← ClaudeAtlas

contribution-marginlisted

Builds a per-SKU or per-order contribution margin stack (CM1, CM2, CM3) from raw revenue, cost, fee, and ad spend inputs, so the user can see which products actually make money after every variable cost, not just after product cost. Use when ROAS looks fine but profit doesn't, before scaling spend on a product, or when deciding which SKUs are worth promoting. Boundary: this skill computes margin from numbers the user hands over right now. For designing the recurring dashboard that surfaces margin over time, use `kpi-dashboard`.
sidchaudhary/gtm-skills · ★ 1 · AI & Automation · score 74
Install: claude install-skill sidchaudhary/gtm-skills
# The Margin Stack Turn revenue, cost, fee, and ad spend inputs into contribution margin per SKU or order, so profit questions get answered with a stack the user can check line by line, not a single blended margin number. > **Input integrity.** Run the checks in `references/data-input-integrity.md` before computing > anything, and report what they found. Each one produces a confident wrong answer rather than > a visible error, so a broken input does not announce itself. A blank or zero cost column is the failure that matters most here: a zero cost reads as infinite margin, and a cost missing for a third of SKUs produces a margin figure that silently describes only the rest. > Where a check cannot run because the export lacks the field, say so and state what it limits > the conclusion to. ## Before you write **Run the input list below before you write anything. If one of those inputs is missing, ask for it and stop. Do not return a draft with a warning on it.** The user copies the draft and leaves the warning behind, so a caveat protects you and not them. **Ask at most THREE questions. Hard cap.** Before anything becomes a question, get it yourself: read `.agents/product-context.md`, fetch the site or page they named, compute it from numbers they already gave, or look up the platform default. Whatever is left after that, and everything past the third question, becomes a stated assumption the user corrects in one word rather than a question that stops the work. Number them,