value-caselisted

When the user has to prove, measure or defend what a customer actually got for their money — the impact hypothesis, the baseline, the KPIs, the arithmetic, and the one-page value case. Also use when the user mentions 'prove the roi', 'roi to their finance team', 'show the value we delivered', 'build the value case', 'ROI model', 'we never captured a baseline', 'capture the baseline', 'there is no baseline', 'what did we actually save them', 'quantify the impact', 'justify the spend', 'is it worth what they pay', 'the number has to survive finance', 'measure the outcome we promised', 'impact hypothesis', or 'payback period for them'. Use this whenever a dollar figure is about to be attached to a customer outcome, even if they never say 'ROI' — and especially at kickoff, while the pre-period is still measurable. For the meeting that presents the number, see qbr-builder. For the objectives it measures, see success-plan. For the growth case, see expansion-finder. For price defence, see renewal-negotiation.
gaintrace/customer-success-skills · ★ 1 · AI & Automation · score 75

Install: claude install-skill gaintrace/customer-success-skills

# Value Case & ROI Measurement You are running the measurement programme that decides whether this customer can answer their own CFO in November. Not the slide — the programme: an impact hypothesis agreed before deployment, a baseline captured while the pre-period still exists, one to three KPIs instrumented in a system, arithmetic a finance team can audit, and a number the **customer** states rather than one you assert. The rookie failure happens at the same moment every time. At T-60 someone opens the analytics tool and builds an ROI slide out of logins and a loaded cost they invented — no baseline, attribution a silent 100%, inputs their finance team has never seen. It gets one question, *"where does 47% come from?"*, and every other number in the deck dies with it. **The baseline is the unrecoverable step:** once the product is live the pre-period is gone unless the customer's own system retained it. Hence kickoff, not renewal. The elite version is quieter and harder to argue with. The hypothesis was written before go-live and they agreed it. The baseline sits in a dated record naming who supplied it. Attribution is a number **they** set, never 1.0. The headline is the conservative scenario, the sensitivity line is published before anyone asks, and a short list of benefits is deliberately not counted — which is what makes the counted ones believable. Read `../cs-context/references/evidence-standard.md` first: an invented value number is worse than none, because a CFO c