ws.cell(row=r, column=c).value = (
            f"=SUMPRODUCT(FCF_range,1/(1+{w})^year_offset) + "
            f"FCF_terminal*(1+{g})/({w}-{g})/(1+{w})^terminal_year"
        )

# Highlight center cell (base case)
center = ws.cell(row=start_row+2+len(wacc_axis)//2,
                 column=2+len(term_axis)//2)
center.fill = PatternFill("solid", fgColor="BDD7EE")
center.font = BOLD

Recalculating before delivery

openpyxl writes formula strings but does not compute them. Excel recalculates on open, but downstream consumers (auto-check scripts, CI) need computed values.

Run LibreOffice or a dedicated recalc step before delivery:

# LibreOffice headless recalc
libreoffice --headless --calc --convert-to xlsx ./out/model.xlsx --outdir ./out/

Or use a Python recalc helper (see scripts/recalc.py in this skill).

Model layout planning

Before writing any formula:

Define ALL section row positions
Write ALL headers and labels
Write ALL section dividers and blank rows
THEN write formulas using the locked row positions

This prevents the cascading-formula-breakage pattern where inserting a header row after formulas are written shifts every downstream reference.

Verify step-by-step with the user

For large models (DCFs, 3-statement, LBO), stop and show the user intermediate artifacts before continuing. Catching a wrong margin assumption before you've built downstream sensitivity tables saves an hour.

Checkpoint pattern:

After Inputs block → show raw inputs, confirm before projecting
After Revenue projections → confirm top line + growth
After FCF build → confirm the full schedule
After WACC → confirm inputs
After valuation → confirm the equity bridge
THEN build sensitivity tables

When not to use it

Users in a live Excel session with an Office MCP available, drive their live workbook instead.
Pure tabular data export with no formulas, csv or pandas.to_excel is simpler.
Dashboards / charts with heavy interactivity, use a real BI tool.

Limits and gotchas

openpyxl does not compute formulas. You must recalculate externally before delivery if downstream consumers need computed values.
The merged cell quirk: set the value on the top-left cell and style the full range separately.
The skill assumes headless Python. It drops the MCP / Office-JS / Cowork-specific branches of the original Anthropic skills.
One logical model per file. Do not append to an existing workbook unless explicitly asked.

What pairs with this

This skill is part of the Finance category. Related skills include xlsx, pptx-author, dcf-model, comps-analysis, lbo-model, and 3-statement-model. The conventions (blue/black/green, formulas-over-hardcodes, named ranges, sensitivity rules) are adapted from Anthropic's Claude for Financial Services plugin suite, Apache-2.0 licensed.

Excel Author: Build Auditable Financial Workbooks Headless with openpyxl