{"id":"bd7ba48a-3fd9-458c-86bb-4579aeaa4e51","entityType":"agent","slug":"clawhub-aaron-he-zhu-roi-calculator","name":"Roi Calculator","canonicalUrl":"https://www.xpersona.co/agent/clawhub-aaron-he-zhu-roi-calculator","canonicalPath":"/agent/clawhub-aaron-he-zhu-roi-calculator","generatedAt":"2026-10-11T05:43:13.007Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T03:32:47.787Z","emptyReason":null},"description":"Use when the user asks to \"calculate influencer ROI\", \"prove campaign value\", or \"what was our ROAS\"; produces direct ROI/ROAS, earned media value, attributi... Skill: Roi Calculator Owner: aaron-he-zhu Summary: Use when the user asks to \"calculate influencer ROI\", \"prove campaign value\", or \"what was our ROAS\"; produces direct ROI/ROAS, earned media value, attributi... Tags: latest:19.0.0 Version history: v19.0.0 | 2026-07-24T15:07:03.940Z | auto **roi-calculator 19.0.0 Changelog** - Added distribution-manifest.json file for new distribution/configuration support. - Updated","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17e1tg8pjra8dn1dvtq21sahx83hrxj:roi-calculator","sourceUrl":"https://clawhub.ai/aaron-he-zhu/roi-calculator","homepage":"https://clawhub.ai/aaron-he-zhu/skills/roi-calculator","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/aaron-he-zhu/roi-calculator","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/aaron-he-zhu/skills/roi-calculator","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Use when the user asks to \"calculate influencer ROI\", \"prove campaign value\", or \"what was our ROAS\"; produces direct ROI/ROAS, earned media value, attributi..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T03:32:47.787Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T03:32:47.787Z","emptyReason":null},"stars":null,"forks":null,"downloads":1172,"packageName":null,"latestVersion":"19.0.0","tractionLabel":"1.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T03:32:47.714Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T03:32:47.787Z","lastCrawledAt":"2026-10-11T03:32:47.714Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T03:32:47.714Z","lastVerifiedAt":null,"highlights":[{"version":"19.0.0","createdAt":"2026-07-24T15:07:03.940Z","changelog":"**roi-calculator 19.0.0 Changelog** - Added `distribution-manifest.json` file for new distribution/configuration support. - Updated SKILL.md: improved bilingual clarity in description (added Chinese summary), version incremented, and metadata revised. - Removed `skill-card.md` file to streamline documentation.","fileCount":5,"zipByteSize":11492},{"version":"18.0.0","createdAt":"2026-07-13T06:26:07.828Z","changelog":"**roi-calculator v18.0.0** - Updated SKILL.md to align with the new STAR framework, clarifying that this skill now produces measured Return (R) evidence for use in SQS/STAR, rather than emitting composite scores. - Removed direct references to producing CVI or running the scorer; the financial outputs are now returned as campaign Return evidence (R1–R6) only. - Updated phase from \"measure\" to \"report\" and added relevant metadata changes (e.g., geo-relevance). - Adjusted summary and contract language to clarify calculation/benchmarking requirements and emphasize labeling of figures for SQS evidence collection. - Removed the skill-card.md file.","fileCount":4,"zipByteSize":10742},{"version":"17.0.0","createdAt":"2026-07-11T16:36:45.107Z","changelog":"**Changelog for roi-calculator v17.0.0** - Updates headline metric promotion: now requires separate authorization, specifies attribution window, source, and uncertainty; calculation requests alone do not update the hot cache. - Compares headline metrics only to user-declared, source-dated targets; does not invent or assume global benchmarks. - Cost-efficiency benchmarks (CPM, CPA, etc.) are compared only when compatible market, window, and attribution basis are declared—otherwise, results are reported as descriptive and marked as pending comparison. - Expands C3 scoring instructions for reliability: clarifies actual vs. forecast practices, evidence requirements, scoring state, and handling of results-unverified cases. - Removes obsolete `skill-card.md` file.","fileCount":4,"zipByteSize":11098},{"version":"16.0.1","createdAt":"2026-07-08T13:01:53.106Z","changelog":"- Bumped skill version to 16.0.1 in SKILL.md. - No functional or logic changes; documentation and metadata update only.","fileCount":4,"zipByteSize":9761},{"version":"16.0.0","createdAt":"2026-07-06T03:03:12.593Z","changelog":"- Version updated to 16.0.0. - Metadata field \"version\" updated from 14.0.0 to 16.0.0. - No functional or instructional changes to the skill—documentation only.","fileCount":4,"zipByteSize":9749},{"version":"14.0.0","createdAt":"2026-07-05T08:45:57.659Z","changelog":"Version 14.0.0 - Version updated to 14.0.0 throughout skill metadata. - Metadata \"version\" advanced from 13.0.0 to 14.0.0. - No changes to logic, instructions, or functionality in the SKILL.md other than versioning.","fileCount":4,"zipByteSize":9644},{"version":"13.0.0","createdAt":"2026-07-05T02:34:12.899Z","changelog":"Version 13.0.0 introduces a comprehensive methodology for influencer ROI calculation across multiple frameworks. - Adds detailed multi-step process for influencer ROI, ROAS, EMV, cost-efficiency, attribution, LTV-based ROI, and by-influencer breakdowns. - Now computes and emits a standardized summary, benchmarking all headline metrics, pass/fail ratings, and recommendations. - Introduces integration as the “return-math engine” for other paid marketing skills (used by paid-measurement-loop, attribution-reconciler, and budget-optimizer). - Implements the C³ Campaign Value Index (CVI) calculation, combining ACE, ART, and ROI scope scores into a holistic campaign value. - Fully functional with or without live integrations (manual table entry supported). - Expanded documentation and template links to ensure consistent output and handoff to report generation.","fileCount":4,"zipByteSize":9647}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17e1tg8pjra8dn1dvtq21sahx83hrxj:roi-calculator","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-roi-calculator/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-roi-calculator/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-roi-calculator/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-roi-calculator/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-roi-calculator/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-roi-calculator/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T05:43:13.004Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-roi-calculator/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-roi-calculator/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-roi-calculator/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-aaron-he-zhu-roi-calculator/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-11T03:32:47.787Z","emptyReason":null},"readme":"Skill: Roi Calculator\n\nOwner: aaron-he-zhu\n\nSummary: Use when the user asks to \"calculate influencer ROI\", \"prove campaign value\", or \"what was our ROAS\"; produces direct ROI/ROAS, earned media value, attributi...\n\nTags: latest:19.0.0\n\nVersion history:\n\nv19.0.0 | 2026-07-24T15:07:03.940Z | auto\n\n**roi-calculator 19.0.0 Changelog**\n\n- Added `distribution-manifest.json` file for new distribution/configuration support.\n- Updated SKILL.md: improved bilingual clarity in description (added Chinese summary), version incremented, and metadata revised.\n- Removed `skill-card.md` file to streamline documentation.\n\nv18.0.0 | 2026-07-13T06:26:07.828Z | auto\n\n**roi-calculator v18.0.0**\n\n- Updated SKILL.md to align with the new STAR framework, clarifying that this skill now produces measured Return (R) evidence for use in SQS/STAR, rather than emitting composite scores.\n- Removed direct references to producing CVI or running the scorer; the financial outputs are now returned as campaign Return evidence (R1–R6) only.\n- Updated phase from \"measure\" to \"report\" and added relevant metadata changes (e.g., geo-relevance).\n- Adjusted summary and contract language to clarify calculation/benchmarking requirements and emphasize labeling of figures for SQS evidence collection.\n- Removed the skill-card.md file.\n\nv17.0.0 | 2026-07-11T16:36:45.107Z | auto\n\n**Changelog for roi-calculator v17.0.0**\n\n- Updates headline metric promotion: now requires separate authorization, specifies attribution window, source, and uncertainty; calculation requests alone do not update the hot cache.\n- Compares headline metrics only to user-declared, source-dated targets; does not invent or assume global benchmarks.\n- Cost-efficiency benchmarks (CPM, CPA, etc.) are compared only when compatible market, window, and attribution basis are declared—otherwise, results are reported as descriptive and marked as pending comparison.\n- Expands C3 scoring instructions for reliability: clarifies actual vs. forecast practices, evidence requirements, scoring state, and handling of results-unverified cases.\n- Removes obsolete `skill-card.md` file.\n\nv16.0.1 | 2026-07-08T13:01:53.106Z | auto\n\n- Bumped skill version to 16.0.1 in SKILL.md.\n- No functional or logic changes; documentation and metadata update only.\n\nv16.0.0 | 2026-07-06T03:03:12.593Z | auto\n\n- Version updated to 16.0.0.\n- Metadata field \"version\" updated from 14.0.0 to 16.0.0.\n- No functional or instructional changes to the skill—documentation only.\n\nv14.0.0 | 2026-07-05T08:45:57.659Z | auto\n\nVersion 14.0.0\n\n- Version updated to 14.0.0 throughout skill metadata.\n- Metadata \"version\" advanced from 13.0.0 to 14.0.0.\n- No changes to logic, instructions, or functionality in the SKILL.md other than versioning.\n\nv13.0.0 | 2026-07-05T02:34:12.899Z | auto\n\nVersion 13.0.0 introduces a comprehensive methodology for influencer ROI calculation across multiple frameworks.\n\n- Adds detailed multi-step process for influencer ROI, ROAS, EMV, cost-efficiency, attribution, LTV-based ROI, and by-influencer breakdowns.\n- Now computes and emits a standardized summary, benchmarking all headline metrics, pass/fail ratings, and recommendations.\n- Introduces integration as the “return-math engine” for other paid marketing skills (used by paid-measurement-loop, attribution-reconciler, and budget-optimizer).\n- Implements the C³ Campaign Value Index (CVI) calculation, combining ACE, ART, and ROI scope scores into a holistic campaign value.\n- Fully functional with or without live integrations (manual table entry supported).\n- Expanded documentation and template links to ensure consistent output and handoff to report generation.\n\nArchive index:\n\nArchive v19.0.0: 5 files, 11492 bytes\n\nFiles: distribution-manifest.json (1178b), references/roi-templates.md (12637b), skill-card.md (2441b), SKILL.md (11428b), _meta.json (134b)\n\nFile v19.0.0:SKILL.md\n\n---\nname: roi-calculator\nslug: aaron-roi-calculator\ndisplayName: \"ROI Calculator · ROI 计算\"\nsummary: \"活动投入产出核算:成本归集、收益口径与 ROI 及 STAR 回报(R)证据汇总\"\ndescription: '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'\nversion: \"19.0.0\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use when measuring or projecting influencer campaign ROI, justifying or defending budgets, comparing ROI across campaigns or channels, evaluating individual influencer or tier value, or preparing executive-level ROI numbers. Activate when the user supplies spend and results data and wants ROI, ROAS, EMV, CPA/CAC, attribution, or LTV impact computed.\"\nargument-hint: \" [revenue] [results data]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"19.0.0\", \"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\"}}\n---\n\n# ROI Calculator\n\nThis skill helps you calculate and communicate the return on investment for influencer marketing campaigns using various methodologies appropriate for your goals and available data.\n\n> **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/`.\n\n## Quick Start\n\nShortest invocation:\n\n```\nCalculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\n```\n\nCommon scenario — compare methods before reporting:\n\n```\nWhat's the ROI of our campaign using direct revenue, EMV, and LTV-based methods?\n```\n\n## Skill Contract\n\n- **Reads**: campaign spend breakdown, results data (reach, impressions, engagements, clicks, conversions, revenue, new customers), AOV and repeat-rate data if LTV is in scope, any prior performance output from `performance-analyzer`.\n- **Writes**: ROI calculation file at `memory/influencer/roi-calculator/YYYY-MM-DD-.md` containing direct ROI/ROAS, EMV, cost-efficiency metrics, attribution-modeled revenue, LTV-based ROI, by-influencer ROI, and a summary report block.\n- **Promotes**: only with separate authorization, durable headline numbers with their attribution window, source, and uncertainty; a calculation request alone does not authorize hot-cache writes.\n- **Done when**:\n 1. At least one ROI methodology is computed with the inputs and formula shown.\n 2. Each headline metric is stated against a declared, source-dated comparison target; no universal benchmark is invented.\n 3. A bottom-line assessment (profitable / break-even / loss) and 1-3 recommendations are written.\n- **Primary next skill**: [report-generator](../report-generator/SKILL.md)\n\n### Handoff Summary\n\n> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).\n\n## Data Sources\n\nThis 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:\n\n- `~~social platform analytics` — reach, impressions, engagements, video views per platform for EMV and cost-per-metric math.\n- `~~ecommerce / analytics` — revenue, conversions, link clicks, and AOV for direct ROI and attribution.\n- `~~CRM` — new-customer counts, repeat-purchase rate, and lifetime value for LTV-based ROI.\n- `~~influencer database` — per-influencer fees and tier data for by-influencer ROI.\n\nWith 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.\n\n## Instructions\n\nWhen 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.\n\n1. **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))\n\n2. **Calculate direct ROI** — Simple ROI = (Revenue − Investment) / Investment × 100; ROAS = Revenue / Investment. State profit and a Profitable/Break-even/Loss assessment. ([template](references/roi-templates.md#step-2--direct-roi-calculation))\n\n3. **Calculate Earned Media Value (EMV)** — impression-based (Impressions × CPM / 1000) and engagement-based (Engagements × CPE), then average. Flag EMV as directional, not absolute. ([template](references/roi-templates.md#step-3--earned-media-value-emv))\n\n4. **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))\n\n5. **Apply attribution modeling** — run first-touch, last-touch, linear, time-decay, and position-based; recommend the model that fits the customer journey. ([template](references/roi-templates.md#step-5--attribution-analysis))\n\n6. **Calculate customer lifetime value impact** — LTV-Based ROI = (New Customers × Avg LTV − Investment) / Investment; project short- vs. long-term and compare customer quality to organic/paid. ([template](references/roi-templates.md#step-6--lifetime-value-analysis))\n\n7. **Calculate by-influencer ROI** — per-influencer ROI/ROAS rank, investment efficiency, and ROI by tier (macro/micro/nano). ([template](references/roi-templates.md#step-7--influencer-level-roi))\n\n8. **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))\n\n9. **Produce the measured Return (R) evidence for the gate**\n\n The financial outputs from steps 1–8 are the campaign's **measured 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`). Measured Return exists only at `assessment_time: actual`; a forecast read has no `R1`–`R6`. Label each figure Measured / User-provided / Calculated / Estimated.\n\n Hand this Return evidence to the [creator-content-auditor](../../activate/creator-content-auditor/SKILL.md) 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.\n\n 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.\n\n10. **Persist only with permission** — save under `memory/influencer/roi-calculator/` (or the paid path) only after authorization; request separate authorization for hot-cache promotion.\n\n## Example\n\n**User**: \"Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\"\n\n**Output**:\n\n```markdown\n# ROI Calculation Summary\n\n## Investment & Returns\n\n| Item | Value |\n|------|-------|\n| Total Investment | $25,000 |\n| Direct Revenue | $72,000 |\n| Total Reach | 2,100,000 |\n\n## ROI Results\n\n### Direct ROI\n- **Profit**: $47,000\n- **ROI**: 188%\n- **ROAS**: 2.88:1\n\nFor every $1 spent, you generated $2.88 in revenue.\n\n### Earned Media Value\n- **EMV** (directional scenario at a declared $8 CPM): $16,800\n- **EMV Multiple**: 0.67x\n\n### Cost Efficiency\n- **CPM**: $11.90\n- **CPA**: Unknown (conversion count was not supplied)\n\n## Assessment: Profitable on the supplied direct-revenue basis\n\nDirect revenue exceeds the supplied investment, but no source-dated peer target or incrementality evidence was provided. Do not infer benchmark outperformance or authorize a scale decision from this read alone; obtain verified conversions, attribution evidence, and the campaign owner's precommitted decision rule first.\n```\n\nThe source-dated benchmark evidence template lives in [references/roi-templates.md#benchmark-evidence-template](references/roi-templates.md#benchmark-evidence-template).\n\n## Reference Materials\n\n- [references/roi-templates.md](references/roi-templates.md) — fill-in templates for every Instructions step, the worked example, and benchmark evidence inputs.\n- [measurement-protocol.md](../../../references/measurement-protocol.md) — read ROI and Return (R) deltas against a control over the readback window; do not over-claim attribution.\n- [skill-contract.md](../../../references/skill-contract.md) — shared contract and Handoff Summary format.\n- [state-model.md](../../../references/state-model.md) — memory tiers and save-path conventions.\n- [CONNECTORS.md](../../../CONNECTORS.md) — free/keyless data recipe per connector category.\n- STAR scoring: [star-benchmark.md](../../../references/star-benchmark.md) — the Return (R) dimension this skill's evidence feeds and the profile-weighted SQS the gate computes.\n- [performance-analyzer](../performance-analyzer/SKILL.md) — supplies the results data this skill consumes.\n- [report-generator](../report-generator/SKILL.md) — wraps these numbers into a full report.\n- [budget-optimizer](../../target/budget-optimizer/SKILL.md) — uses ROI output to reallocate spend.\n- [campaign-planner](../../target/campaign-planner/SKILL.md) — sets the ROI targets these results are checked against.\n\n## Next Best Skill\n\n**Primary**: [report-generator](../report-generator/SKILL.md) — turn the ROI numbers into a stakeholder-ready report.\n\n**Alternates** (same Report family):\n\n- [performance-analyzer](../performance-analyzer/SKILL.md) — go back for deeper performance breakdowns if the ROI math exposed gaps.\n- [budget-optimizer](../../target/budget-optimizer/SKILL.md) — feed by-influencer and by-tier ROI into the next budget allocation.