Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nousresearch/excel-author
Build auditable financial workbooks headless via openpyxl.
Passed 16 of 22 test cases with the skill, and 13 of 22 without it.
and 2 more in the full report
4 fixed12 passed either way5 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
In a Python financial model builder script, what rule applies when entering historical revenue assumptions like $1.25B into input cells, and how is it implemented on the cell object?
| Checked | Without skill | With skill |
|---|---|---|
| Input cells must include cell comments attached at creation time | Missed | Passed |
| The comment text documents the source document and page reference | Missed | Passed |
The instructions your model reads when the skill loads.
Produce an .xlsx file on disk using openpyxl. Follow the banker-grade conventions below so the model is auditable, flexible, and reviewable by someone other than the person who built it.
Adapted from Anthropic's xlsx-author and audit-xls skills in the anthropics/financial-services repo. The MCP / Office-JS / Cowork-specific branches of the originals are dropped — this skill assumes headless Python.
./out/<name>.xlsx. Create ./out/ if it does not exist.pip install "openpyxl>=3.0"
Font(color="0000FF")) — hardcoded input a human entered. Revenue drivers, WACC inputs, terminal growth, market data.Font(color="006100")) — link to another sheet or external file.A reviewer can then scan the sheet and immediately see what's an assumption vs. what's computed.
Every calculation cell MUST be a formula string, never a number computed in Python and pasted as a value.
# WRONG — silent bug waiting to happen
ws["D20"] = revenue_prior_year * (1 + growth)
# CORRECT — flexes when the user changes the assumption
ws["D20"] = "=D19*(1+$B$8)"
The only hardcoded numbers permitted:
test cases passed, vs 13 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.