Agent skill · software engineering · nousresearch
excel-author
Build auditable financial workbooks headless via openpyxl.
Why this skill is useful
Adds executable scripts for generating auditable financial models with specific conventions that are not commonly known.
What it needs
Requires openpyxl installed locally. About 6k tokens when loaded. Last updated 2026-08-07. 226,679 stars on the source repository.
What this skill does
excel-author 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. Output contract Write to ./out/<name>.xlsx. Create ./out/ if it does not exist. Return the relative path in your final message so downstream tools can pick it up. One logical model per file. Do not append to an existing workbook unless explicitly asked. Setup Use python when it already imports openpyxl (the Hermes Docker image ships it). Otherwise, when hermes is on PATH, let Hermes build its shared, pinned documents environment under the Hermes home (safe to run from several agents at once); in a Docker sandbox without Hermes the block builds a venv in the sandbox home with the same pinned versions. It is the same block as the microsoft-office/pdf skills. Never pip install into the interpreter that runs Hermes: Run the model-building Python with "$PY". 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. The only hardcoded numbers permitted: 1. Raw historical inputs (actual revenues, reported EBITDA, etc.) 2. Assumption drivers the user is meant to flex (growth rates, WACC inputs, terminal g) 3. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nousresearch/excel-author