agentsclimarketplace

Sku profitability

Skill JeffBrines/openfpa/skills/generated/sku-profitability

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 sku-profitability

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 analyzing which products make or lose money, ranking SKUs by margin or contribution, running a Pareto/80-20 on a product line, or deciding which SKUs to cut, reprice, or push in a product business.

SKILL.md

2.7 KB, as published. Nobody here has run it

SKU Profitability

Generated skill (example). This is the kind of bespoke skill fpa-learn-business proposes when the business profile says "product company with a discrete SKU set." It lives in skills/generated/ - in a real engagement it would be written into the client's repo after human approval, citing the profile facts that justify it (here: a limited-SKU D2C brand where per-product economics drive the mix decision).

Overview

The channel-level forecast tells you the business is healthy; it doesn't tell you which products carry it. This skill computes per-SKU economics and the Pareto curve so you can see the 80/20, find margin-dilutive SKUs, and make cut/reprice/push calls.

Core principle: Revenue flatters; margin and contribution decide. Rank by gross profit, not by sales.

When to use

  • "Which products actually make money?" / "what should we cut?"
  • Product-mix, pricing, or assortment-rationalization decisions
  • Any product business with a discrete SKU set (especially limited-SKU brands)

Workflow

  1. Load the SKUs (annual units, price, unit cost):

    import pyfpa
skus = pyfpa.load_skus("examples/ridgeline/skus.yaml")   # or build [Sku(...)] inline
df = pyfpa.sku_profitability(skus)

    df is sorted by gross profit (desc), indexed by SKU, with columns: units, revenue, cogs, gross_profit, gross_margin, revenue_share, cumulative_revenue_pct.

  2. Find the 80/20:

    n = pyfpa.pareto_breakpoint(df, threshold=0.8)   # SKUs that make 80% of revenue

  3. Read the signals:

    • Top of the list (high gross profit) - protect and push these.
    • High revenue, low gross_margin - reprice or renegotiate cost; they're buying share with your margin.
    • Low revenue_share AND low margin - candidates to cut (carrying cost without contribution).
    • The Pareto tail - if the bottom SKUs add complexity (SKUs to manage, inventory to hold) without margin, rationalize them.

  4. Recommend in business terms: which SKUs to push, reprice, or discontinue, and the margin impact of each move.

Judgment checks (see fpa-cfo-judgment)

  • gross_margin here is per-unit price minus unit cost - it excludes channel fees, returns, and fulfillment. A D2C SKU and a wholesale SKU at the same listed margin are not equally profitable once channel economics hit.
  • A "high-margin" SKU with tiny volume may not be worth the operational complexity it adds. Weigh contribution dollars, not just the percentage.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.