← Back to list
📣

roi-calculator Checked

Use when the user asks to "calculate influencer ROI", "prove campaign value", or "what was our RO…
📣 Marketing skills By aaron-he-zhu Version v1.0.0 Added 2026-09-03 Updated 2026-09-03 Source ↗
8.8Overall rating
2Views
6Downloads
2.7kStars

Installation

🤖 Install via AI

Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.

Install the "roi-calculator" skill by following the instructions at https://skill123.me/install/roi-calculator.
⌨️ Command line install

Run in your terminal — downloads and installs to ~/.claude/skills/.

curl -fsSL https://skill123.me/install/roi-calculator.sh | bash
📦 Download ZIP

Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.

⬇ Download v1.0.0 · 12 KB
📊 Static rating
8.8/10
Trigger
9.5
Structure
8.0
Workflow
9.2
Content
8.0
Engineering
6.0
Security
10.0

Six-dimension rubric with reviewer rationale.

View scorecard ↓
🛡 Dynamic test
—

Not live-tested yet — this skill is rated on static analysis only.

About this skill

Use when the user asks to "calculate influencer ROI", "prove campaign value", or "what was our ROAS"; produces direct ROI/ROAS, earned media value, attribution-modeled revenue, LTV-based ROI, and a stakeholder-ready summary. Not for building the full slide/written report — use report-generator. 达人营销ROI计算/投资回报测算

ROI Calculator

This skill helps you calculate and communicate the return on investment for influencer marketing campaigns using various methodologies appropriate for your goals and available data.

> **Cross-discipline (paid ads):** this is the shared **return-math engine** for paid ads — paid-measurement-loop (../../../ad/scale/paid-measurement-loop/SKILL.md), attribution-reconciler (../../../ad/scale/attribution-reconciler/SKILL.md), and budget-optimizer delegate ROAS/CPA/payback ratios here rather than recomputing them. Save paid runs under memory/ad/roi-calculator/.

Documentation

Use when the user asks to "calculate influencer ROI", "prove campaign value", or "what was our ROAS"; produces direct ROI/ROAS, earned media value, attribution-modeled revenue, LTV-based ROI, and a stakeholder-ready summary. Not for building the full slide/written report — use report-generator. 达人营销ROI计算/投资回报测算

ROI Calculator

This skill helps you calculate and communicate the return on investment for influencer marketing campaigns using various methodologies appropriate for your goals and available data.

> **Cross-discipline (paid ads):** this is the shared **return-math engine** for paid ads — paid-measurement-loop (../../../ad/scale/paid-measurement-loop/SKILL.md), attribution-reconciler (../../../ad/scale/attribution-reconciler/SKILL.md), and budget-optimizer delegate ROAS/CPA/payback ratios here rather than recomputing them. Save paid runs under memory/ad/roi-calculator/.

Quick Start

Shortest invocation:


Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach

Common scenario — compare methods before reporting:


What's the ROI of our campaign using direct revenue, EMV, and LTV-based methods?

Skill Contract

  • **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.
  • **Done when**:

1. At least one ROI methodology is computed with the inputs and formula shown.

2. Each headline metric is stated against a declared, source-dated comparison target; no universal benchmark is invented.

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.

  • **Primary next skill**: report-generator (../report-generator/SKILL.md)
View full documentation

### Handoff Summary

> Emit the standard shape from skill-contract.md §Handoff Summary Format (../../../references/skill-contract.md).

Data Sources

This family is Tier 1 — it works with no live integrations. Ask the user for spend and results data and compute everything from those inputs. Connectors below can pull the numbers automatically when available:

  • ~~social platform analytics — reach, impressions, engagements, video views per platform for EMV and cost-per-metric math.
  • ~~ecommerce / analytics — revenue, conversions, link clicks, and AOV for direct ROI and attribution.
  • ~~CRM — new-customer counts, repeat-purchase rate, and lifetime value for LTV-based ROI.
  • ~~influencer database — per-influencer fees and tier data for by-influencer ROI.

With zero integrations, supply the investment and results tables by hand and the skill still produces every calculation. See CONNECTORS.md (../../../CONNECTORS.md) for the free/keyless recipe per category.

Instructions

When a user requests ROI calculation, work the steps below. Each step has a fill-in template in references/roi-templates.md (references/roi-templates.md) — link the step number to its block there.

1. **Gather ROI inputs** — campaign details, the investment (total spend) table, and the results-data table. (template (references/roi-templates.md#step-1--roi-calculation-inputs))

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))

4. **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 (references/roi-templates.md#step-4--cost-efficiency-analysis))

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))

8. **Generate the ROI report summary** — investment, returns, ROI by methodology, key metrics vs. benchmark, bottom line, and 1-3 recommendations. (template (references/roi-templates.md#step-8--roi-summary-report))

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 re

Score breakdown

Trigger
9.5
Rich What/When/When-Not description with ROI/ROAS/EMV/LTV keywords and Chinese triggers; slightly thin scenario variants.
Structure
8.0
Compact 158-line SKILL.md offloading templates to references/; heavy cross-family links clutter structure.
Workflow
9.2
Ten explicit steps with formulas, NEEDS_INPUT error paths, denominator checks and Done-when verification; excellent guard design.
Content
8.0
Imperative, concrete templates; privacy-contract jargon adds some verbosity.
Engineering
6.0
Valid frontmatter, no scripts, but most sibling references like ../report-generator/SKILL.md and ../../../references/* do not exist in the zip.
Security
10.0
No scripts, no network calls, no secrets, no injection; homepage points to github.com.
Strong task-oriented ROI engine with rigorous denominator guards and authorization gates, but many cross-skill relative links are dead in this standalone package.