\n\nTermination note: keep a visited-set of skills invoked this session. If the primary next skill was already run, stop and report the chain complete rather than re-invoking it. Stop after at most 3 hops in a single chain.\n\nFile v19.0.0:_meta.json\n\n{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"roi-calculator\",\n \"version\": \"19.0.0\",\n \"publishedAt\": 1784905623940\n}\n\nFile v19.0.0:references/roi-templates.md\n\n# ROI Calculator — Templates & Benchmark Inputs\n\nFill-in templates for each methodology in [../SKILL.md](../SKILL.md) Instructions, plus the worked example and benchmark-evidence contract. Each block maps to a numbered step.\n\n## Step 1 — ROI Calculation Inputs\n\n```markdown\n### ROI Calculation Inputs\n\n**Campaign Details**:\n- Campaign: [name]\n- Duration: [dates]\n- Objective: [awareness/consideration/conversion]\n\n**Investment (Total Spend)**:\n| Category | Amount |\n|----------|--------|\n| Influencer fees | $[X] |\n| Product/Gifting | $[X] |\n| Production costs | $[X] |\n| Paid amplification | $[X] |\n| Agency/Tools | $[X] |\n| **Total Investment** | **$[X]** |\n\n**Results Data**:\n| Metric | Value |\n|--------|-------|\n| Total Reach | [X] |\n| Total Impressions | [X] |\n| Total Engagements | [X] |\n| Video Views | [X] |\n| Link Clicks | [X] |\n| Conversions/Sales | [X] |\n| Revenue | $[X] |\n| New Customers | [X] |\n```\n\n## Step 2 — Direct ROI Calculation\n\n```markdown\n## Direct ROI Calculation\n\n### Simple ROI\n\n**Formula**: (Revenue - Investment) / Investment × 100\n\n```\nRevenue: $[X]\nInvestment: $[X]\nProfit: $[X]\n\nROI = ($[Revenue] - $[Investment]) / $[Investment] × 100\nROI = [X]%\n```\n\n### Return on Ad Spend (ROAS)\n\n**Formula**: Revenue / Investment\n\n```\nROAS = $[Revenue] / $[Investment]\nROAS = [X]:1\n\nInterpretation: For every $1 spent, generated $[X] in revenue\n```\n\n### Direct ROI Summary\n\n| Metric | Value | Declared target (source/date) | Comparison |\n|--------|-------|-------------------------------|------------|\n| ROI % | [X]% | [X]% ([source], [date]) | [above/below/equal/pending] |\n| ROAS | [X]:1 | [X]:1 ([source], [date]) | [above/below/equal/pending] |\n| Profit | $[X] | Not applicable | Descriptive |\n\n**Assessment**: [Profitable/Break-even/Loss]\n```\n\n## Step 3 — Earned Media Value (EMV)\n\n```markdown\n## Earned Media Value Calculation\n\n### EMV Methodology\n\nEMV estimates the equivalent paid media cost to achieve the same results.\n\n### Impression-Based EMV\n\n**Formula**: Impressions × declared comparable CPM / 1000\n\n| Platform | Impressions | CPM | EMV |\n|----------|-------------|-----|-----|\n| Instagram | [X] | $[X] | $[X] |\n| TikTok | [X] | $[X] | $[X] |\n| YouTube | [X] | $[X] | $[X] |\n| **Total** | **[X]** | - | **$[X]** |\n\n### Engagement-Based EMV\n\n**Formula**: Engagements × Cost per Engagement\n\n| Engagement Type | Volume | CPE | EMV |\n|-----------------|--------|-----|-----|\n| Likes | [X] | $[X] | $[X] |\n| Comments | [X] | $[X] | $[X] |\n| Shares | [X] | $[X] | $[X] |\n| Saves | [X] | $[X] | $[X] |\n| Video Views | [X] | $[X] | $[X] |\n| **Total** | - | - | **$[X]** |\n\n### Combined EMV\n\n| Method | Value |\n|--------|-------|\n| Impression EMV | $[X] |\n| Engagement EMV | $[X] |\n| **Average EMV** | **$[X]** |\n\n### EMV ROI\n\n```\nEMV Generated: $[X]\nInvestment: $[X]\nEMV Multiple: [X]x\n\nFor every $1 spent, earned $[X] in equivalent media value\n```\n\n### EMV Caveats\n\n⚠️ **Note**: EMV is an estimate and varies by methodology. Use for directional comparison, not absolute measurement.\n```\n\n## Step 4 — Cost Efficiency Analysis\n\n```markdown\n## Cost Efficiency Analysis\n\n### Cost Per Metrics\n\n| Metric | Formula | Result | Declared target (source/date) | Comparison |\n|--------|---------|--------|-------------------------------|------------|\n| CPM | Spend ÷ (Impressions/1000) | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPR (Reach) | Spend ÷ (Reach/1000) | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPE | Spend ÷ Engagements | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPV (Video) | Spend ÷ Views | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPC | Spend ÷ Clicks | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPA | Spend ÷ Acquisitions | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CAC | Total Spend ÷ New Customers | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n\n### Comparison Contract\n\n| Field | Required value |\n|-------|----------------|\n| Target metric and rule | [metric, threshold/range, better direction] |\n| Source | [publisher or first-party cohort query] |\n| Publication/retrieval date | [YYYY-MM-DD] |\n| Market and comparison cohort | [market, industry, audience, platform] |\n| Observation window | [dates and lag] |\n| Attribution basis | [model and conversion definition] |\n| Cost and currency basis | [included costs, currency, FX date] |\n| Compatibility notes | [material differences or none] |\n\n**Comparison result**: [above/below/equal/pending]. Use `pending` when the target is absent, stale, or materially incompatible.\n\n### vs. Other Channels\n\nNormalize currency, included costs, observation window, and attribution before comparing channels.\n\n| Channel | CPA | Source/date | Comparable basis? | vs. Influencer |\n|---------|-----|-------------|-------------------|----------------|\n| Influencer Marketing | $[X] | [source/date] | Baseline | - |\n| Paid Social | $[X] | [source/date] | [yes/no] | [+/-X% or pending] |\n| Paid Search | $[X] | [source/date] | [yes/no] | [+/-X% or pending] |\n| Display Ads | $[X] | [source/date] | [yes/no] | [+/-X% or pending] |\n| Email Marketing | $[X] | [source/date] | [yes/no] | [+/-X% or pending] |\n```\n\n## Step 5 — Attribution Analysis\n\n```markdown\n## Attribution Analysis\n\n### Attribution Methods\n\n| Method | Description | Result | Notes |\n|--------|-------------|--------|-------|\n| First Touch | All credit to first interaction | $[X] | Awareness focus |\n| Last Touch | All credit to last interaction | $[X] | Conversion focus |\n| Linear | Equal credit across touchpoints | $[X] | Balanced view |\n| Time Decay | More credit to recent touches | $[X] | Recency bias |\n| Position Based | 40/20/40 first/middle/last | $[X] | Common B2C model |\n\n### Attributed Revenue by Model\n\n| Model | Attributed Revenue | ROI |\n|-------|-------------------|-----|\n| First Touch | $[X] | [X]% |\n| Last Touch | $[X] | [X]% |\n| Linear | $[X] | [X]% |\n| Time Decay | $[X] | [X]% |\n| Position Based | $[X] | [X]% |\n\n### Recommended Model for Your Business\n\n**Recommended**: [Model]\n**Rationale**: [Why this model fits your customer journey]\n\n### Multi-Touch Journey Example\n\n```\nCustomer Journey:\n\nDay 1: Sees @creator1 TikTok (Awareness) ─────┐\nDay 3: Sees @creator2 Instagram Reel ─────────┤\nDay 5: Clicks @creator1's link (Consideration)┼── Purchase Day 7\nDay 7: Uses @creator2's code (Conversion) ────┘\n\nAttribution:\nLast Touch: 100% to @creator2\nFirst Touch: 100% to @creator1\nLinear: 50% each\nPosition Based: 40% @creator1, 40% @creator2, 20% repeat exposure\n```\n```\n\n## Step 6 — Lifetime Value Analysis\n\n```markdown\n## Lifetime Value Analysis\n\n### New Customer Metrics\n\n| Metric | Influencer Acquired | Overall Average |\n|--------|--------------------|--------------------|\n| New customers | [X] | - |\n| First order AOV | $[X] | $[X] |\n| Repeat purchase rate | [%] | [%] |\n| Customer lifetime value | $[X] | $[X] |\n\n### LTV-Based ROI\n\n**Formula**: (New Customers × Avg LTV) - Investment / Investment\n\n```\nNew Customers: [X]\nAverage LTV: $[X]\nTotal LTV: $[X]\nInvestment: $[X]\n\nLTV-Based ROI = ($[X] - $[X]) / $[X] × 100\nLTV-Based ROI = [X]%\n```\n\n### Short-term vs. Long-term View\n\n| Timeframe | Revenue | ROI |\n|-----------|---------|-----|\n| Immediate (this campaign) | $[X] | [X]% |\n| 6-month projected | $[X] | [X]% |\n| 12-month projected | $[X] | [X]% |\n| Lifetime projected | $[X] | [X]% |\n\n### Customer Quality Indicators\n\n| Indicator | Influencer-Acquired | Organic | Paid Ads |\n|-----------|--------------------|---------| ---------|\n| AOV | $[X] | $[X] | $[X] |\n| Return rate | [%] | [%] | [%] |\n| Repeat rate | [%] | [%] | [%] |\n| NPS/Satisfaction | [X] | [X] | [X] |\n```\n\n## Step 7 — Influencer-Level ROI\n\n```markdown\n## Influencer-Level ROI\n\n### Individual Influencer Performance\n\n| Influencer | Investment | Revenue | ROI | ROAS | Rank |\n|------------|------------|---------|-----|------|------|\n| @[handle1] | $[X] | $[X] | [X]% | [X]:1 | 1 |\n| @[handle2] | $[X] | $[X] | [X]% | [X]:1 | 2 |\n| @[handle3] | $[X] | $[X] | [X]% | [X]:1 | 3 |\n| @[handle4] | $[X] | $[X] | [X]% | [X]:1 | 4 |\n| @[handle5] | $[X] | $[X] | [X]% | [X]:1 | 5 |\n\n### ROI Distribution\n\n```\nInfluencer ROI Distribution:\n\n@handle1 |████████████████████| 320%\n@handle2 |██████████████ | 180%\n@handle3 |████████████ | 150%\n@handle4 |██████ | 75%\n@handle5 |████ | 45%\n\nCampaign Average: 180%\n```\n\n### Investment Efficiency\n\n| Influencer | % of Budget | % of Revenue | Efficiency |\n|------------|-------------|--------------|------------|\n| @[handle1] | [%] | [%] | [X]x |\n| @[handle2] | [%] | [%] | [X]x |\n\n### ROI by Tier\n\n| Tier | Investment | Revenue | ROI | Avg ROAS |\n|------|------------|---------|-----|----------|\n| Macro | $[X] | $[X] | [%] | [X]:1 |\n| Micro | $[X] | $[X] | [%] | [X]:1 |\n| Nano | $[X] | $[X] | [%] | [X]:1 |\n```\n\n## Step 8 — ROI Summary Report\n\n```markdown\n# ROI Summary Report\n\n## Campaign: [Name]\n## Period: [Dates]\n\n---\n\n## Investment Summary\n\n| Category | Amount | % of Total |\n|----------|--------|------------|\n| Influencer Fees | $[X] | [%] |\n| Product/Gifts | $[X] | [%] |\n| Amplification | $[X] | [%] |\n| Other | $[X] | [%] |\n| **Total Investment** | **$[X]** | **100%** |\n\n## Returns Summary\n\n| Return Type | Value |\n|-------------|-------|\n| Direct Revenue | $[X] |\n| Earned Media Value | $[X] |\n| New Customers | [X] |\n| Projected LTV | $[X] |\n\n## ROI by Methodology\n\n| Methodology | ROI | Notes |\n|-------------|-----|-------|\n| Direct Revenue ROI | [X]% | Hard returns |\n| ROAS | [X]:1 | Revenue per dollar |\n| EMV Multiple | [X]x | Media value generated |\n| LTV-Based ROI | [X]% | Long-term value |\n\n## Key Metrics\n\n| Metric | Result | Declared target (source/date) | Comparison |\n|--------|--------|-------------------------------|------------|\n| CPM | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPA | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| ROAS | [X]:1 | [X]:1 ([source], [date]) | [above/below/equal/pending] |\n\n## Bottom Line\n\n**Investment**: $[X]\n**Return**: $[X]\n**Net Profit**: $[X]\n**ROI**: [X]%\n\n**Assessment**: [Campaign was profitable/broke even/lost money]\n\n## Recommendations\n\n1. [Key recommendation 1]\n2. [Key recommendation 2]\n3. [Key recommendation 3]\n\n**Decision owner and precommitted rule**: [owner / rule / UNDECIDED]\n\n---\n\n*Report Generated: [Date]*\n```\n\n## Worked Example\n\n**User**: \"Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\"\n\n**Output**:\n\n```markdown\n# ROI Calculation Summary\n\n## Investment & Returns\n\n| Item | Value |\n|------|-------|\n| Total Investment | $25,000 |\n| Direct Revenue | $72,000 |\n| Total Reach | 2,100,000 |\n\n## ROI Results\n\n### Direct ROI\n- **Profit**: $47,000\n- **ROI**: 188%\n- **ROAS**: 2.88:1\n\nFor every $1 spent, you generated $2.88 in revenue.\n\n### Earned Media Value\n- **EMV** (directional scenario at a declared $8 CPM): $16,800\n- **EMV Multiple**: 0.67x\n\n### Cost Efficiency\n- **CPM**: $11.90\n- **CPA**: Unknown (conversion count was not supplied)\n\n## Assessment: Profitable on the supplied direct-revenue basis\n\nDirect revenue exceeds the supplied investment, but no source-dated peer target or incrementality evidence was provided. Do not infer benchmark outperformance or authorize a scale decision from this read alone; obtain verified conversions, attribution evidence, and the campaign owner's precommitted decision rule first.\n```\n\n## Benchmark Evidence Template\n\nDo not use a repository-default industry threshold. Supply a first-party target or a source-dated external comparator whose market, cohort, window, attribution, and cost basis are compatible with the campaign.\n\n| Field | Value |\n|-------|-------|\n| Metric | [ROAS / ROI / CPM / CPA / CAC / other] |\n| Target or distribution | [value, range, or quantile] |\n| Better direction | [higher/lower] |\n| Source | [publisher, report, URL, or first-party query] |\n| Publication/retrieval date | [YYYY-MM-DD] |\n| Market / industry / platform | [scope] |\n| Comparison cohort | [selection definition and sample size, if known] |\n| Observation window and lag | [dates] |\n| Attribution and conversion definition | [basis] |\n| Included costs / currency / FX date | [basis] |\n| Compatibility assessment | [compatible / materially different / unknown] |\n| Comparison status | [above / below / equal / pending] |\n\nFile v19.0.0:skill-card.md\n\n## Description:\n\nCalculates influencer campaign ROI and ROAS, earned media value, attribution-modeled revenue, LTV-based ROI, and stakeholder-ready summaries from supplied campaign performance data.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)\n\n### License/Terms of Use:\n\nApache-2.0\n\n## Use Case:\n\nMarketing teams, creators, and operators use this skill to calculate or project influencer campaign returns, compare ROI methods, evaluate individual creators or tiers, and prepare numbers for budget justification or reporting.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Campaign, ecommerce, analytics, or CRM inputs may contain sensitive business performance information.\n\nMitigation: Review supplied data before use and authorize memory saves or connector-backed pulls only when those numbers may be reused for future campaign analysis.\n\nRisk: ROI, attribution, or benchmark comparisons may overstate campaign performance when conversions, targets, or comparison baselines are unverified.\n\nMitigation: Use source-dated targets and attribution windows, label each figure as measured, user-provided, calculated, or estimated, and avoid attributable-return claims when conversions are unverified.\n\nRisk: Earned media value is directional and can vary by methodology.\n\nMitigation: Present EMV as an estimate, disclose the CPM or engagement assumptions used, and avoid treating EMV as absolute revenue.\n\n## Reference(s):\n\n- [ROI templates and benchmark inputs](references/roi-templates.md)\n- [ClawHub skill page](https://clawhub.ai/aaron-he-zhu/skills/roi-calculator)\n- [Project homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, files, guidance]\n\n**Output Format:** [Markdown calculation summaries and optional memory files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May save ROI calculation files only after user authorization; can use connector-backed campaign data when available.]\n\n## Skill Version(s):\n\n19.0.0 (source: frontmatter and release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v19.0.0:distribution-manifest.json\n\n{\n \"capabilities\": [\n \"inline-delivery\",\n \"canonical-state-read\"\n ],\n \"capability_ceiling\": \"lite\",\n \"catalog_sha256\": \"6f0256cf52710f2916ecebaea0f3110c9313099ec4a69a11cac72ba9b2f3b940\",\n \"files\": [\n {\n \"bytes\": 11428,\n \"mode\": \"0644\",\n \"path\": \"SKILL.md\",\n \"sha256\": \"67510ab1308579d799525c21277cdb6ec6f3962dcb00463d4e1f7a640cf80311\"\n },\n {\n \"bytes\": 12637,\n \"mode\": \"0644\",\n \"path\": \"references/roi-templates.md\",\n \"sha256\": \"2f58cf3247a96e888243d286f153a1d854a29d6916c27e047d171da97562cf14\"\n }\n ],\n \"files_sha256\": \"5c32d263a53936794c87e0c24680f95bd8983d4d38d17f06aebd012f75f087d9\",\n \"hash_algorithm\": \"sha256\",\n \"kind\": \"standalone-skill\",\n \"manifest_excludes\": [\n \"distribution-manifest.json\"\n ],\n \"manifest_path\": \"distribution-manifest.json\",\n \"package_ceiling\": {\n \"max_bytes\": 1000000,\n \"max_files\": 64\n },\n \"profile\": \"lite\",\n \"profile_definition_sha256\": \"4598e1f7bba667ef928ea2a60a6252ad9348086e9eecab29437db442df2a568e\",\n \"schema_version\": \"1.1\",\n \"source\": {\n \"commit\": \"f552620c278afddcb25d09637a0cfcc1ce48faf4\",\n \"repository\": \"aaron-he-zhu/aaron-marketing-skills\"\n }\n}\n\nArchive v18.0.0: 4 files, 10742 bytes\n\nFiles: references/roi-templates.md (12637b), skill-card.md (2765b), SKILL.md (11387b), _meta.json (134b)\n\nFile v18.0.0:SKILL.md\n\n---\nname: roi-calculator\nslug: aaron-roi-calculator\ndisplayName: \"ROI Calculator · ROI 计算\"\nsummary: \"活动投入产出核算:成本归集、收益口径与 ROI 及 STAR 回报(R)证据汇总\"\ndescription: '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.'\nversion: \"18.0.0\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use when measuring or projecting influencer campaign ROI, justifying or defending budgets, comparing ROI across campaigns or channels, evaluating individual influencer or tier value, or preparing executive-level ROI numbers. Activate when the user supplies spend and results data and wants ROI, ROAS, EMV, CPA/CAC, attribution, or LTV impact computed.\"\nargument-hint: \" [revenue] [results data]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"18.0.0\", \"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\"}}\n---\n\n# ROI Calculator\n\nThis skill helps you calculate and communicate the return on investment for influencer marketing campaigns using various methodologies appropriate for your goals and available data.\n\n> **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/`.\n\n## Quick Start\n\nShortest invocation:\n\n```\nCalculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\n```\n\nCommon scenario — compare methods before reporting:\n\n```\nWhat's the ROI of our campaign using direct revenue, EMV, and LTV-based methods?\n```\n\n## Skill Contract\n\n- **Reads**: campaign spend breakdown, results data (reach, impressions, engagements, clicks, conversions, revenue, new customers), AOV and repeat-rate data if LTV is in scope, any prior performance output from `performance-analyzer`.\n- **Writes**: ROI calculation file at `memory/influencer/roi-calculator/YYYY-MM-DD-.md` containing direct ROI/ROAS, EMV, cost-efficiency metrics, attribution-modeled revenue, LTV-based ROI, by-influencer ROI, and a summary report block.\n- **Promotes**: only with separate authorization, durable headline numbers with their attribution window, source, and uncertainty; a calculation request alone does not authorize hot-cache writes.\n- **Done when**:\n 1. At least one ROI methodology is computed with the inputs and formula shown.\n 2. Each headline metric is stated against a declared, source-dated comparison target; no universal benchmark is invented.\n 3. A bottom-line assessment (profitable / break-even / loss) and 1-3 recommendations are written.\n- **Primary next skill**: [report-generator](../report-generator/SKILL.md)\n\n### Handoff Summary\n\n> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).\n\n## Data Sources\n\nThis 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:\n\n- `~~social platform analytics` — reach, impressions, engagements, video views per platform for EMV and cost-per-metric math.\n- `~~ecommerce / analytics` — revenue, conversions, link clicks, and AOV for direct ROI and attribution.