Fpa board briefing

Skill JeffBrines/openfpa/skills/fpa-board-briefing

The FP&A toolbelt for AI coding agents. Claude Code or Codex does the thinking; openfpa gives it a tested finance kernel, durable company memory, and a Karpathy inspired research loop that improves forecasts against your actuals. By Guiderail and Jeff Brines.

Install

npx -y skills add JeffBrines/openfpa --skill fpa-board-briefing

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

5 stars5 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when producing a board deck, investor update, or CFO briefing from an openfpa forecast - turning model output into a board-ready narrative and exportable artifacts.

SKILL.md

2.5 KB, as published. Nobody here has run it

Board Briefing (Operate)

Overview

Turn forecast output into a board/investor-grade briefing: the headline numbers, the cash story, what changed, and the risks - as markdown and Excel. Make the operator look like they have a CFO.

Core principle: A board wants the story and the three things that matter, not a data dump.

When to use

Board decks, investor updates, lender packages
"Summarize the forecast for leadership"

Workflow

Discover the company command. Run openfpa entrypoint-list <company-root> --kind report. Use a registered briefing workflow when one exists.

Build the forecast (monthly + optional runway):

import pyfpa
from pyfpa.io.loaders import load_cash13_config
monthly = pyfpa.cashflow_from_config(pyfpa.load_config("examples/ridgeline/config.yaml"))
runway = pyfpa.runway_summary(pyfpa.cash13_forecast(load_cash13_config("examples/ridgeline/cash13.yaml")))

Render the briefing:

from pyfpa.io.reporting import to_briefing_md, forecast_to_excel
md = to_briefing_md(monthly, title="Acme Inc.", runway=runway)
forecast_to_excel(monthly, "forecast.xlsx")

to_briefing_md emits a headline (revenue, EBITDA, net income, ending cash), an optional 13-week runway section, and a monthly table.

Add the narrative the renderer can't. to_briefing_md emits only the headline, the optional runway section, and the monthly table - it has no narrative slot. So author your own markdown around it: prepend a ## What changed section (the 3 things that moved) and append ## Risks (3 forward risks) and ## The ask (e.g. "approve a $200K line to bridge the spring build"). The rendered briefing is the data spine; you supply the story.
Apply judgment (see fpa-cfo-judgment): caveat any pre-close months, state whether cash is flash or GL, and don't quote ebitda as true EBITDA if D&A matters.
If the audience wants the model itself, produce the live-formula workbook via fpa-excel-model alongside the briefing.

One-command demo

python examples/ridgeline/run_demo.py runs this whole path on the synthetic demo and writes docs/demo/briefing.md + forecast.xlsx.

Common mistakes

Leading with a table instead of the takeaway.
Presenting a cash trough without the recommended action.