-
Gather ROI inputs — campaign details, the investment (total spend) table, and the results-data table. (template)
-
Calculate direct ROI — Simple ROI = (Revenue − Investment) / Investment × 100; ROAS = Revenue / Investment. Call the difference net return under the declared formula, not profit, unless the revenue attribution and complete cost basis are verified. State positive/zero/negative arithmetic return and a separate profitability-verification status. (template)
-
Calculate Earned Media Value (EMV) — impression-based (Impressions × comparable CPM / 1000) or engagement-based (Engagements × comparable CPE) only from supplied or cited, source-dated comparators. Report applicable methods separately and use a predeclared selection/weighting rule; never average or add overlapping methods by default. If no valid comparator exists, return NEEDS_INPUT for EMV. (template)
-
Calculate cost-efficiency metrics — CPM, CPR, CPE, CPV, CPC, CPA, and CAC. Compare only against a declared, source-dated target with a compatible market, window, and attribution basis; otherwise report the metric descriptively and mark the comparison pending. (template)
-
Apply attribution modeling — use one predeclared model only after the complete conversion universe, order/event dedupe key, journey touchpoints, eligible channels, and allocation rule are supplied. Optional alternative models are visibly non-additive sensitivity scenarios over the same deduplicated conversion set; never select the most favorable model after seeing results. Missing inputs or model-selection authority returns NEEDS_INPUT, not attributed revenue. (template)
-
Calculate customer lifetime value impact — label the result LTV-Based ROI only when New Customers is deduplicated against the controlling attribution universe and the supplied LTV is a complete contribution-margin basis with cohort, horizon, retention/churn, refunds, margin, discount/timing, first-order inclusion, source/date, and a positive compatible investment denominator. Then use ((New Customers × contribution-margin LTV) − Investment) / Investment × 100. A revenue-LTV input produces only an Estimated revenue-basis scenario with its basis/horizon/status; it is not economic ROI or profit and is never added to direct attributed revenue or another LTV horizon. Missing fields return NEEDS_INPUT. (template)
-
Calculate by-creator ROI — only for a complete locked creator scope with resolved opaque refs, compatible windows/cost bases, and deduplicated attributed revenue. Per-creator and tier aggregate ROAS is sum(attributed revenue) / sum(spend), never a simple mean; rank only under a predeclared rule. (template)
-
Generate the ROI report summary — investment, returns, ROI by methodology, key metrics vs. benchmark, bottom line, and 1-3 recommendations. (template)
-
Qualify candidate Return (R) evidence for the gate
The financial outputs from steps 1–8 are candidate Return (R) evidence for STAR: ROI/ROAS read against the declared target (R1) and the alternative-channel baseline (R3), CPE/CPM/CPA benchmarked on a normalized window (R2), KPI attainment versus the pre-registered target (R4), conversions attributed with a stated method and rigor (R5), and incremental impact separated from baseline where measurable (R6). A field is Measured only when its exact source, entity, observation window, and attribution basis are verified; arithmetic on User-provided or Estimated inputs is Calculated, not Measured. Return evidence applies only at assessment_time: actual; a forecast read has no R1–R6.
Hand this Return evidence to the creator-content-auditor gate — it folds R into the full actual STAR run and computes the profile-weighted SQS. This skill does not run the scorer or emit the composite. Unverified conversions emit results-unverified: report R1/R2/R5 as low-confidence and make no attributable-return claims. These financial numbers are consumed as R evidence; they are not themselves an SQS.
For a multi-creator campaign, the gate scores each creator partnership separately; a budget-weighted mean of the per-partnership SQS values may summarize the campaign but never replaces the per-partnership diagnosis. This skill supplies the per-partnership Return evidence; it does not aggregate or roll up a composite.
-
Persist only with permission — save under memory/influencer/roi-calculator/ (or the paid path) only after authorization; request separate authorization for hot-cache promotion.