\n- `~~CRM` — new-customer counts, repeat-purchase rate, and lifetime value for LTV-based ROI.\n- `~~influencer database` — per-influencer fees and tier data for by-influencer ROI.\n\nWith 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.\n\n## Instructions\n\nWhen 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.\n\n1. **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))\n\n2. **Calculate direct ROI** — Simple ROI = (Revenue − Investment) / Investment × 100; ROAS = Revenue / Investment. State profit and a Profitable/Break-even/Loss assessment. ([template](references/roi-templates.md#step-2--direct-roi-calculation))\n\n3. **Calculate Earned Media Value (EMV)** — impression-based (Impressions × CPM / 1000) and engagement-based (Engagements × CPE), then average. Flag EMV as directional, not absolute. ([template](references/roi-templates.md#step-3--earned-media-value-emv))\n\n4. **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))\n\n5. **Apply attribution modeling** — run first-touch, last-touch, linear, time-decay, and position-based; recommend the model that fits the customer journey. ([template](references/roi-templates.md#step-5--attribution-analysis))\n\n6. **Calculate customer lifetime value impact** — LTV-Based ROI = (New Customers × Avg LTV − Investment) / Investment; project short- vs. long-term and compare customer quality to organic/paid. ([template](references/roi-templates.md#step-6--lifetime-value-analysis))\n\n7. **Calculate by-influencer ROI** — per-influencer ROI/ROAS rank, investment efficiency, and ROI by tier (macro/micro/nano). ([template](references/roi-templates.md#step-7--influencer-level-roi))\n\n8. **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))\n\n9. **Produce the measured Return (R) evidence for the gate**\n\n The financial outputs from steps 1–8 are the campaign's **measured 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`). Measured Return exists only at `assessment_time: actual`; a forecast read has no `R1`–`R6`. Label each figure Measured / User-provided / Calculated / Estimated.\n\n Hand this Return evidence to the [creator-content-auditor](../../activate/creator-content-auditor/SKILL.md) 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.\n\n 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.\n\n10. **Persist only with permission** — save under `memory/influencer/roi-calculator/` (or the paid path) only after authorization; request separate authorization for hot-cache promotion.\n\n## Example\n\n**User**: \"Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\"\n\n**Output**:\n\n```markdown\n# ROI Calculation Summary\n\n## Investment & Returns\n\n| Item | Value |\n|------|-------|\n| Total Investment | $25,000 |\n| Direct Revenue | $72,000 |\n| Total Reach | 2,100,000 |\n\n## ROI Results\n\n### Direct ROI\n- **Profit**: $47,000\n- **ROI**: 188%\n- **ROAS**: 2.88:1\n\nFor every $1 spent, you generated $2.88 in revenue.\n\n### Earned Media Value\n- **EMV** (directional scenario at a declared $8 CPM): $16,800\n- **EMV Multiple**: 0.67x\n\n### Cost Efficiency\n- **CPM**: $11.90\n- **CPA**: Unknown (conversion count was not supplied)\n\n## Assessment: Profitable on the supplied direct-revenue basis\n\nDirect revenue exceeds the supplied investment, but no source-dated peer target or incrementality evidence was provided. Do not infer benchmark outperformance or authorize a scale decision from this read alone; obtain verified conversions, attribution evidence, and the campaign owner's precommitted decision rule first.\n```\n\nThe source-dated benchmark evidence template lives in [references/roi-templates.md#benchmark-evidence-template](references/roi-templates.md#benchmark-evidence-template).\n\n## Reference Materials\n\n- [references/roi-templates.md](references/roi-templates.md) — fill-in templates for every Instructions step, the worked example, and benchmark evidence inputs.\n- [measurement-protocol.md](../../../references/measurement-protocol.md) — read ROI and Return (R) deltas against a control over the readback window; do not over-claim attribution.\n- [skill-contract.md](../../../references/skill-contract.md) — shared contract and Handoff Summary format.\n- [state-model.md](../../../references/state-model.md) — memory tiers and save-path conventions.\n- [CONNECTORS.md](../../../CONNECTORS.md) — free/keyless data recipe per connector category.\n- STAR scoring: [star-benchmark.md](../../../references/star-benchmark.md) — the Return (R) dimension this skill's evidence feeds and the profile-weighted SQS the gate computes.\n- [performance-analyzer](../performance-analyzer/SKILL.md) — supplies the results data this skill consumes.\n- [report-generator](../report-generator/SKILL.md) — wraps these numbers into a full report.\n- [budget-optimizer](../../target/budget-optimizer/SKILL.md) — uses ROI output to reallocate spend.\n- [campaign-planner](../../target/campaign-planner/SKILL.md) — sets the ROI targets these results are checked against.\n\n## Next Best Skill\n\n**Primary**: [report-generator](../report-generator/SKILL.md) — turn the ROI numbers into a stakeholder-ready report.\n\n**Alternates** (same Report family):\n\n- [performance-analyzer](../performance-analyzer/SKILL.md) — go back for deeper performance breakdowns if the ROI math exposed gaps.\n- [budget-optimizer](../../target/budget-optimizer/SKILL.md) — feed by-influencer and by-tier ROI into the next budget allocation.\n\nTermination note: keep a visited-set of skills invoked this session. If the primary next skill was already run, stop and report the chain complete rather than re-invoking it. Stop after at most 3 hops in a single chain.\n\nFile v18.0.0:_meta.json\n\n{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"roi-calculator\",\n \"version\": \"18.0.0\",\n \"publishedAt\": 1783923967828\n}\n\nFile v18.0.0:references/roi-templates.md\n\n# ROI Calculator — Templates & Benchmark Inputs\n\nFill-in templates for each methodology in [../SKILL.md](../SKILL.md) Instructions, plus the worked example and benchmark-evidence contract. Each block maps to a numbered step.\n\n## Step 1 — ROI Calculation Inputs\n\n```markdown\n### ROI Calculation Inputs\n\n**Campaign Details**:\n- Campaign: [name]\n- Duration: [dates]\n- Objective: [awareness/consideration/conversion]\n\n**Investment (Total Spend)**:\n| Category | Amount |\n|----------|--------|\n| Influencer fees | $[X] |\n| Product/Gifting | $[X] |\n| Production costs | $[X] |\n| Paid amplification | $[X] |\n| Agency/Tools | $[X] |\n| **Total Investment** | **$[X]** |\n\n**Results Data**:\n| Metric | Value |\n|--------|-------|\n| Total Reach | [X] |\n| Total Impressions | [X] |\n| Total Engagements | [X] |\n| Video Views | [X] |\n| Link Clicks | [X] |\n| Conversions/Sales | [X] |\n| Revenue | $[X] |\n| New Customers | [X] |\n```\n\n## Step 2 — Direct ROI Calculation\n\n```markdown\n## Direct ROI Calculation\n\n### Simple ROI\n\n**Formula**: (Revenue - Investment) / Investment × 100\n\n```\nRevenue: $[X]\nInvestment: $[X]\nProfit: $[X]\n\nROI = ($[Revenue] - $[Investment]) / $[Investment] × 100\nROI = [X]%\n```\n\n### Return on Ad Spend (ROAS)\n\n**Formula**: Revenue / Investment\n\n```\nROAS = $[Revenue] / $[Investment]\nROAS = [X]:1\n\nInterpretation: For every $1 spent, generated $[X] in revenue\n```\n\n### Direct ROI Summary\n\n| Metric | Value | Declared target (source/date) | Comparison |\n|--------|-------|-------------------------------|------------|\n| ROI % | [X]% | [X]% ([source], [date]) | [above/below/equal/pending] |\n| ROAS | [X]:1 | [X]:1 ([source], [date]) | [above/below/equal/pending] |\n| Profit | $[X] | Not applicable | Descriptive |\n\n**Assessment**: [Profitable/Break-even/Loss]\n```\n\n## Step 3 — Earned Media Value (EMV)\n\n```markdown\n## Earned Media Value Calculation\n\n### EMV Methodology\n\nEMV estimates the equivalent paid media cost to achieve the same results.\n\n### Impression-Based EMV\n\n**Formula**: Impressions × declared comparable CPM / 1000\n\n| Platform | Impressions | CPM | EMV |\n|----------|-------------|-----|-----|\n| Instagram | [X] | $[X] | $[X] |\n| TikTok | [X] | $[X] | $[X] |\n| YouTube | [X] | $[X] | $[X] |\n| **Total** | **[X]** | - | **$[X]** |\n\n### Engagement-Based EMV\n\n**Formula**: Engagements × Cost per Engagement\n\n| Engagement Type | Volume | CPE | EMV |\n|-----------------|--------|-----|-----|\n| Likes | [X] | $[X] | $[X] |\n| Comments | [X] | $[X] | $[X] |\n| Shares | [X] | $[X] | $[X] |\n| Saves | [X] | $[X] | $[X] |\n| Video Views | [X] | $[X] | $[X] |\n| **Total** | - | - | **$[X]** |\n\n### Combined EMV\n\n| Method | Value |\n|--------|-------|\n| Impression EMV | $[X] |\n| Engagement EMV | $[X] |\n| **Average EMV** | **$[X]** |\n\n### EMV ROI\n\n```\nEMV Generated: $[X]\nInvestment: $[X]\nEMV Multiple: [X]x\n\nFor every $1 spent, earned $[X] in equivalent media value\n```\n\n### EMV Caveats\n\n⚠️ **Note**: EMV is an estimate and varies by methodology. Use for directional comparison, not absolute measurement.\n```\n\n## Step 4 — Cost Efficiency Analysis\n\n```markdown\n## Cost Efficiency Analysis\n\n### Cost Per Metrics\n\n| Metric | Formula | Result | Declared target (source/date) | Comparison |\n|--------|---------|--------|-------------------------------|------------|\n| CPM | Spend ÷ (Impressions/1000) | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPR (Reach) | Spend ÷ (Reach/1000) | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPE | Spend ÷ Engagements | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPV (Video) | Spend ÷ Views | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPC | Spend ÷ Clicks | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPA | Spend ÷ Acquisitions | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CAC | Total Spend ÷ New Customers | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n\n### Comparison Contract\n\n| Field | Required value |\n|-------|----------------|\n| Target metric and rule | [metric, threshold/range, better direction] |\n| Source | [publisher or first-party cohort query] |\n| Publication/retrieval date | [YYYY-MM-DD] |\n| Market and comparison cohort | [market, industry, audience, platform] |\n| Observation window | [dates and lag] |\n| Attribution basis | [model and conversion definition] |\n| Cost and currency basis | [included costs, currency, FX date] |\n| Compatibility notes | [material differences or none] |\n\n**Comparison result**: [above/below/equal/pending]. Use `pending` when the target is absent, stale, or materially incompatible.\n\n### vs. Other Channels\n\nNormalize currency, included costs, observation window, and attribution before comparing channels.\n\n| Channel | CPA | Source/date | Comparable basis? | vs. Influencer |\n|---------|-----|-------------|-------------------|----------------|\n| Influencer Marketing | $[X] | [source/date] | Baseline | - |\n| Paid Social | $[X] | [source/date] | [yes/no] | [+/-X% or pending] |\n| Paid Search | $[X] | [source/date] | [yes/no] | [+/-X% or pending] |\n| Display Ads | $[X] | [source/date] | [yes/no] | [+/-X% or pending] |\n| Email Marketing | $[X] | [source/date] | [yes/no] | [+/-X% or pending] |\n```\n\n## Step 5 — Attribution Analysis\n\n```markdown\n## Attribution Analysis\n\n### Attribution Methods\n\n| Method | Description | Result | Notes |\n|--------|-------------|--------|-------|\n| First Touch | All credit to first interaction | $[X] | Awareness focus |\n| Last Touch | All credit to last interaction | $[X] | Conversion focus |\n| Linear | Equal credit across touchpoints | $[X] | Balanced view |\n| Time Decay | More credit to recent touches | $[X] | Recency bias |\n| Position Based | 40/20/40 first/middle/last | $[X] | Common B2C model |\n\n### Attributed Revenue by Model\n\n| Model | Attributed Revenue | ROI |\n|-------|-------------------|-----|\n| First Touch | $[X] | [X]% |\n| Last Touch | $[X] | [X]% |\n| Linear | $[X] | [X]% |\n| Time Decay | $[X] | [X]% |\n| Position Based | $[X] | [X]% |\n\n### Recommended Model for Your Business\n\n**Recommended**: [Model]\n**Rationale**: [Why this model fits your customer journey]\n\n### Multi-Touch Journey Example\n\n```\nCustomer Journey:\n\nDay 1: Sees @creator1 TikTok (Awareness) ─────┐\nDay 3: Sees @creator2 Instagram Reel ─────────┤\nDay 5: Clicks @creator1's link (Consideration)┼── Purchase Day 7\nDay 7: Uses @creator2's code (Conversion) ────┘\n\nAttribution:\nLast Touch: 100% to @creator2\nFirst Touch: 100% to @creator1\nLinear: 50% each\nPosition Based: 40% @creator1, 40% @creator2, 20% repeat exposure\n```\n```\n\n## Step 6 — Lifetime Value Analysis\n\n```markdown\n## Lifetime Value Analysis\n\n### New Customer Metrics\n\n| Metric | Influencer Acquired | Overall Average |\n|--------|--------------------|--------------------|\n| New customers | [X] | - |\n| First order AOV | $[X] | $[X] |\n| Repeat purchase rate | [%] | [%] |\n| Customer lifetime value | $[X] | $[X] |\n\n### LTV-Based ROI\n\n**Formula**: (New Customers × Avg LTV) - Investment / Investment\n\n```\nNew Customers: [X]\nAverage LTV: $[X]\nTotal LTV: $[X]\nInvestment: $[X]\n\nLTV-Based ROI = ($[X] - $[X]) / $[X] × 100\nLTV-Based ROI = [X]%\n```\n\n### Short-term vs. Long-term View\n\n| Timeframe | Revenue | ROI |\n|-----------|---------|-----|\n| Immediate (this campaign) | $[X] | [X]% |\n| 6-month projected | $[X] | [X]% |\n| 12-month projected | $[X] | [X]% |\n| Lifetime projected | $[X] | [X]% |\n\n### Customer Quality Indicators\n\n| Indicator | Influencer-Acquired | Organic | Paid Ads |\n|-----------|--------------------|---------| ---------|\n| AOV | $[X] | $[X] | $[X] |\n| Return rate | [%] | [%] | [%] |\n| Repeat rate | [%] | [%] | [%] |\n| NPS/Satisfaction | [X] | [X] | [X] |\n```\n\n## Step 7 — Influencer-Level ROI\n\n```markdown\n## Influencer-Level ROI\n\n### Individual Influencer Performance\n\n| Influencer | Investment | Revenue | ROI | ROAS | Rank |\n|------------|------------|---------|-----|------|------|\n| @[handle1] | $[X] | $[X] | [X]% | [X]:1 | 1 |\n| @[handle2] | $[X] | $[X] | [X]% | [X]:1 | 2 |\n| @[handle3] | $[X] | $[X] | [X]% | [X]:1 | 3 |\n| @[handle4] | $[X] | $[X] | [X]% | [X]:1 | 4 |\n| @[handle5] | $[X] | $[X] | [X]% | [X]:1 | 5 |\n\n### ROI Distribution\n\n```\nInfluencer ROI Distribution:\n\n@handle1 |████████████████████| 320%\n@handle2 |██████████████ | 180%\n@handle3 |████████████ | 150%\n@handle4 |██████ | 75%\n@handle5 |████ | 45%\n\nCampaign Average: 180%\n```\n\n### Investment Efficiency\n\n| Influencer | % of Budget | % of Revenue | Efficiency |\n|------------|-------------|--------------|------------|\n| @[handle1] | [%] | [%] | [X]x |\n| @[handle2] | [%] | [%] | [X]x |\n\n### ROI by Tier\n\n| Tier | Investment | Revenue | ROI | Avg ROAS |\n|------|------------|---------|-----|----------|\n| Macro | $[X] | $[X] | [%] | [X]:1 |\n| Micro | $[X] | $[X] | [%] | [X]:1 |\n| Nano | $[X] | $[X] | [%] | [X]:1 |\n```\n\n## Step 8 — ROI Summary Report\n\n```markdown\n# ROI Summary Report\n\n## Campaign: [Name]\n## Period: [Dates]\n\n---\n\n## Investment Summary\n\n| Category | Amount | % of Total |\n|----------|--------|------------|\n| Influencer Fees | $[X] | [%] |\n| Product/Gifts | $[X] | [%] |\n| Amplification | $[X] | [%] |\n| Other | $[X] | [%] |\n| **Total Investment** | **$[X]** | **100%** |\n\n## Returns Summary\n\n| Return Type | Value |\n|-------------|-------|\n| Direct Revenue | $[X] |\n| Earned Media Value | $[X] |\n| New Customers | [X] |\n| Projected LTV | $[X] |\n\n## ROI by Methodology\n\n| Methodology | ROI | Notes |\n|-------------|-----|-------|\n| Direct Revenue ROI | [X]% | Hard returns |\n| ROAS | [X]:1 | Revenue per dollar |\n| EMV Multiple | [X]x | Media value generated |\n| LTV-Based ROI | [X]% | Long-term value |\n\n## Key Metrics\n\n| Metric | Result | Declared target (source/date) | Comparison |\n|--------|--------|-------------------------------|------------|\n| CPM | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPA | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| ROAS | [X]:1 | [X]:1 ([source], [date]) | [above/below/equal/pending] |\n\n## Bottom Line\n\n**Investment**: $[X]\n**Return**: $[X]\n**Net Profit**: $[X]\n**ROI**: [X]%\n\n**Assessment**: [Campaign was profitable/broke even/lost money]\n\n## Recommendations\n\n1. [Key recommendation 1]\n2. [Key recommendation 2]\n3. [Key recommendation 3]\n\n**Decision owner and precommitted rule**: [owner / rule / UNDECIDED]\n\n---\n\n*Report Generated: [Date]*\n```\n\n## Worked Example\n\n**User**: \"Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\"\n\n**Output**:\n\n```markdown\n# ROI Calculation Summary\n\n## Investment & Returns\n\n| Item | Value |\n|------|-------|\n| Total Investment | $25,000 |\n| Direct Revenue | $72,000 |\n| Total Reach | 2,100,000 |\n\n## ROI Results\n\n### Direct ROI\n- **Profit**: $47,000\n- **ROI**: 188%\n- **ROAS**: 2.88:1\n\nFor every $1 spent, you generated $2.88 in revenue.\n\n### Earned Media Value\n- **EMV** (directional scenario at a declared $8 CPM): $16,800\n- **EMV Multiple**: 0.67x\n\n### Cost Efficiency\n- **CPM**: $11.90\n- **CPA**: Unknown (conversion count was not supplied)\n\n## Assessment: Profitable on the supplied direct-revenue basis\n\nDirect revenue exceeds the supplied investment, but no source-dated peer target or incrementality evidence was provided. Do not infer benchmark outperformance or authorize a scale decision from this read alone; obtain verified conversions, attribution evidence, and the campaign owner's precommitted decision rule first.\n```\n\n## Benchmark Evidence Template\n\nDo not use a repository-default industry threshold. Supply a first-party target or a source-dated external comparator whose market, cohort, window, attribution, and cost basis are compatible with the campaign.\n\n| Field | Value |\n|-------|-------|\n| Metric | [ROAS / ROI / CPM / CPA / CAC / other] |\n| Target or distribution | [value, range, or quantile] |\n| Better direction | [higher/lower] |\n| Source | [publisher, report, URL, or first-party query] |\n| Publication/retrieval date | [YYYY-MM-DD] |\n| Market / industry / platform | [scope] |\n| Comparison cohort | [selection definition and sample size, if known] |\n| Observation window and lag | [dates] |\n| Attribution and conversion definition | [basis] |\n| Included costs / currency / FX date | [basis] |\n| Compatibility assessment | [compatible / materially different / unknown] |\n| Comparison status | [above / below / equal / pending] |\n\nFile v18.0.0:skill-card.md\n\n## Description:
\nCalculates influencer campaign ROI, ROAS, earned media value, attribution-modeled revenue, LTV-based ROI, cost-efficiency metrics, and measured Return evidence for stakeholder reporting.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nMarketing practitioners and agents use this skill to calculate and explain influencer campaign return from supplied spend, revenue, conversion, reach, engagement, attribution, and customer value data. It helps prepare ROI/ROAS, EMV, cost-efficiency, attribution, LTV, and measured Return evidence for reports and downstream campaign assessment.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: ROI or ROAS can be overstated when revenue, conversion, attribution, or benchmark inputs are unverified or not source-dated.
