v20.0.0 to v20.1.0

+ version: "20.1.0"

+ metadata: {"author": "aaron-he-zhu", "version": "20.1.0", "discipline": "influencer", "phase": "report", "geo-relevance": "low", "hermes": {"tags": ["marketing", "influencer", "report"], "category": "influencer"}, "openclaw": {"emoji": "📣", "homepage": "https://github.com/aaron-he-zhu/aaron-marketing-skills"}}

+ - **Reads**: campaign ID, complete opaque creator scope when creator-level math is requested, spend/cost-basis breakdown, deduplicated results data (reach, impressions, engagements, clicks, conversions, attributed revenue, new customers), the predeclared attribution model/window/decision rule, AOV and economic LTV inputs if LTV is in scope, and prior performance output from `performance-analyzer`. Reuse authorized opaque `creator_ref` values; raw handles/names/URLs/provider IDs stay transient and never identify a saved row.

+ - **Writes**: return the ROI calculation and summary inline by default; save them to `memory/influencer/roi-calculator/YYYY-MM-DD-<topic>.md` (or the declared paid path) only with exact WARM-save authorization. Saved output uses `campaign_id`, complete opaque `creator_ref` scope, and opaque evidence/artifact refs—never raw identity locators.

+ - **Promotes**: only with separate exact authorization, promote durable headline numbers with their attribution window, source, and uncertainty to `memory/hot-cache.md`; a calculation or WARM-save request does not authorize this operation.

+ 3. A bottom-line arithmetic assessment and 1-3 recommendations are written. Call the campaign profitable only when attributed revenue and a complete campaign cost basis are verified; otherwise state that profitability is unverified.

+ 4. Every denominator is verified numeric and `> 0`; zero, negative, missing, or incompatible denominators yield `undefined`/`NEEDS_INPUT`, never a ratio.

+ 2. **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](references/roi-templates.md#step-2--direct-roi-calculation))

+ 3. **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](references/roi-templates.md#step-3--earned-media-value-emv))

+ 5. **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](references/roi-templates.md#step-5--attribution-analysis))

+ 6. **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](references/roi-templates.md#step-6--lifetime-value-analysis))

+ 7. **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](references/roi-templates.md#step-7--influencer-level-roi))

+ 9. **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`.

+ For every formula in this skill, verify the denominator is numeric and strictly greater than zero. If investment, impressions, reach, engagements, views, clicks, acquisitions, customers, or another required denominator is zero, negative, missing, or incompatible with the numerator window, report the ratio as `undefined` and return `NEEDS_INPUT` for that metric. Never silently divide by zero, coerce it, or substitute a nominal value.

+

+ | Revenue used in calculation | $72,000 (User-provided; source/window unverified) |

+ ### Direct ROI — calculated on User-provided revenue basis

+ - **Net return under the declared formula**: $47,000

+ The supplied revenue implies $2.88 per $1 spent. `results-unverified`: no attribution source, method, or window was supplied, so this is not an attributable, causal, or incremental-return claim.

+ - **EMV**: `NEEDS_INPUT` — no source-dated comparable CPM/CPE or declared valuation rule was supplied

+ - **EMV Multiple**: `NEEDS_INPUT`

+ ## Assessment: Positive arithmetic return on the supplied basis; profitability and causality unverified

+ Supplied revenue exceeds supplied investment under the declared formula, but no complete cost basis, attribution source/window, source-dated peer target, or incrementality evidence was provided. Do not infer profit, benchmark outperformance, or causal lift, and do not authorize a scale decision from this read alone; obtain verified conversions, attribution evidence, complete costs, and the campaign owner's precommitted decision rule first.