Fpa monthly close

Skill JeffBrines/openfpa/skills/fpa-monthly-close

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-monthly-close

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 running a month-end close, refreshing a forecast with the latest actuals, computing plan-vs-actual variance, or producing a "how did the month go" analysis in openfpa.

SKILL.md

2.3 KB, as published. Nobody here has run it

Monthly Close (Operate)

Overview

Fold the latest actuals into the model, refresh the forward forecast from the last closed position, and explain the variance. The output is a narrative, not just a variance table - what changed, why, and what it means forward.

Core principle: A close that only reports numbers isn't done. The value is the explanation.

When to use

Month-end actuals are available
"How did we do vs plan?" / reforecast requests

Workflow

Discover the company command. Run openfpa entrypoint-list <company-root> --kind close. Use a registered close command when one exists; otherwise build the workflow from the approved company architecture.
Ingest the closed month's actuals (see fpa-configure-actuals).
Establish the freeze line: closed months use actuals; the forecast resumes from the last closed balance. Never let a not-yet-closed month drive conclusions (see fpa-cfo-judgment).
Recompute the forecast: pyfpa.cashflow_from_config(cfg) after updating config with the new closed position.
Variance: compare actual vs plan for revenue, gross margin, EBITDA, and ending cash. For each material variance, state the driver (volume, price, cost ratio, timing).
Pick a reforecast posture and say which you used:
- Plan - frozen forecast unchanged
- Latest estimate - actuals for closed months, plan forward from the last closed balance
- Run-rate - project the YTD actual pace forward
Write the narrative: the 3 things that moved, the 3 risks forward.

Judgment checks (always)

Is the "closed" month actually closed, or are accruals/COGS still posting?
Did any account move because of a one-time/timing item? Separate it from run-rate.
Multi-entity: is intercompany eliminated before you total?

Close done → fpa-cash-runway (near-term liquidity), fpa-board-briefing (the writeup), and fpa-backtest-learn (score the prior forecast). Persistent or material misses feed fpa-research-loop for bounded challenger epochs.