\nMitigation: Require source-dated targets and label each figure as measured, user-provided, calculated, or estimated before using the result for decisions.
\nRisk: Earned media value and attribution-modeled revenue are directional estimates that can be mistaken for directly measured return.
\nMitigation: Present EMV and attribution outputs with methodology, assumptions, uncertainty, and comparison basis rather than as absolute proof of incremental revenue.
\nRisk: The skill may write calculation files or promote headline numbers if the user authorizes persistence.
\nMitigation: Request separate authorization before saving or promoting durable metrics, and include attribution window, source, and uncertainty with any persisted headline number.
\n\n\n## Reference(s):
\n- [ROI templates](references/roi-templates.md)
\n- [ClawHub skill page](https://clawhub.ai/aaron-he-zhu/skills/roi-calculator)
\n- [Metadata homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, guidance]
\n**Output Format:** [Markdown summaries, tables, formulas, and optional saved calculation files]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [Labels figures as measured, user-provided, calculated, or estimated; persists files only with separate authorization.]
\n\n## Skill Version(s):
\n18.0.0 (source: server release metadata, target metadata, and skill frontmatter)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v17.0.0: 4 files, 11098 bytes\n\nFiles: references/roi-templates.md (12637b), skill-card.md (2780b), SKILL.md (12146b), _meta.json (134b)\n\nFile v17.0.0:SKILL.md\n\n---\nname: roi-calculator\nslug: aaron-roi-calculator\ndisplayName: \"ROI Calculator · ROI 计算\"\nsummary: \"活动投入产出核算:成本归集、收益口径与 CVI/ROI 汇总\"\ndescription: '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.'\nversion: \"17.0.0\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use when measuring or projecting influencer campaign ROI, justifying or defending budgets, comparing ROI across campaigns or channels, evaluating individual influencer or tier value, or preparing executive-level ROI numbers. Activate when the user supplies spend and results data and wants ROI, ROAS, EMV, CPA/CAC, attribution, or LTV impact computed.\"\nargument-hint: \" [revenue] [results data]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"17.0.0\", \"discipline\": \"influencer\", \"phase\": \"measure\", \"family\": \"influencer-marketing\", \"hermes\": {\"tags\": [\"marketing\", \"influencer\", \"measure\"], \"category\": \"influencer\"}, \"openclaw\": {\"emoji\": \"📣\", \"homepage\": \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"}}\n---\n\n# ROI Calculator\n\nThis skill helps you calculate and communicate the return on investment for influencer marketing campaigns using various methodologies appropriate for your goals and available data.\n\n> **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/`.\n\n## Quick Start\n\nShortest invocation:\n\n```\nCalculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\n```\n\nCommon scenario — compare methods before reporting:\n\n```\nWhat's the ROI of our campaign using direct revenue, EMV, and LTV-based methods?\n```\n\n## Skill Contract\n\n- **Reads**: campaign spend breakdown, results data (reach, impressions, engagements, clicks, conversions, revenue, new customers), AOV and repeat-rate data if LTV is in scope, any prior performance output from `performance-analyzer`.\n- **Writes**: ROI calculation file at `memory/influencer/roi-calculator/YYYY-MM-DD-.md` containing direct ROI/ROAS, EMV, cost-efficiency metrics, attribution-modeled revenue, LTV-based ROI, by-influencer ROI, and a summary report block.\n- **Promotes**: only with separate authorization, durable headline numbers with their attribution window, source, and uncertainty; a calculation request alone does not authorize hot-cache writes.\n- **Done when**:\n 1. At least one ROI methodology is computed with the inputs and formula shown.\n 2. Each headline metric is stated against a declared, source-dated comparison target; no universal benchmark is invented.\n 3. A bottom-line assessment (profitable / break-even / loss) and 1-3 recommendations are written.\n- **Primary next skill**: [report-generator](../report-generator/SKILL.md)\n\n### Handoff Summary\n\n> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).\n\n## Data Sources\n\nThis 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:\n\n- `~~social platform analytics` — reach, impressions, engagements, video views per platform for EMV and cost-per-metric math.\n- `~~ecommerce / analytics` — revenue, conversions, link clicks, and AOV for direct ROI and attribution.\n- `~~CRM` — new-customer counts, repeat-purchase rate, and lifetime value for LTV-based ROI.\n- `~~influencer database` — per-influencer fees and tier data for by-influencer ROI.\n\nWith 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.\n\n## Instructions\n\nWhen 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.\n\n1. **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))\n\n2. **Calculate direct ROI** — Simple ROI = (Revenue − Investment) / Investment × 100; ROAS = Revenue / Investment. State profit and a Profitable/Break-even/Loss assessment. ([template](references/roi-templates.md#step-2--direct-roi-calculation))\n\n3. **Calculate Earned Media Value (EMV)** — impression-based (Impressions × CPM / 1000) and engagement-based (Engagements × CPE), then average. Flag EMV as directional, not absolute. ([template](references/roi-templates.md#step-3--earned-media-value-emv))\n\n4. **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))\n\n5. **Apply attribution modeling** — run first-touch, last-touch, linear, time-decay, and position-based; recommend the model that fits the customer journey. ([template](references/roi-templates.md#step-5--attribution-analysis))\n\n6. **Calculate customer lifetime value impact** — LTV-Based ROI = (New Customers × Avg LTV − Investment) / Investment; project short- vs. long-term and compare customer quality to organic/paid. ([template](references/roi-templates.md#step-6--lifetime-value-analysis))\n\n7. **Calculate by-influencer ROI** — per-influencer ROI/ROAS rank, investment efficiency, and ROI by tier (macro/micro/nano). ([template](references/roi-templates.md#step-7--influencer-level-roi))\n\n8. **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))\n\n9. **Produce the typed C3 ROI scope and, when complete, CVI**\n\n Declare goal, profile `roi-`, `scope: roi`, `assessment_time: forecast|actual`, campaign `rollup_id`, observation date, and the same catalog version used by ACE/ART. Follow [`runtime-invocation.md`](../../../references/runtime-invocation.md), resolve `AARON_SKILLS_ROOT=\"${CLAUDE_PLUGIN_ROOT:-$(git rev-parse --show-toplevel 2>/dev/null || true)}\"`, verify the scorer and typed catalog, then score all 12 ROI items through `python3 \"$AARON_SKILLS_ROOT/scripts/rubric-score.py\" score `. If the standalone install lacks them, return `score_state: NOT_SCORED` / `score_confidence: not_scored` and do not hand-calculate or persist a typed result. Actual-only R1/R2/I1/I2/I3 items are N/A with reasons in a forecast read; they require evidence in an actual read. **This 0–100 rubric result is not financial ROI %** from steps 1-8: the financial outputs are evidence consumed by ROI.R items, never the CVI input themselves.\n\n ROI.I3 Fail emits `results-unverified`; report I1/I2/R1/R2 as low-confidence and do not make attributable-return claims. Preserve the scorer result rather than recomputing it in prose.\n\n For CVI, combine complete typed ACE results from [fit-scorer](../../discover/fit-scorer/SKILL.md), complete ART results from [content-reviewer](../../activate/content-reviewer/SKILL.md), and exactly one ROI result through `python3 \"$AARON_SKILLS_ROOT/scripts/rubric-score.py\" c3-rollup `:\n\n ```\n CVI = ( ACE_avg × ART_avg × ROI )^(1/3)\n ```\n\n Use the typed [`c3-rollup.schema.json`](../../../references/c3-rollup.schema.json) `components` form for real campaigns: positive budget weights for every ACE result, equal-weight ART results, and one ROI result. All components must share goal, `rollup_id`, observation date, assessment time, and catalog version. Keep the three aggregate scope scores beside CVI. If ACE/ART is missing, incomplete, or Unknown, emit ROI and mark CVI pending. If any component is `BLOCK` and therefore has no final scope score, **do not emit CVI**; report the blocking component instead of capping or averaging it.\n\n10. **Persist only with permission** — save under `memory/influencer/roi-calculator/` (or the paid path) only after authorization; request separate authorization for hot-cache promotion.\n\n## Example\n\n**User**: \"Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\"\n\n**Output**:\n\n```markdown\n# ROI Calculation Summary\n\n## Investment & Returns\n\n| Item | Value |\n|------|-------|\n| Total Investment | $25,000 |\n| Direct Revenue | $72,000 |\n| Total Reach | 2,100,000 |\n\n## ROI Results\n\n### Direct ROI\n- **Profit**: $47,000\n- **ROI**: 188%\n- **ROAS**: 2.88:1\n\nFor every $1 spent, you generated $2.88 in revenue.\n\n### Earned Media Value\n- **EMV** (directional scenario at a declared $8 CPM): $16,800\n- **EMV Multiple**: 0.67x\n\n### Cost Efficiency\n- **CPM**: $11.90\n- **CPA**: Unknown (conversion count was not supplied)\n\n## Assessment: Profitable on the supplied direct-revenue basis\n\nDirect revenue exceeds the supplied investment, but no source-dated peer target or incrementality evidence was provided. Do not infer benchmark outperformance or authorize a scale decision from this read alone; obtain verified conversions, attribution evidence, and the campaign owner's precommitted decision rule first.\n```\n\nThe source-dated benchmark evidence template lives in [references/roi-templates.md#benchmark-evidence-template](references/roi-templates.md#benchmark-evidence-template).\n\n## Reference Materials\n\n- [references/roi-templates.md](references/roi-templates.md) — fill-in templates for every Instructions step, the worked example, and benchmark evidence inputs.\n- [measurement-protocol.md](../../../references/measurement-protocol.md) — read ROI/CVI deltas against a control over the readback window; do not over-claim attribution.\n- [skill-contract.md](../../../references/skill-contract.md) — shared contract and Handoff Summary format.\n- [state-model.md](../../../references/state-model.md) — memory tiers and save-path conventions.\n- [CONNECTORS.md](../../../CONNECTORS.md) — free/keyless data recipe per connector category.\n- C³ scoring: [c3-benchmark.md](../../../references/c3-benchmark.md), [c3/roi-campaign-benchmark.md](../../../references/c3/roi-campaign-benchmark.md), and [c3-rollup.schema.json](../../../references/c3-rollup.schema.json) — typed ROI and multi-component CVI contracts.\n- [performance-analyzer](../performance-analyzer/SKILL.md) — supplies the results data this skill consumes.\n- [report-generator](../report-generator/SKILL.md) — wraps these numbers into a full report.\n- [budget-optimizer](../../plan/budget-optimizer/SKILL.md) — uses ROI output to reallocate spend.\n- [campaign-planner](../../plan/campaign-planner/SKILL.md) — sets the ROI targets these results are checked against.\n\n## Next Best Skill\n\n**Primary**: [report-generator](../report-generator/SKILL.md) — turn the ROI numbers into a stakeholder-ready report.\n\n**Alternates** (same Measure family):\n\n- [performance-analyzer](../performance-analyzer/SKILL.md) — go back for deeper performance breakdowns if the ROI math exposed gaps.\n- [budget-optimizer](../../plan/budget-optimizer/SKILL.md) — feed by-influencer and by-tier ROI into the next budget allocation.\n\nTermination note: keep a visited-set of skills invoked this session. If the primary next skill was already run, stop and report the chain complete rather than re-invoking it. Stop after at most 3 hops in a single chain.\n\nFile v17.0.0:_meta.json\n\n{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"roi-calculator\",\n \"version\": \"17.0.0\",\n \"publishedAt\": 1783787805107\n}\n\nFile v17.0.0:references/roi-templates.md\n\n# ROI Calculator — Templates & Benchmark Inputs\n\nFill-in templates for each methodology in [../SKILL.md](../SKILL.md) Instructions, plus the worked example and benchmark-evidence contract. Each block maps to a numbered step.\n\n## Step 1 — ROI Calculation Inputs\n\n```markdown\n### ROI Calculation Inputs\n\n**Campaign Details**:\n- Campaign: [name]\n- Duration: [dates]\n- Objective: [awareness/consideration/conversion]\n\n**Investment (Total Spend)**:\n| Category | Amount |\n|----------|--------|\n| Influencer fees | $[X] |\n| Product/Gifting | $[X] |\n| Production costs | $[X] |\n| Paid amplification | $[X] |\n| Agency/Tools | $[X] |\n| **Total Investment** | **$[X]** |\n\n**Results Data**:\n| Metric | Value |\n|--------|-------|\n| Total Reach | [X] |\n| Total Impressions | [X] |\n| Total Engagements | [X] |\n| Video Views | [X] |\n| Link Clicks | [X] |\n| Conversions/Sales | [X] |\n| Revenue | $[X] |\n| New Customers | [X] |\n```\n\n## Step 2 — Direct ROI Calculation\n\n```markdown\n## Direct ROI Calculation\n\n### Simple ROI\n\n**Formula**: (Revenue - Investment) / Investment × 100\n\n```\nRevenue: $[X]\nInvestment: $[X]\nProfit: $[X]\n\nROI = ($[Revenue] - $[Investment]) / $[Investment] × 100\nROI = [X]%\n```\n\n### Return on Ad Spend (ROAS)\n\n**Formula**: Revenue / Investment\n\n```\nROAS = $[Revenue] / $[Investment]\nROAS = [X]:1\n\nInterpretation: For every $1 spent, generated $[X] in revenue\n```\n\n### Direct ROI Summary\n\n| Metric | Value | Declared target (source/date) | Comparison |\n|--------|-------|-------------------------------|------------|\n| ROI % | [X]% | [X]% ([source], [date]) | [above/below/equal/pending] |\n| ROAS | [X]:1 | [X]:1 ([source], [date]) | [above/below/equal/pending] |\n| Profit | $[X] | Not applicable | Descriptive |\n\n**Assessment**: [Profitable/Break-even/Loss]\n```\n\n## Step 3 — Earned Media Value (EMV)\n\n```markdown\n## Earned Media Value Calculation\n\n### EMV Methodology\n\nEMV estimates the equivalent paid media cost to achieve the same results.\n\n### Impression-Based EMV\n\n**Formula**: Impressions × declared comparable CPM / 1000\n\n| Platform | Impressions | CPM | EMV |\n|----------|-------------|-----|-----|\n| Instagram | [X] | $[X] | $[X] |\n| TikTok | [X] | $[X] | $[X] |\n| YouTube | [X] | $[X] | $[X] |\n| **Total** | **[X]** | - | **$[X]** |\n\n### Engagement-Based EMV\n\n**Formula**: Engagements × Cost per Engagement\n\n| Engagement Type | Volume | CPE | EMV |\n|-----------------|--------|-----|-----|\n| Likes | [X] | $[X] | $[X] |\n| Comments | [X] | $[X] | $[X] |\n| Shares | [X] | $[X] | $[X] |\n| Saves | [X] | $[X] | $[X] |\n| Video Views | [X] | $[X] | $[X] |\n| **Total** | - | - | **$[X]** |\n\n### Combined EMV\n\n| Method | Value |\n|--------|-------|\n| Impression EMV | $[X] |\n| Engagement EMV | $[X] |\n| **Average EMV** | **$[X]** |\n\n### EMV ROI\n\n```\nEMV Generated: $[X]\nInvestment: $[X]\nEMV Multiple: [X]x\n\nFor every $1 spent, earned $[X] in equivalent media value\n```\n\n### EMV Caveats\n\n⚠️ **Note**: EMV is an estimate and varies by methodology. Use for directional comparison, not absolute measurement.\n```\n\n## Step 4 — Cost Efficiency Analysis\n\n```markdown\n## Cost Efficiency Analysis\n\n### Cost Per Metrics\n\n| Metric | Formula | Result | Declared target (source/date) | Comparison |\n|--------|---------|--------|-------------------------------|------------|\n| CPM | Spend ÷ (Impressions/1000) | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPR (Reach) | Spend ÷ (Reach/1000) | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPE | Spend ÷ Engagements | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPV (Video) | Spend ÷ Views | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPC | Spend ÷ Clicks | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPA | Spend ÷ Acquisitions | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CAC | Total Spend ÷ New Customers | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n\n### Comparison Contract\n\n| Field | Required value |\n|-------|----------------|\n| Target metric and rule | [metric, threshold/range, better direction] |\n| Source | [publisher or first-party cohort query] |\n| Publication/retrieval date | [YYYY-MM-DD] |\n| Market and comparison cohort | [market, industry, audience, platform] |\n| Observation window | [dates and lag] |\n| Attribution basis | [model and conversion definition] |\n| Cost and currency basis | [included costs, currency, FX date] |\n| Compatibility notes | [material differences or none] |\n\n**Comparison result**: [above/below/equal/pending]. Use `pending` when the target is absent, stale, or materially incompatible.\n\n### vs. Other Channels\n\nNormalize currency, included costs, observation window, and attribution before comparing channels.\n\n| Channel | CPA | Source/date | Comparable basis? | vs. Influencer |\n|---------|-----|-------------|-------------------|----------------|\n| Influencer Marketing | $[X] | [source/date] | Baseline | - |\n| Paid Social | $[X] | [source/date] | [yes/no] | [+/-X% or pending] |\n| Paid Search | $[X] | [source/date] | [yes/no] | [+/-X% or pending] |\n| Display Ads | $[X] | [source/date] | [yes/no] | [+/-X% or pending] |\n| Email Marketing | $[X] | [source/date] | [yes/no] | [+/-X% or pending] |\n```\n\n## Step 5 — Attribution Analysis\n\n```markdown\n## Attribution Analysis\n\n### Attribution Methods\n\n| Method | Description | Result | Notes |\n|--------|-------------|--------|-------|\n| First Touch | All credit to first interaction | $[X] | Awareness focus |\n| Last Touch | All credit to last interaction | $[X] | Conversion focus |\n| Linear | Equal credit across touchpoints | $[X] | Balanced view |\n| Time Decay | More credit to recent touches | $[X] | Recency bias |\n| Position Based | 40/20/40 first/middle/last | $[X] | Common B2C model |\n\n### Attributed Revenue by Model\n\n| Model | Attributed Revenue | ROI |\n|-------|-------------------|-----|\n| First Touch | $[X] | [X]% |\n| Last Touch | $[X] | [X]% |\n| Linear | $[X] | [X]% |\n| Time Decay | $[X] | [X]% |\n| Position Based | $[X] | [X]% |\n\n### Recommended Model for Your Business\n\n**Recommended**: [Model]\n**Rationale**: [Why this model fits your customer journey]\n\n### Multi-Touch Journey Example\n\n```\nCustomer Journey:\n\nDay 1: Sees @creator1 TikTok (Awareness) ─────┐\nDay 3: Sees @creator2 Instagram Reel ─────────┤\nDay 5: Clicks @creator1's link (Consideration)┼── Purchase Day 7\nDay 7: Uses @creator2's code (Conversion) ────┘\n\nAttribution:\nLast Touch: 100% to @creator2\nFirst Touch: 100% to @creator1\nLinear: 50% each\nPosition Based: 40% @creator1, 40% @creator2, 20% repeat exposure\n```\n```\n\n## Step 6 — Lifetime Value Analysis\n\n```markdown\n## Lifetime Value Analysis\n\n### New Customer Metrics\n\n| Metric | Influencer Acquired | Overall Average |\n|--------|--------------------|--------------------|\n| New customers | [X] | - |\n| First order AOV | $[X] | $[X] |\n| Repeat purchase rate | [%] | [%] |\n| Customer lifetime value | $[X] | $[X] |\n\n### LTV-Based ROI\n\n**Formula**: (New Customers × Avg LTV) - Investment / Investment\n\n```\nNew Customers: [X]\nAverage LTV: $[X]\nTotal LTV: $[X]\nInvestment: $[X]\n\nLTV-Based ROI = ($[X] - $[X]) / $[X] × 100\nLTV-Based ROI = [X]%\n```\n\n### Short-term vs. Long-term View\n\n| Timeframe | Revenue | ROI |\n|-----------|---------|-----|\n| Immediate (this campaign) | $[X] | [X]% |\n| 6-month projected | $[X] | [X]% |\n| 12-month projected | $[X] | [X]% |\n| Lifetime projected | $[X] | [X]% |\n\n### Customer Quality Indicators\n\n| Indicator | Influencer-Acquired | Organic | Paid Ads |\n|-----------|--------------------|---------| ---------|\n| AOV | $[X] | $[X] | $[X] |\n| Return rate | [%] | [%] | [%] |\n| Repeat rate | [%] | [%] | [%] |\n| NPS/Satisfaction | [X] | [X] | [X] |\n```\n\n## Step 7 — Influencer-Level ROI\n\n```markdown\n## Influencer-Level ROI\n\n### Individual Influencer Performance\n\n| Influencer | Investment | Revenue | ROI | ROAS | Rank |\n|------------|------------|---------|-----|------|------|\n| @[handle1] | $[X] | $[X] | [X]% | [X]:1 | 1 |\n| @[handle2] | $[X] | $[X] | [X]% | [X]:1 | 2 |\n| @[handle3] | $[X] | $[X] | [X]% | [X]:1 | 3 |\n| @[handle4] | $[X] | $[X] | [X]% | [X]:1 | 4 |\n| @[handle5] | $[X] | $[X] | [X]% | [X]:1 | 5 |\n\n### ROI Distribution\n\n```\nInfluencer ROI Distribution:\n\n@handle1 |████████████████████| 320%\n@handle2 |██████████████ | 180%\n@handle3 |████████████ | 150%\n@handle4 |██████ | 75%\n@handle5 |████ | 45%\n\nCampaign Average: 180%\n```\n\n### Investment Efficiency\n\n| Influencer | % of Budget | % of Revenue | Efficiency |\n|------------|-------------|--------------|------------|\n| @[handle1] | [%] | [%] | [X]x |\n| @[handle2] | [%] | [%] | [X]x |\n\n### ROI by Tier\n\n| Tier | Investment | Revenue | ROI | Avg ROAS |\n|------|------------|---------|-----|----------|\n| Macro | $[X] | $[X] | [%] | [X]:1 |\n| Micro | $[X] | $[X] | [%] | [X]:1 |\n| Nano | $[X] | $[X] | [%] | [X]:1 |\n```\n\n## Step 8 — ROI Summary Report\n\n```markdown\n# ROI Summary Report\n\n## Campaign: [Name]\n## Period: [Dates]\n\n---\n\n## Investment Summary\n\n| Category | Amount | % of Total |\n|----------|--------|------------|\n| Influencer Fees | $[X] | [%] |\n| Product/Gifts | $[X] | [%] |\n| Amplification | $[X] | [%] |\n| Other | $[X] | [%] |\n| **Total Investment** | **$[X]** | **100%** |\n\n## Returns Summary\n\n| Return Type | Value |\n|-------------|-------|\n| Direct Revenue | $[X] |\n| Earned Media Value | $[X] |\n| New Customers | [X] |\n| Projected LTV | $[X] |\n\n## ROI by Methodology\n\n| Methodology | ROI | Notes |\n|-------------|-----|-------|\n| Direct Revenue ROI | [X]% | Hard returns |\n| ROAS | [X]:1 | Revenue per dollar |\n| EMV Multiple | [X]x | Media value generated |\n| LTV-Based ROI | [X]% | Long-term value |\n\n## Key Metrics\n\n| Metric | Result | Declared target (source/date) | Comparison |\n|--------|--------|-------------------------------|------------|\n| CPM | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| CPA | $[X] | $[X] ([source], [date]) | [above/below/equal/pending] |\n| ROAS | [X]:1 | [X]:1 ([source], [date]) | [above/below/equal/pending] |\n\n## Bottom Line\n\n**Investment**: $[X]\n**Return**: $[X]\n**Net Profit**: $[X]\n**ROI**: [X]%\n\n**Assessment**: [Campaign was profitable/broke even/lost money]\n\n## Recommendations\n\n1. [Key recommendation 1]\n2. [Key recommendation 2]\n3. [Key recommendation 3]\n\n**Decision owner and precommitted rule**: [owner / rule / UNDECIDED]\n\n---\n\n*Report Generated: [Date]*\n```\n\n## Worked Example\n\n**User**: \"Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\"\n\n**Output**:\n\n```markdown\n# ROI Calculation Summary\n\n## Investment & Returns\n\n| Item | Value |\n|------|-------|\n| Total Investment | $25,000 |\n| Direct Revenue | $72,000 |\n| Total Reach | 2,100,000 |\n\n## ROI Results\n\n### Direct ROI\n- **Profit**: $47,000\n- **ROI**: 188%\n- **ROAS**: 2.88:1\n\nFor every $1 spent, you generated $2.88 in revenue.\n\n### Earned Media Value\n- **EMV** (directional scenario at a declared $8 CPM): $16,800\n- **EMV Multiple**: 0.67x\n\n### Cost Efficiency\n- **CPM**: $11.90\n- **CPA**: Unknown (conversion count was not supplied)\n\n## Assessment: Profitable on the supplied direct-revenue basis\n\nDirect revenue exceeds the supplied investment, but no source-dated peer target or incrementality evidence was provided. Do not infer benchmark outperformance or authorize a scale decision from this read alone; obtain verified conversions, attribution evidence, and the campaign owner's precommitted decision rule first.\n```\n\n## Benchmark Evidence Template\n\nDo not use a repository-default industry threshold. Supply a first-party target or a source-dated external comparator whose market, cohort, window, attribution, and cost basis are compatible with the campaign.\n\n| Field | Value |\n|-------|-------|\n| Metric | [ROAS / ROI / CPM / CPA / CAC / other] |\n| Target or distribution | [value, range, or quantile] |\n| Better direction | [higher/lower] |\n| Source | [publisher, report, URL, or first-party query] |\n| Publication/retrieval date | [YYYY-MM-DD] |\n| Market / industry / platform | [scope] |\n| Comparison cohort | [selection definition and sample size, if known] |\n| Observation window and lag | [dates] |\n| Attribution and conversion definition | [basis] |\n| Included costs / currency / FX date | [basis] |\n| Compatibility assessment | [compatible / materially different / unknown] |\n| Comparison status | [above / below / equal / pending] |\n\nFile v17.0.0:skill-card.md\n\n## Description:
\nUse when the user asks to calculate influencer ROI, prove campaign value, or evaluate ROAS; produces direct ROI/ROAS, earned media value, attribution-modeled revenue, LTV-based ROI, and a stakeholder-ready summary.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nMarketing and growth teams use this skill to measure or project influencer campaign ROI, compare campaigns or channels, evaluate influencer value, and prepare executive-level ROI numbers from supplied spend, revenue, attribution, and results data.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: ROI outputs may be mistaken for verified financial truth when source campaign inputs, attribution windows, or benchmarks are incomplete.
\nMitigation: Require accurate spend, revenue, attribution, and benchmark inputs; compare headline metrics only against declared, source-dated targets and label unresolved comparisons as pending.
\nRisk: Durable memory saves or hot-cache promotion could preserve figures before assumptions and uncertainty are ready to retain.
\nMitigation: Persist calculation files and promote headline metrics only after separate user authorization that includes attribution window, source, and uncertainty.
\nRisk: C3/CVI rubric scores could be confused with financial ROI percentages.
\nMitigation: Keep financial ROI outputs separate from typed C3/CVI scorer results and report missing or unverified scorer evidence as pending or not scored.
\n\n\n## Reference(s):
\n- [ROI Templates and Benchmark Inputs](artifact/references/roi-templates.md)
\n- [ClawHub Skill Page](https://clawhub.ai/aaron-he-zhu/skills/roi-calculator)
\n- [Publisher Homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, shell commands, guidance]
\n**Output Format:** [Markdown ROI summaries, calculation tables, attribution notes, and optional scorer command guidance]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [May propose memory files or hot-cache promotion only after separate user authorization; distinguishes financial ROI percentages from C3/CVI rubric scores.]
\n\n## Skill Version(s):
\n17.0.0 (source: server release evidence and artifact frontmatter)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v16.0.1: 4 files, 9761 bytes\n\nFiles: references/roi-templates.md (10396b), skill-card.md (2534b), SKILL.md (10717b), _meta.json (134b)\n\nFile v16.0.1:SKILL.md\n\n---\nname: roi-calculator\nslug: aaron-roi-calculator\ndisplayName: \"ROI Calculator · ROI 计算\"\nsummary: \"活动投入产出核算:成本归集、收益口径与 CVI/ROI 汇总\"\ndescription: '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.'\nversion: \"16.0.1\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use when measuring or projecting influencer campaign ROI, justifying or defending budgets, comparing ROI across campaigns or channels, evaluating individual influencer or tier value, or preparing executive-level ROI numbers. Activate when the user supplies spend and results data and wants ROI, ROAS, EMV, CPA/CAC, attribution, or LTV impact computed.\"\nargument-hint: \" [revenue] [results data]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"16.0.1\", \"discipline\": \"influencer\", \"phase\": \"measure\", \"family\": \"influencer-marketing\", \"hermes\": {\"tags\": [\"marketing\", \"influencer\", \"measure\"], \"category\": \"influencer\"}, \"openclaw\": {\"emoji\": \"📣\", \"homepage\": \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"}}\n---\n\n# ROI Calculator\n\nThis skill helps you calculate and communicate the return on investment for influencer marketing campaigns using various methodologies appropriate for your goals and available data.\n\n> **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/`.\n\n## Quick Start\n\nShortest invocation:\n\n```\nCalculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\n```\n\nCommon scenario — compare methods before reporting:\n\n```\nWhat's the ROI of our campaign using direct revenue, EMV, and LTV-based methods?\n```\n\n## Skill Contract\n\n- **Reads**: campaign spend breakdown, results data (reach, impressions, engagements, clicks, conversions, revenue, new customers), AOV and repeat-rate data if LTV is in scope, any prior performance output from `performance-analyzer`.\n- **Writes**: ROI calculation file at `memory/influencer/roi-calculator/YYYY-MM-DD-.md` containing direct ROI/ROAS, EMV, cost-efficiency metrics, attribution-modeled revenue, LTV-based ROI, by-influencer ROI, and a summary report block.\n- **Promotes**: durable headline numbers (final ROI %, ROAS, total investment, net profit, recommended attribution model) to `memory/hot-cache.md`.\n- **Done when**:\n 1. At least one ROI methodology is computed with the inputs and formula shown.\n 2. Each headline metric is stated against a benchmark with a pass/fail status.\n 3. A bottom-line assessment (profitable / break-even / loss) and 1-3 recommendations are written.\n- **Primary next skill**: [report-generator](../report-generator/SKILL.md)\n\n### Handoff Summary\n\n> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).\n\n## Data Sources\n\nThis 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:\n\n- `~~social platform analytics` — reach, impressions, engagements, video views per platform for EMV and cost-per-metric math.\n- `~~ecommerce / analytics` — revenue, conversions, link clicks, and AOV for direct ROI and attribution.\n- `~~CRM` — new-customer counts, repeat-purchase rate, and lifetime value for LTV-based ROI.\n- `~~influencer database` — per-influencer fees and tier data for by-influencer ROI.\n\nWith 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.\n\n## Instructions\n\nWhen 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.\n\n1. **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))\n\n2. **Calculate direct ROI** — Simple ROI = (Revenue − Investment) / Investment × 100; ROAS = Revenue / Investment. State profit and a Profitable/Break-even/Loss assessment. ([template](references/roi-templates.md#step-2--direct-roi-calculation))\n\n3. **Calculate Earned Media Value (EMV)** — impression-based (Impressions × CPM / 1000) and engagement-based (Engagements × CPE), then average. Flag EMV as directional, not absolute. ([template](references/roi-templates.md#step-3--earned-media-value-emv))\n\n4. **Calculate cost-efficiency metrics** — CPM, CPR, CPE, CPV, CPC, CPA, CAC, each against a benchmark; rate the campaign and compare CPA to other channels. ([template](references/roi-templates.md#step-4--cost-efficiency-analysis))\n\n5. **Apply attribution modeling** — run first-touch, last-touch, linear, time-decay, and position-based; recommend the model that fits the customer journey. ([template](references/roi-templates.md#step-5--attribution-analysis))\n\n6. **Calculate customer lifetime value impact** — LTV-Based ROI = (New Customers × Avg LTV − Investment) / Investment; project short- vs. long-term and compare customer quality to organic/paid. ([template](references/roi-templates.md#step-6--lifetime-value-analysis))\n\n7. **Calculate by-influencer ROI** — per-influencer ROI/ROAS rank, investment efficiency, and ROI by tier (macro/micro/nano). ([template](references/roi-templates.md#step-7--influencer-level-roi))\n\n8. **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))\n\n9. **Roll up into the C³ Campaign Value Index (CVI)**\n\n This skill emits the **ROI** scope score of [C³](../../../references/c3-benchmark.md) and the **CVI** rollup. Score ROI on the **0–100 rubric** in [c3/roi-campaign-benchmark.md](../../../references/c3/roi-campaign-benchmark.md) (Return · Orchestration · Impact, each on Pass/Partial/Fail → scaled to 0–100). **This 0–100 ROI score is not the financial ROI % from steps 1–8** — feed the rubric score into the formula, never the percentage (R1 simply *consumes* your ROI%/ROAS as one of its inputs). Then combine it with the Creator and Content scope scores — from [fit-scorer](../../discover/fit-scorer/SKILL.md) (ACE) and [content-reviewer](../../activate/content-reviewer/SKILL.md) (ART) — as a geometric mean:\n\n ```\n CVI = ( ACE_avg × ART_avg × ROI )^(1/3)\n ```\n\n `ACE_avg` is the **budget-weighted** mean of the campaign's creator ACE scores; `ART_avg` is the simple mean of its content ART scores (per scoring-architecture §8). Keep the three scope scores beside the CVI — the index ranks and alerts, the three scores diagnose. If ACE or ART is unavailable, emit the ROI score and mark CVI **pending (needs ACE/ART)** rather than guessing. A blocked scope (e.g. an ART T1/T2 veto on the content, or an ACE A2/C1/E2 veto on the creator) caps the rollup — surface it, don't average it away.\n\n## Example\n\n**User**: \"Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\"\n\n**Output**:\n\n```markdown\n# ROI Calculation Summary\n\n## Investment & Returns\n\n| Item | Value |\n|------|-------|\n| Total Investment | $25,000 |\n| Direct Revenue | $72,000 |\n| Total Reach | 2,100,000 |\n\n## ROI Results\n\n### Direct ROI\n- **Profit**: $47,000\n- **ROI**: 188%\n- **ROAS**: 2.88:1\n\nFor every $1 spent, you generated $2.88 in revenue.\n\n### Earned Media Value\n- **EMV** (at $8 CPM): $16,800\n- **EMV Multiple**: 0.67x\n\n### Cost Efficiency\n- **CPM**: $11.90 (Good)\n- **Est. CPA**: ~$54 (if 460 conversions)\n\n## Assessment: ✅ Strong Performance\n\nThis campaign outperformed the typical 2:1 ROAS benchmark for influencer marketing. Recommend increasing investment in similar campaigns.\n```\n\nIndustry ROAS benchmarks (Beauty, Fashion, Food & Beverage, Tech, Health) live in [references/roi-templates.md#industry-roi-benchmarks](references/roi-templates.md#industry-roi-benchmarks).\n\n## Reference Materials\n\n- [references/roi-templates.md](references/roi-templates.md) — fill-in templates for every Instructions step, the worked example, and industry ROAS benchmarks.\n- [measurement-protocol.md](../../../references/measurement-protocol.md) — read ROI/CVI deltas against a control over the readback window; do not over-claim attribution.\n- [skill-contract.md](../../../references/skill-contract.md) — shared contract and Handoff Summary format.\n- [state-model.md](../../../references/state-model.md) — memory tiers and save-path conventions.\n- [CONNECTORS.md](../../../CONNECTORS.md) — free/keyless data recipe per connector category.\n- C³ scoring: [c3-benchmark.md](../../../references/c3-benchmark.md) (CVI rollup formula) and [c3/roi-campaign-benchmark.md](../../../references/c3/roi-campaign-benchmark.md) — the ROI Campaign rubric this skill emits into the CVI.\n- [performance-analyzer](../performance-analyzer/SKILL.md) — supplies the results data this skill consumes.\n- [report-generator](../report-generator/SKILL.md) — wraps these numbers into a full report.\n- [budget-optimizer](../../plan/budget-optimizer/SKILL.md) — uses ROI output to reallocate spend.\n- [campaign-planner](../../plan/campaign-planner/SKILL.md) — sets the ROI targets these results are checked against.\n\n## Next Best Skill\n\n**Primary**: [report-generator](../report-generator/SKILL.md) — turn the ROI numbers into a stakeholder-ready report.\n\n**Alternates** (same Measure family):\n\n- [performance-analyzer](../performance-analyzer/SKILL.md) — go back for deeper performance breakdowns if the ROI math exposed gaps.\n- [budget-optimizer](../../plan/budget-optimizer/SKILL.md) — feed by-influencer and by-tier ROI into the next budget allocation.\n\nTermination note: keep a visited-set of skills invoked this session. If the primary next skill was already run, stop and report the chain complete rather than re-invoking it. Stop after at most 3 hops in a single chain.\n\nFile v16.0.1:_meta.json\n\n{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"roi-calculator\",\n \"version\": \"16.0.1\",\n \"publishedAt\": 1783515713106\n}\n\nFile v16.0.1:references/roi-templates.md\n\n# ROI Calculator — Templates & Benchmarks\n\nFill-in templates for each methodology in [../SKILL.md](../SKILL.md) Instructions, plus the worked example and industry ROAS benchmarks. Each block maps to a numbered step.\n\n## Step 1 — ROI Calculation Inputs\n\n```markdown\n### ROI Calculation Inputs\n\n**Campaign Details**:\n- Campaign: [name]\n- Duration: [dates]\n- Objective: [awareness/consideration/conversion]\n\n**Investment (Total Spend)**:\n| Category | Amount |\n|----------|--------|\n| Influencer fees | $[X] |\n| Product/Gifting | $[X] |\n| Production costs | $[X] |\n| Paid amplification | $[X] |\n| Agency/Tools | $[X] |\n| **Total Investment** | **$[X]** |\n\n**Results Data**:\n| Metric | Value |\n|--------|-------|\n| Total Reach | [X] |\n| Total Impressions | [X] |\n| Total Engagements | [X] |\n| Video Views | [X] |\n| Link Clicks | [X] |\n| Conversions/Sales | [X] |\n| Revenue | $[X] |\n| New Customers | [X] |\n```\n\n## Step 2 — Direct ROI Calculation\n\n```markdown\n## Direct ROI Calculation\n\n### Simple ROI\n\n**Formula**: (Revenue - Investment) / Investment × 100\n\n```\nRevenue: $[X]\nInvestment: $[X]\nProfit: $[X]\n\nROI = ($[Revenue] - $[Investment]) / $[Investment] × 100\nROI = [X]%\n```\n\n### Return on Ad Spend (ROAS)\n\n**Formula**: Revenue / Investment\n\n```\nROAS = $[Revenue] / $[Investment]\nROAS = [X]:1\n\nInterpretation: For every $1 spent, generated $[X] in revenue\n```\n\n### Direct ROI Summary\n\n| Metric | Value | Benchmark | Status |\n|--------|-------|-----------|--------|\n| ROI % | [X]% | [X]% | ✅/❌ |\n| ROAS | [X]:1 | [X]:1 | ✅/❌ |\n| Profit | $[X] | - | |\n\n**Assessment**: [Profitable/Break-even/Loss]\n```\n\n## Step 3 — Earned Media Value (EMV)\n\n```markdown\n## Earned Media Value Calculation\n\n### EMV Methodology\n\nEMV estimates the equivalent paid media cost to achieve the same results.\n\n### Impression-Based EMV\n\n**Formula**: Impressions × Industry CPM / 1000\n\n| Platform | Impressions | CPM | EMV |\n|----------|-------------|-----|-----|\n| Instagram | [X] | $[X] | $[X] |\n| TikTok | [X] | $[X] | $[X] |\n| YouTube | [X] | $[X] | $[X] |\n| **Total** | **[X]** | - | **$[X]** |\n\n### Engagement-Based EMV\n\n**Formula**: Engagements × Cost per Engagement\n\n| Engagement Type | Volume | CPE | EMV |\n|-----------------|--------|-----|-----|\n| Likes | [X] | $[X] | $[X] |\n| Comments | [X] | $[X] | $[X] |\n| Shares | [X] | $[X] | $[X] |\n| Saves | [X] | $[X] | $[X] |\n| Video Views | [X] | $[X] | $[X] |\n| **Total** | - | - | **$[X]** |\n\n### Combined EMV\n\n| Method | Value |\n|--------|-------|\n| Impression EMV | $[X] |\n| Engagement EMV | $[X] |\n| **Average EMV** | **$[X]** |\n\n### EMV ROI\n\n```\nEMV Generated: $[X]\nInvestment: $[X]\nEMV Multiple: [X]x\n\nFor every $1 spent, earned $[X] in equivalent media value\n```\n\n### EMV Caveats\n\n⚠️ **Note**: EMV is an estimate and varies by methodology. Use for directional comparison, not absolute measurement.\n```\n\n## Step 4 — Cost Efficiency Analysis\n\n```markdown\n## Cost Efficiency Analysis\n\n### Cost Per Metrics\n\n| Metric | Formula | Result | Benchmark | Status |\n|--------|---------|--------|-----------|--------|\n| CPM | Spend ÷ (Impressions/1000) | $[X] | $[X] | ✅/❌ |\n| CPR (Reach) | Spend ÷ (Reach/1000) | $[X] | $[X] | ✅/❌ |\n| CPE | Spend ÷ Engagements | $[X] | $[X] | ✅/❌ |\n| CPV (Video) | Spend ÷ Views | $[X] | $[X] | ✅/❌ |\n| CPC | Spend ÷ Clicks | $[X] | $[X] | ✅/❌ |\n| CPA | Spend ÷ Acquisitions | $[X] | $[X] | ✅/❌ |\n| CAC | Total Spend ÷ New Customers | $[X] | $[X] | ✅/❌ |\n\n### Efficiency Score\n\n| Rating | CPM Range | CPC Range | CPA Range |\n|--------|-----------|-----------|-----------|\n| Excellent | <$[X] | <$[X] | <$[X] |\n| Good | $[X]-$[X] | $[X]-$[X] | $[X]-$[X] |\n| Average | $[X]-$[X] | $[X]-$[X] | $[X]-$[X] |\n| Below Avg | $[X]-$[X] | $[X]-$[X] | $[X]-$[X] |\n| Poor | >$[X] | >$[X] | >$[X] |\n\n**Your Campaign**: [Rating]\n\n### vs. Other Channels\n\n| Channel | CPA | vs. Influencer |\n|---------|-----|----------------|\n| Influencer Marketing | $[X] | - |\n| Paid Social | $[X] | [+/-X%] |\n| Paid Search | $[X] | [+/-X%] |\n| Display Ads | $[X] | [+/-X%] |\n| Email Marketing | $[X] | [+/-X%] |\n```\n\n## Step 5 — Attribution Analysis\n\n```markdown\n## Attribution Analysis\n\n### Attribution Methods\n\n| Method | Description | Result | Notes |\n|--------|-------------|--------|-------|\n| First Touch | All credit to first interaction | $[X] | Awareness focus |\n| Last Touch | All credit to last interaction | $[X] | Conversion focus |\n| Linear | Equal credit across touchpoints | $[X] | Balanced view |\n| Time Decay | More credit to recent touches | $[X] | Recency bias |\n| Position Based | 40/20/40 first/middle/last | $[X] | Common B2C model |\n\n### Attributed Revenue by Model\n\n| Model | Attributed Revenue | ROI |\n|-------|-------------------|-----|\n| First Touch | $[X] | [X]% |\n| Last Touch | $[X] | [X]% |\n| Linear | $[X] | [X]% |\n| Time Decay | $[X] | [X]% |\n| Position Based | $[X] | [X]% |\n\n### Recommended Model for Your Business\n\n**Recommended**: [Model]\n**Rationale**: [Why this model fits your customer journey]\n\n### Multi-Touch Journey Example\n\n```\nCustomer Journey:\n\nDay 1: Sees @creator1 TikTok (Awareness) ─────┐\nDay 3: Sees @creator2 Instagram Reel ─────────┤\nDay 5: Clicks @creator1's link (Consideration)┼── Purchase Day 7\nDay 7: Uses @creator2's code (Conversion) ────┘\n\nAttribution:\nLast Touch: 100% to @creator2\nFirst Touch: 100% to @creator1\nLinear: 50% each\nPosition Based: 40% @creator1, 40% @creator2, 20% repeat exposure\n```\n```\n\n## Step 6 — Lifetime Value Analysis\n\n```markdown\n## Lifetime Value Analysis\n\n### New Customer Metrics\n\n| Metric | Influencer Acquired | Overall Average |\n|--------|--------------------|--------------------|\n| New customers | [X] | - |\n| First order AOV | $[X] | $[X] |\n| Repeat purchase rate | [%] | [%] |\n| Customer lifetime value | $[X] | $[X] |\n\n### LTV-Based ROI\n\n**Formula**: (New Customers × Avg LTV) - Investment / Investment\n\n```\nNew Customers: [X]\nAverage LTV: $[X]\nTotal LTV: $[X]\nInvestment: $[X]\n\nLTV-Based ROI = ($[X] - $[X]) / $[X] × 100\nLTV-Based ROI = [X]%\n```\n\n### Short-term vs. Long-term View\n\n| Timeframe | Revenue | ROI |\n|-----------|---------|-----|\n| Immediate (this campaign) | $[X] | [X]% |\n| 6-month projected | $[X] | [X]% |\n| 12-month projected | $[X] | [X]% |\n| Lifetime projected | $[X] | [X]% |\n\n### Customer Quality Indicators\n\n| Indicator | Influencer-Acquired | Organic | Paid Ads |\n|-----------|--------------------|---------| ---------|\n| AOV | $[X] | $[X] | $[X] |\n| Return rate | [%] | [%] | [%] |\n| Repeat rate | [%] | [%] | [%] |\n| NPS/Satisfaction | [X] | [X] | [X] |\n```\n\n## Step 7 — Influencer-Level ROI\n\n```markdown\n## Influencer-Level ROI\n\n### Individual Influencer Performance\n\n| Influencer | Investment | Revenue | ROI | ROAS | Rank |\n|------------|------------|---------|-----|------|------|\n| @[handle1] | $[X] | $[X] | [X]% | [X]:1 | 1 |\n| @[handle2] | $[X] | $[X] | [X]% | [X]:1 | 2 |\n| @[handle3] | $[X] | $[X] | [X]% | [X]:1 | 3 |\n| @[handle4] | $[X] | $[X] | [X]% | [X]:1 | 4 |\n| @[handle5] | $[X] | $[X] | [X]% | [X]:1 | 5 |\n\n### ROI Distribution\n\n```\nInfluencer ROI Distribution:\n\n@handle1 |████████████████████| 320%\n@handle2 |██████████████ | 180%\n@handle3 |████████████ | 150%\n@handle4 |██████ | 75%\n@handle5 |████ | 45%\n\nCampaign Average: 180%\n```\n\n### Investment Efficiency\n\n| Influencer | % of Budget | % of Revenue | Efficiency |\n|------------|-------------|--------------|------------|\n| @[handle1] | [%] | [%] | [X]x |\n| @[handle2] | [%] | [%] | [X]x |\n\n### ROI by Tier\n\n| Tier | Investment | Revenue | ROI | Avg ROAS |\n|------|------------|---------|-----|----------|\n| Macro | $[X] | $[X] | [%] | [X]:1 |\n| Micro | $[X] | $[X] | [%] | [X]:1 |\n| Nano | $[X] | $[X] | [%] | [X]:1 |\n```\n\n## Step 8 — ROI Summary Report\n\n```markdown\n# ROI Summary Report\n\n## Campaign: [Name]\n## Period: [Dates]\n\n---\n\n## Investment Summary\n\n| Category | Amount | % of Total |\n|----------|--------|------------|\n| Influencer Fees | $[X] | [%] |\n| Product/Gifts | $[X] | [%] |\n| Amplification | $[X] | [%] |\n| Other | $[X] | [%] |\n| **Total Investment** | **$[X]** | **100%** |\n\n## Returns Summary\n\n| Return Type | Value |\n|-------------|-------|\n| Direct Revenue | $[X] |\n| Earned Media Value | $[X] |\n| New Customers | [X] |\n| Projected LTV | $[X] |\n\n## ROI by Methodology\n\n| Methodology | ROI | Notes |\n|-------------|-----|-------|\n| Direct Revenue ROI | [X]% | Hard returns |\n| ROAS | [X]:1 | Revenue per dollar |\n| EMV Multiple | [X]x | Media value generated |\n| LTV-Based ROI | [X]% | Long-term value |\n\n## Key Metrics\n\n| Metric | Result | Benchmark | Status |\n|--------|--------|-----------|--------|\n| CPM | $[X] | $[X] | ✅/❌ |\n| CPA | $[X] | $[X] | ✅/❌ |\n| ROAS | [X]:1 | [X]:1 | ✅/❌ |\n\n## Bottom Line\n\n**Investment**: $[X]\n**Return**: $[X]\n**Net Profit**: $[X]\n**ROI**: [X]%\n\n**Assessment**: [Campaign was profitable/broke even/lost money]\n\n## Recommendations\n\n1. [Key recommendation 1]\n2. [Key recommendation 2]\n3. [Key recommendation 3]\n\n---\n\n*Report Generated: [Date]*\n```\n\n## Worked Example\n\n**User**: \"Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\"\n\n**Output**:\n\n```markdown\n# ROI Calculation Summary\n\n## Investment & Returns\n\n| Item | Value |\n|------|-------|\n| Total Investment | $25,000 |\n| Direct Revenue | $72,000 |\n| Total Reach | 2,100,000 |\n\n## ROI Results\n\n### Direct ROI\n- **Profit**: $47,000\n- **ROI**: 188%\n- **ROAS**: 2.88:1\n\nFor every $1 spent, you generated $2.88 in revenue.\n\n### Earned Media Value\n- **EMV** (at $8 CPM): $16,800\n- **EMV Multiple**: 0.67x\n\n### Cost Efficiency\n- **CPM**: $11.90 (Good)\n- **Est. CPA**: ~$54 (if 460 conversions)\n\n## Assessment: ✅ Strong Performance\n\nThis campaign outperformed the typical 2:1 ROAS benchmark for influencer marketing. Recommend increasing investment in similar campaigns.\n```\n\n## Industry ROI Benchmarks\n\n| Industry | Avg ROAS | Good ROAS | Excellent ROAS |\n|----------|----------|-----------|----------------|\n| Beauty/Skincare | 3:1 | 5:1 | 8:1 |\n| Fashion | 2.5:1 | 4:1 | 6:1 |\n| Food & Beverage | 2:1 | 3.5:1 | 5:1 |\n| Tech/Electronics | 2:1 | 3:1 | 4:1 |\n| Health/Fitness | 2.5:1 | 4:1 | 6:1 |\n\nFile v16.0.1:skill-card.md\n\n## Description:
\nCalculates influencer marketing ROI/ROAS, earned media value, attribution-modeled revenue, LTV-based ROI, and stakeholder-ready summaries from user-supplied campaign metrics.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nMarketing teams and analysts use this skill to measure or project influencer campaign value, compare ROI across creators or channels, and prepare executive-level ROI, ROAS, EMV, attribution, CPA/CAC, LTV, and CVI numbers.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Campaign spend, revenue, attribution, and customer-value summaries may be persisted in agent memory.
\nMitigation: Use only business data approved for that environment and clear or restrict memory where needed.
\nRisk: Optional CRM, ecommerce, social analytics, or influencer database connectors can expose sensitive commercial or customer data.
\nMitigation: Review connector scopes before enabling integrations and grant only the access needed for the ROI calculation.
\nRisk: Earned media value, attribution-modeled revenue, and CVI rollups are estimates that can mislead stakeholders if treated as exact financial outcomes.
\nMitigation: Show formulas and assumptions, label EMV as directional, and review source data and benchmarks before using outputs for budget decisions.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/aaron-he-zhu/skills/roi-calculator)
\n- [Project homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)
\n- [ROI templates and benchmarks](references/roi-templates.md)
\n\n\n## Skill Output:
\n**Output Type(s):** [Text, Markdown, Analysis, Files, Guidance]
\n**Output Format:** [Markdown with tables, formulas, benchmark statuses, and summary recommendations]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [May save ROI calculation notes and headline metrics to agent memory when the host supports memory.]
\n\n## Skill Version(s):
\n16.0.1 (source: server release metadata and SKILL.md frontmatter)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v16.0.0: 4 files, 9749 bytes\n\nFiles: references/roi-templates.md (10396b), skill-card.md (2512b), SKILL.md (10715b), _meta.json (134b)\n\nFile v16.0.0:SKILL.md\n\n---\nname: roi-calculator\nslug: aaron-roi-calculator\ndisplayName: \"ROI Calculator · ROI 计算\"\nsummary: \"活动投入产出核算:成本归集、收益口径与 CVI/ROI 汇总\"\ndescription: '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.'\nversion: \"16.0.0\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use when measuring or projecting influencer campaign ROI, justifying or defending budgets, comparing ROI across campaigns or channels, evaluating individual influencer or tier value, or preparing executive-level ROI numbers. Activate when the user supplies spend and results data and wants ROI, ROAS, EMV, CPA/CAC, attribution, or LTV impact computed.\"\nargument-hint: \" [revenue] [results data]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"16.0.0\", \"discipline\": \"influencer\", \"phase\": \"measure\", \"family\": \"influencer-marketing\", \"hermes\": {\"tags\": [\"marketing\", \"influencer\", \"measure\"], \"category\": \"influencer\"}, \"openclaw\": {\"emoji\": \"📣\", \"homepage\": \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"}}\n---\n\n# ROI Calculator\n\nThis skill helps you calculate and communicate the return on investment for influencer marketing campaigns using various methodologies appropriate for your goals and available data.\n\n> **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/`.\n\n## Quick Start\n\nShortest invocation:\n\n```\nCalculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\n```\n\nCommon scenario — compare methods before reporting:\n\n```\nWhat's the ROI of our campaign using direct revenue, EMV, and LTV-based methods?\n```\n\n## Skill Contract\n\n- **Reads**: campaign spend breakdown, results data (reach, impressions, engagements, clicks, conversions, revenue, new customers), AOV and repeat-rate data if LTV is in scope, any prior performance output from `performance-analyzer`.\n- **Writes**: ROI calculation file at `memory/influencer/roi-calculator/YYYY-MM-DD-.md` containing direct ROI/ROAS, EMV, cost-efficiency metrics, attribution-modeled revenue, LTV-based ROI, by-influencer ROI, and a summary report block.\n- **Promotes**: durable headline numbers (final ROI %, ROAS, total investment, net profit, recommended attribution model) to `memory/hot-cache.md`.\n- **Done when**:\n 1. At least one ROI methodology is computed with the inputs and formula shown.\n 2. Each headline metric is stated against a benchmark with a pass/fail status.\n 3. A bottom-line assessment (profitable / break-even / loss) and 1-3 recommendations are written.\n- **Primary next skill**: [report-generator](../report-generator/SKILL.md)\n\n### Handoff Summary\n\n> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).\n\n## Data Sources\n\nThis 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:\n\n- `~~social platform analytics` — reach, impressions, engagements, video views per platform for EMV and cost-per-metric math.\n- `~~ecommerce / analytics` — revenue, conversions, link clicks, and AOV for direct ROI and attribution.\n- `~~CRM` — new-customer counts, repeat-purchase rate, and lifetime value for LTV-based ROI.\n- `~~influencer database` — per-influencer fees and tier data for by-influencer ROI.\n\nWith 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.\n\n## Instructions\n\nWhen 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.\n\n1. **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))\n\n2. **Calculate direct ROI** — Simple ROI = (Revenue − Investment) / Investment × 100; ROAS = Revenue / Investment. State profit and a Profitable/Break-even/Loss assessment. ([template](references/roi-templates.md#step-2--direct-roi-calculation))\n\n3. **Calculate Earned Media Value (EMV)** — impression-based (Impressions × CPM / 1000) and engagement-based (Engagements × CPE), then average. Flag EMV as directional, not absolute. ([template](references/roi-templates.md#step-3--earned-media-value-emv))\n\n4. **Calculate cost-efficiency metrics** — CPM, CPR, CPE, CPV, CPC, CPA, CAC, each against a benchmark; rate the campaign and compare CPA to other channels. ([template](references/roi-templates.md#step-4--cost-efficiency-analysis))\n\n5. **Apply attribution modeling** — run first-touch, last-touch, linear, time-decay, and position-based; recommend the model that fits the customer journey. ([template](references/roi-templates.md#step-5--attribution-analysis))\n\n6. **Calculate customer lifetime value impact** — LTV-Based ROI = (New Customers × Avg LTV − Investment) / Investment; project short- vs. long-term and compare customer quality to organic/paid. ([template](references/roi-templates.md#step-6--lifetime-value-analysis))\n\n7. **Calculate by-influencer ROI** — per-influencer ROI/ROAS rank, investment efficiency, and ROI by tier (macro/micro/nano). ([template](references/roi-templates.md#step-7--influencer-level-roi))\n\n8. **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))\n\n9. **Roll up into the C³ Campaign Value Index (CVI)**\n\n This skill emits the **ROI** scope score of [C³](../../../references/c3-benchmark.md) and the **CVI** rollup. Score ROI on the **0–100 rubric** in [c3/roi-campaign-benchmark.md](../../../references/c3/roi-campaign-benchmark.md) (Return · Orchestration · Impact, each on Pass/Partial/Fail → scaled to 0–100). **This 0–100 ROI score is not the financial ROI % from steps 1–8** — feed the rubric score into the formula, never the percentage (R1 simply *consumes* your ROI%/ROAS as one of its inputs). Then combine it with the Creator and Content scope scores — from [fit-scorer](../../discover/fit-scorer/SKILL.md) (ACE) and [content-reviewer](../../activate/content-reviewer/SKILL.md) (ART) — as a geometric mean:\n\n ```\n CVI = ( ACE_avg × ART_avg × ROI )^(1/3)\n ```\n\n `ACE_avg` is the **budget-weighted** mean of the campaign's creator ACE scores; `ART_avg` is the simple mean of its content ART scores (per scoring-architecture §8). Keep the three scope scores beside the CVI — the index ranks and alerts, the three scores diagnose. If ACE or ART is unavailable, emit the ROI score and mark CVI **pending (needs ACE/ART)** rather than guessing. A blocked scope (e.g. an ART T1/T2 veto on the content, or an ACE A2/C1/E2 veto on the creator) caps the rollup — surface it, don't average it away.\n\n## Example\n\n**User**: \"Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\"\n\n**Output**:\n\n```markdown\n# ROI Calculation Summary\n\n## Investment & Returns\n\n| Item | Value |\n|------|-------|\n| Total Investment | $25,000 |\n| Direct Revenue | $72,000 |\n| Total Reach | 2,100,000 |\n\n## ROI Results\n\n### Direct ROI\n- **Profit**: $47,000\n- **ROI**: 188%\n- **ROAS**: 2.88:1\n\nFor every $1 spent, you generated $2.88 in revenue.\n\n### Earned Media Value\n- **EMV** (at $8 CPM): $16,800\n- **EMV Multiple**: 0.67x\n\n### Cost Efficiency\n- **CPM**: $11.90 (Good)\n- **Est. CPA**: ~$54 (if 460 conversions)\n\n## Assessment: ✅ Strong Performance\n\nThis campaign outperformed the typical 2:1 ROAS benchmark for influencer marketing. Recommend increasing investment in similar campaigns.\n```\n\nIndustry ROAS benchmarks (Beauty, Fashion, Food & Beverage, Tech, Health) live in [references/roi-templates.md#industry-roi-benchmarks](references/roi-templates.md#industry-roi-benchmarks).\n\n## Reference Materials\n\n- [references/roi-templates.md](references/roi-templates.md) — fill-in templates for every Instructions step, the worked example, and industry ROAS benchmarks.\n- [measurement-protocol.md](../../../references/measurement-protocol.md) — read ROI/CVI deltas against a control over the readback window; do not over-claim attribution.\n- [skill-contract.md](../../../references/skill-contract.md) — shared contract and Handoff Summary format.\n- [state-model.md](../../../references/state-model.md) — memory tiers and save-path conventions.\n- [CONNECTORS.md](../../../CONNECTORS.md) — free/keyless data recipe per connector category.\n- C³ scoring: [c3-benchmark.md](../../../references/c3-benchmark.md) (CVI rollup formula) and [c3/roi-campaign-benchmark.md](../../../references/c3/roi-campaign-benchmark.md) — the ROI Campaign rubric this skill emits into the CVI.\n- [performance-analyzer](../performance-analyzer/SKILL.md) — supplies the results data this skill consumes.\n- [report-generator](../report-generator/SKILL.md) — wraps these numbers into a full report.\n- [budget-optimizer](../../plan/budget-optimizer/SKILL.md) — uses ROI output to reallocate spend.\n- [campaign-planner](../../plan/campaign-planner/SKILL.md) — sets the ROI targets these results are checked against.\n\n## Next Best Skill\n\n**Primary**: [report-generator](../report-generator/SKILL.md) — turn the ROI numbers into a stakeholder-ready report.\n\n**Alternates** (same Track family):\n\n- [performance-analyzer](../performance-analyzer/SKILL.md) — go back for deeper performance breakdowns if the ROI math exposed gaps.\n- [budget-optimizer](../../plan/budget-optimizer/SKILL.md) — feed by-influencer and by-tier ROI into the next budget allocation.\n\nTermination note: keep a visited-set of skills invoked this session. If the primary next skill was already run, stop and report the chain complete rather than re-invoking it. Stop after at most 3 hops in a single chain.\n\nFile v16.0.0:_meta.json\n\n{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"roi-calculator\",\n \"version\": \"16.0.0\",\n \"publishedAt\": 1783306992593\n}\n\nFile v16.0.0:references/roi-templates.md\n\n# ROI Calculator — Templates & Benchmarks\n\nFill-in templates for each methodology in [../SKILL.md](../SKILL.md) Instructions, plus the worked example and industry ROAS benchmarks. Each block maps to a numbered step.\n\n## Step 1 — ROI Calculation Inputs\n\n```markdown\n### ROI Calculation Inputs\n\n**Campaign Details**:\n- Campaign: [name]\n- Duration: [dates]\n- Objective: [awareness/consideration/conversion]\n\n**Investment (Total Spend)**:\n| Category | Amount |\n|----------|--------|\n| Influencer fees | $[X] |\n| Product/Gifting | $[X] |\n| Production costs | $[X] |\n| Paid amplification | $[X] |\n| Agency/Tools | $[X] |\n| **Total Investment** | **$[X]** |\n\n**Results Data**:\n| Metric | Value |\n|--------|-------|\n| Total Reach | [X] |\n| Total Impressions | [X] |\n| Total Engagements | [X] |\n| Video Views | [X] |\n| Link Clicks | [X] |\n| Conversions/Sales | [X] |\n| Revenue | $[X] |\n| New Customers | [X] |\n```\n\n## Step 2 — Direct ROI Calculation\n\n```markdown\n## Direct ROI Calculation\n\n### Simple ROI\n\n**Formula**: (Revenue - Investment) / Investment × 100\n\n```\nRevenue: $[X]\nInvestment: $[X]\nProfit: $[X]\n\nROI = ($[Revenue] - $[Investment]) / $[Investment] × 100\nROI = [X]%\n```\n\n### Return on Ad Spend (ROAS)\n\n**Formula**: Revenue / Investment\n\n```\nROAS = $[Revenue] / $[Investment]\nROAS = [X]:1\n\nInterpretation: For every $1 spent, generated $[X] in revenue\n```\n\n### Direct ROI Summary\n\n| Metric | Value | Benchmark | Status |\n|--------|-------|-----------|--------|\n| ROI % | [X]% | [X]% | ✅/❌ |\n| ROAS | [X]:1 | [X]:1 | ✅/❌ |\n| Profit | $[X] | - | |\n\n**Assessment**: [Profitable/Break-even/Loss]\n```\n\n## Step 3 — Earned Media Value (EMV)\n\n```markdown\n## Earned Media Value Calculation\n\n### EMV Methodology\n\nEMV estimates the equivalent paid media cost to achieve the same results.\n\n### Impression-Based EMV\n\n**Formula**: Impressions × Industry CPM / 1000\n\n| Platform | Impressions | CPM | EMV |\n|----------|-------------|-----|-----|\n| Instagram | [X] | $[X] | $[X] |\n| TikTok | [X] | $[X] | $[X] |\n| YouTube | [X] | $[X] | $[X] |\n| **Total** | **[X]** | - | **$[X]** |\n\n### Engagement-Based EMV\n\n**Formula**: Engagements × Cost per Engagement\n\n| Engagement Type | Volume | CPE | EMV |\n|-----------------|--------|-----|-----|\n| Likes | [X] | $[X] | $[X] |\n| Comments | [X] | $[X] | $[X] |\n| Shares | [X] | $[X] | $[X] |\n| Saves | [X] | $[X] | $[X] |\n| Video Views | [X] | $[X] | $[X] |\n| **Total** | - | - | **$[X]** |\n\n### Combined EMV\n\n| Method | Value |\n|--------|-------|\n| Impression EMV | $[X] |\n| Engagement EMV | $[X] |\n| **Average EMV** | **$[X]** |\n\n### EMV ROI\n\n```\nEMV Generated: $[X]\nInvestment: $[X]\nEMV Multiple: [X]x\n\nFor every $1 spent, earned $[X] in equivalent media value\n```\n\n### EMV Caveats\n\n⚠️ **Note**: EMV is an estimate and varies by methodology. Use for directional comparison, not absolute measurement.\n```\n\n## Step 4 — Cost Efficiency Analysis\n\n```markdown\n## Cost Efficiency Analysis\n\n### Cost Per Metrics\n\n| Metric | Formula | Result | Benchmark | Status |\n|--------|---------|--------|-----------|--------|\n| CPM | Spend ÷ (Impressions/1000) | $[X] | $[X] | ✅/❌ |\n| CPR (Reach) | Spend ÷ (Reach/1000) | $[X] | $[X] | ✅/❌ |\n| CPE | Spend ÷ Engagements | $[X] | $[X] | ✅/❌ |\n| CPV (Video) | Spend ÷ Views | $[X] | $[X] | ✅/❌ |\n| CPC | Spend ÷ Clicks | $[X] | $[X] | ✅/❌ |\n| CPA | Spend ÷ Acquisitions | $[X] | $[X] | ✅/❌ |\n| CAC | Total Spend ÷ New Customers | $[X] | $[X] | ✅/❌ |\n\n### Efficiency Score\n\n| Rating | CPM Range | CPC Range | CPA Range |\n|--------|-----------|-----------|-----------|\n| Excellent | <$[X] | <$[X] | <$[X] |\n| Good | $[X]-$[X] | $[X]-$[X] | $[X]-$[X] |\n| Average | $[X]-$[X] | $[X]-$[X] | $[X]-$[X] |\n| Below Avg | $[X]-$[X] | $[X]-$[X] | $[X]-$[X] |\n| Poor | >$[X] | >$[X] | >$[X] |\n\n**Your Campaign**: [Rating]\n\n### vs. Other Channels\n\n| Channel | CPA | vs. Influencer |\n|---------|-----|----------------|\n| Influencer Marketing | $[X] | - |\n| Paid Social | $[X] | [+/-X%] |\n| Paid Search | $[X] | [+/-X%] |\n| Display Ads | $[X] | [+/-X%] |\n| Email Marketing | $[X] | [+/-X%] |\n```\n\n## Step 5 — Attribution Analysis\n\n```markdown\n## Attribution Analysis\n\n### Attribution Methods\n\n| Method | Description | Result | Notes |\n|--------|-------------|--------|-------|\n| First Touch | All credit to first interaction | $[X] | Awareness focus |\n| Last Touch | All credit to last interaction | $[X] | Conversion focus |\n| Linear | Equal credit across touchpoints | $[X] | Balanced view |\n| Time Decay | More credit to recent touches | $[X] | Recency bias |\n| Position Based | 40/20/40 first/middle/last | $[X] | Common B2C model |\n\n### Attributed Revenue by Model\n\n| Model | Attributed Revenue | ROI |\n|-------|-------------------|-----|\n| First Touch | $[X] | [X]% |\n| Last Touch | $[X] | [X]% |\n| Linear | $[X] | [X]% |\n| Time Decay | $[X] | [X]% |\n| Position Based | $[X] | [X]% |\n\n### Recommended Model for Your Business\n\n**Recommended**: [Model]\n**Rationale**: [Why this model fits your customer journey]\n\n### Multi-Touch Journey Example\n\n```\nCustomer Journey:\n\nDay 1: Sees @creator1 TikTok (Awareness) ─────┐\nDay 3: Sees @creator2 Instagram Reel ─────────┤\nDay 5: Clicks @creator1's link (Consideration)┼── Purchase Day 7\nDay 7: Uses @creator2's code (Conversion) ────┘\n\nAttribution:\nLast Touch: 100% to @creator2\nFirst Touch: 100% to @creator1\nLinear: 50% each\nPosition Based: 40% @creator1, 40% @creator2, 20% repeat exposure\n```\n```\n\n## Step 6 — Lifetime Value Analysis\n\n```markdown\n## Lifetime Value Analysis\n\n### New Customer Metrics\n\n| Metric | Influencer Acquired | Overall Average |\n|--------|--------------------|--------------------|\n| New customers | [X] | - |\n| First order AOV | $[X] | $[X] |\n| Repeat purchase rate | [%] | [%] |\n| Customer lifetime value | $[X] | $[X] |\n\n### LTV-Based ROI\n\n**Formula**: (New Customers × Avg LTV) - Investment / Investment\n\n```\nNew Customers: [X]\nAverage LTV: $[X]\nTotal LTV: $[X]\nInvestment: $[X]\n\nLTV-Based ROI = ($[X] - $[X]) / $[X] × 100\nLTV-Based ROI = [X]%\n```\n\n### Short-term vs. Long-term View\n\n| Timeframe | Revenue | ROI |\n|-----------|---------|-----|\n| Immediate (this campaign) | $[X] | [X]% |\n| 6-month projected | $[X] | [X]% |\n| 12-month projected | $[X] | [X]% |\n| Lifetime projected | $[X] | [X]% |\n\n### Customer Quality Indicators\n\n| Indicator | Influencer-Acquired | Organic | Paid Ads |\n|-----------|--------------------|---------| ---------|\n| AOV | $[X] | $[X] | $[X] |\n| Return rate | [%] | [%] | [%] |\n| Repeat rate | [%] | [%] | [%] |\n| NPS/Satisfaction | [X] | [X] | [X] |\n```\n\n## Step 7 — Influencer-Level ROI\n\n```markdown\n## Influencer-Level ROI\n\n### Individual Influencer Performance\n\n| Influencer | Investment | Revenue | ROI | ROAS | Rank |\n|------------|------------|---------|-----|------|------|\n| @[handle1] | $[X] | $[X] | [X]% | [X]:1 | 1 |\n| @[handle2] | $[X] | $[X] | [X]% | [X]:1 | 2 |\n| @[handle3] | $[X] | $[X] | [X]% | [X]:1 | 3 |\n| @[handle4] | $[X] | $[X] | [X]% | [X]:1 | 4 |\n| @[handle5] | $[X] | $[X] | [X]% | [X]:1 | 5 |\n\n### ROI Distribution\n\n```\nInfluencer ROI Distribution:\n\n@handle1 |████████████████████| 320%\n@handle2 |██████████████ | 180%\n@handle3 |████████████ | 150%\n@handle4 |██████ | 75%\n@handle5 |████ | 45%\n\nCampaign Average: 180%\n```\n\n### Investment Efficiency\n\n| Influencer | % of Budget | % of Revenue | Efficiency |\n|------------|-------------|--------------|------------|\n| @[handle1] | [%] | [%] | [X]x |\n| @[handle2] | [%] | [%] | [X]x |\n\n### ROI by Tier\n\n| Tier | Investment | Revenue | ROI | Avg ROAS |\n|------|------------|---------|-----|----------|\n| Macro | $[X] | $[X] | [%] | [X]:1 |\n| Micro | $[X] | $[X] | [%] | [X]:1 |\n| Nano | $[X] | $[X] | [%] | [X]:1 |\n```\n\n## Step 8 — ROI Summary Report\n\n```markdown\n# ROI Summary Report\n\n## Campaign: [Name]\n## Period: [Dates]\n\n---\n\n## Investment Summary\n\n| Category | Amount | % of Total |\n|----------|--------|------------|\n| Influencer Fees | $[X] | [%] |\n| Product/Gifts | $[X] | [%] |\n| Amplification | $[X] | [%] |\n| Other | $[X] | [%] |\n| **Total Investment** | **$[X]** | **100%** |\n\n## Returns Summary\n\n| Return Type | Value |\n|-------------|-------|\n| Direct Revenue | $[X] |\n| Earned Media Value | $[X] |\n| New Customers | [X] |\n| Projected LTV | $[X] |\n\n## ROI by Methodology\n\n| Methodology | ROI | Notes |\n|-------------|-----|-------|\n| Direct Revenue ROI | [X]% | Hard returns |\n| ROAS | [X]:1 | Revenue per dollar |\n| EMV Multiple | [X]x | Media value generated |\n| LTV-Based ROI | [X]% | Long-term value |\n\n## Key Metrics\n\n| Metric | Result | Benchmark | Status |\n|--------|--------|-----------|--------|\n| CPM | $[X] | $[X] | ✅/❌ |\n| CPA | $[X] | $[X] | ✅/❌ |\n| ROAS | [X]:1 | [X]:1 | ✅/❌ |\n\n## Bottom Line\n\n**Investment**: $[X]\n**Return**: $[X]\n**Net Profit**: $[X]\n**ROI**: [X]%\n\n**Assessment**: [Campaign was profitable/broke even/lost money]\n\n## Recommendations\n\n1. [Key recommendation 1]\n2. [Key recommendation 2]\n3. [Key recommendation 3]\n\n---\n\n*Report Generated: [Date]*\n```\n\n## Worked Example\n\n**User**: \"Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\"\n\n**Output**:\n\n```markdown\n# ROI Calculation Summary\n\n## Investment & Returns\n\n| Item | Value |\n|------|-------|\n| Total Investment | $25,000 |\n| Direct Revenue | $72,000 |\n| Total Reach | 2,100,000 |\n\n## ROI Results\n\n### Direct ROI\n- **Profit**: $47,000\n- **ROI**: 188%\n- **ROAS**: 2.88:1\n\nFor every $1 spent, you generated $2.88 in revenue.\n\n### Earned Media Value\n- **EMV** (at $8 CPM): $16,800\n- **EMV Multiple**: 0.67x\n\n### Cost Efficiency\n- **CPM**: $11.90 (Good)\n- **Est. CPA**: ~$54 (if 460 conversions)\n\n## Assessment: ✅ Strong Performance\n\nThis campaign outperformed the typical 2:1 ROAS benchmark for influencer marketing. Recommend increasing investment in similar campaigns.\n```\n\n## Industry ROI Benchmarks\n\n| Industry | Avg ROAS | Good ROAS | Excellent ROAS |\n|----------|----------|-----------|----------------|\n| Beauty/Skincare | 3:1 | 5:1 | 8:1 |\n| Fashion | 2.5:1 | 4:1 | 6:1 |\n| Food & Beverage | 2:1 | 3.5:1 | 5:1 |\n| Tech/Electronics | 2:1 | 3:1 | 4:1 |\n| Health/Fitness | 2.5:1 | 4:1 | 6:1 |\n\nFile v16.0.0:skill-card.md\n\n## Description:
\nCalculates influencer campaign ROI, ROAS, earned media value, attribution-modeled revenue, LTV-based ROI, cost-efficiency metrics, and stakeholder-ready summaries from campaign spend and results data.
\n\nThis skill is ready for commercial/non-commercial use.
\n\n## Publisher:
\n[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)
\n\n### License/Terms of Use:
\nMIT-0
\n\n\n## Use Case:
\nMarketing teams, influencer-program operators, and analysts use this skill to measure or project campaign value from supplied spend, revenue, conversion, customer, and engagement data. It helps compare ROI methodologies, assess performance against benchmarks, and prepare concise recommendations for budget and reporting decisions.
\n\n### Deployment Geography for Use:
\nGlobal
\n\n## Known Risks and Mitigations:
\nRisk: Campaign spend, revenue, conversion, customer-count, and LTV data may be used in calculations and saved to the memory locations described by the skill.
\nMitigation: Confirm the user is comfortable sharing and retaining that campaign data before running the workflow, and avoid saving confidential inputs unless approved.
\nRisk: ROI, EMV, attribution, and LTV outputs can be mistaken for definitive financial truth when the source data or model assumptions are incomplete.
\nMitigation: Show formulas, inputs, assumptions, and benchmark context with each headline metric, and label EMV and attribution results as directional when appropriate.
\n\n\n## Reference(s):
\n- [ClawHub skill page](https://clawhub.ai/aaron-he-zhu/skills/roi-calculator)
\n- [Project homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)
\n- [ROI templates and benchmarks](references/roi-templates.md)
\n\n\n## Skill Output:
\n**Output Type(s):** [text, markdown, guidance]
\n**Output Format:** [Markdown calculation summaries, formulas, tables, benchmark assessments, and recommendations]
\n**Output Parameters:** [1D]
\n**Other Properties Related to Output:** [May save ROI calculation summaries to agent memory paths described by the skill contract.]
\n\n## Skill Version(s):
\n16.0.0 (source: server release evidence and artifact metadata)
\n\n## Ethical Considerations:
\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.
\n\nArchive v14.0.0: 4 files, 9644 bytes\n\nFiles: references/roi-templates.md (10396b), skill-card.md (2252b), SKILL.md (10715b), _meta.json (134b)\n\nFile v14.0.0:SKILL.md\n\n---\nname: roi-calculator\nslug: aaron-roi-calculator\ndisplayName: \"ROI Calculator · ROI 计算\"\nsummary: \"活动投入产出核算:成本归集、收益口径与 CVI/ROI 汇总\"\ndescription: '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.'\nversion: \"14.0.0\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use when measuring or projecting influencer campaign ROI, justifying or defending budgets, comparing ROI across campaigns or channels, evaluating individual influencer or tier value, or preparing executive-level ROI numbers. Activate when the user supplies spend and results data and wants ROI, ROAS, EMV, CPA/CAC, attribution, or LTV impact computed.\"\nargument-hint: \" [revenue] [results data]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"14.0.0\", \"discipline\": \"influencer\", \"phase\": \"measure\", \"family\": \"influencer-marketing\", \"hermes\": {\"tags\": [\"marketing\", \"influencer\", \"measure\"], \"category\": \"influencer\"}, \"openclaw\": {\"emoji\": \"📣\", \"homepage\": \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"}}\n---\n\n# ROI Calculator\n\nThis skill helps you calculate and communicate the return on investment for influencer marketing campaigns using various methodologies appropriate for your goals and available data.\n\n> **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/`.\n\n## Quick Start\n\nShortest invocation:\n\n```\nCalculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\n```\n\nCommon scenario — compare methods before reporting:\n\n```\nWhat's the ROI of our campaign using direct revenue, EMV, and LTV-based methods?\n```\n\n## Skill Contract\n\n- **Reads**: campaign spend breakdown, results data (reach, impressions, engagements, clicks, conversions, revenue, new customers), AOV and repeat-rate data if LTV is in scope, any prior performance output from `performance-analyzer`.\n- **Writes**: ROI calculation file at `memory/influencer/roi-calculator/YYYY-MM-DD-.md` containing direct ROI/ROAS, EMV, cost-efficiency metrics, attribution-modeled revenue, LTV-based ROI, by-influencer ROI, and a summary report block.\n- **Promotes**: durable headline numbers (final ROI %, ROAS, total investment, net profit, recommended attribution model) to `memory/hot-cache.md`.\n- **Done when**:\n 1. At least one ROI methodology is computed with the inputs and formula shown.\n 2. Each headline metric is stated against a benchmark with a pass/fail status.\n 3. A bottom-line assessment (profitable / break-even / loss) and 1-3 recommendations are written.\n- **Primary next skill**: [report-generator](../report-generator/SKILL.md)\n\n### Handoff Summary\n\n> Emit the standard shape from [skill-contract.md §Handoff Summary Format](../../../references/skill-contract.md).\n\n## Data Sources\n\nThis 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:\n\n- `~~social platform analytics` — reach, impressions, engagements, video views per platform for EMV and cost-per-metric math.\n- `~~ecommerce / analytics` — revenue, conversions, link clicks, and AOV for direct ROI and attribution.\n- `~~CRM` — new-customer counts, repeat-purchase rate, and lifetime value for LTV-based ROI.\n- `~~influencer database` — per-influencer fees and tier data for by-influencer ROI.\n\nWith 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.\n\n## Instructions\n\nWhen 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.\n\n1. **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))\n\n2. **Calculate direct ROI** — Simple ROI = (Revenue − Investment) / Investment × 100; ROAS = Revenue / Investment. State profit and a Profitable/Break-even/Loss assessment. ([template](references/roi-templates.md#step-2--direct-roi-calculation))\n\n3. **Calculate Earned Media Value (EMV)** — impression-based (Impressions × CPM / 1000) and engagement-based (Engagements × CPE), then average. Flag EMV as directional, not absolute. ([template](references/roi-templates.md#step-3--earned-media-value-emv))\n\n4. **Calculate cost-efficiency metrics** — CPM, CPR, CPE, CPV, CPC, CPA, CAC, each against a benchmark; rate the campaign and compare CPA to other channels. ([template](references/roi-templates.md#step-4--cost-efficiency-analysis))\n\n5. **Apply attribution modeling** — run first-touch, last-touch, linear, time-decay, and position-based; recommend the model that fits the customer journey. ([template](references/roi-templates.md#step-5--attribution-analysis))\n\n6. **Calculate customer lifetime value impact** — LTV-Based ROI = (New Customers × Avg LTV − Investment) / Investment; project short- vs. long-term and compare customer quality to organic/paid. ([template](references/roi-templates.md#step-6--lifetime-value-analysis))\n\n7. **Calculate by-influencer ROI** — per-influencer ROI/ROAS rank, investment efficiency, and ROI by tier (macro/micro/nano). ([template](references/roi-templates.md#step-7--influencer-level-roi))\n\n8. **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))\n\n9. **Roll up into the C³ Campaign Value Index (CVI)**\n\n This skill emits the **ROI** scope score of [C³](../../../references/c3-benchmark.md) and the **CVI** rollup. Score ROI on the **0–100 rubric** in [c3/roi-campaign-benchmark.md](../../../references/c3/roi-campaign-benchmark.md) (Return · Orchestration · Impact, each on Pass/Partial/Fail → scaled to 0–100). **This 0–100 ROI score is not the financial ROI % from steps 1–8** — feed the rubric score into the formula, never the percentage (R1 simply *consumes* your ROI%/ROAS as one of its inputs). Then combine it with the Creator and Content scope scores — from [fit-scorer](../../discover/fit-scorer/SKILL.md) (ACE) and [content-reviewer](../../activate/content-reviewer/SKILL.md) (ART) — as a geometric mean:\n\n ```\n CVI = ( ACE_avg × ART_avg × ROI )^(1/3)\n ```\n\n `ACE_avg` is the **budget-weighted** mean of the campaign's creator ACE scores; `ART_avg` is the simple mean of its content ART scores (per scoring-architecture §8). Keep the three scope scores beside the CVI — the index ranks and alerts, the three scores diagnose. If ACE or ART is unavailable, emit the ROI score and mark CVI **pending (needs ACE/ART)** rather than guessing. A blocked scope (e.g. an ART T1/T2 veto on the content, or an ACE A2/C1/E2 veto on the creator) caps the rollup — surface it, don't average it away.\n\n## Example\n\n**User**: \"Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\"\n\n**Output**:\n\n```markdown\n# ROI Calculation Summary\n\n## Investment & Returns\n\n| Item | Value |\n|------|-------|\n| Total Investment | $25,000 |\n| Direct Revenue | $72,000 |\n| Total Reach | 2,100,000 |\n\n## ROI Results\n\n### Direct ROI\n- **Profit**: $47,000\n- **ROI**: 188%\n- **ROAS**: 2.88:1\n\nFor every $1 spent, you generated $2.88 in revenue.\n\n### Earned Media Value\n- **EMV** (at $8 CPM): $16,800\n- **EMV Multiple**: 0.67x\n\n### Cost Efficiency\n- **CPM**: $11.90 (Good)\n- **Est. CPA**: ~$54 (if 460 conversions)\n\n## Assessment: ✅ Strong Performance\n\nThis campaign outperformed the typical 2:1 ROAS benchmark for influencer marketing. Recommend increasing investment in similar campaigns.\n```\n\nIndustry ROAS benchmarks (Beauty, Fashion, Food & Beverage, Tech, Health) live in [references/roi-templates.md#industry-roi-benchmarks](references/roi-templates.md#industry-roi-benchmarks).\n\n## Reference Materials\n\n- [references/roi-templates.md](references/roi-templates.md) — fill-in templates for every Instructions step, the worked example, and industry ROAS benchmarks.\n- [measurement-protocol.md](../../../references/measurement-protocol.md) — read ROI/CVI deltas against a control over the readback window; do not over-claim attribution.\n- [skill-contract.md](../../../references/skill-contract.md) — shared contract and Handoff Summary format.\n- [state-model.md](../../../references/state-model.md) — memory tiers and save-path conventions.\n- [CONNECTORS.md](../../../CONNECTORS.md) — free/keyless data recipe per connector category.\n- C³ scoring: [c3-benchmark.md](../../../references/c3-benchmark.md) (CVI rollup formula) and [c3/roi-campaign-benchmark.md](../../../references/c3/roi-campaign-benchmark.md) — the ROI Campaign rubric this skill emits into the CVI.\n- [performance-analyzer](../performance-analyzer/SKILL.md) — supplies the results data this skill consumes.\n- [report-generator](../report-generator/SKILL.md) — wraps these numbers into a full report.\n- [budget-optimizer](../../plan/budget-optimizer/SKILL.md) — uses ROI output to reallocate spend.\n- [campaign-planner](../../plan/campaign-planner/SKILL.md) — sets the ROI targets these results are checked against.\n\n## Next Best Skill\n\n**Primary**: [report-generator](../report-generator/SKILL.md) — turn the ROI numbers into a stakeholder-ready report.\n\n**Alternates** (same Track family):\n\n- [performance-analyzer](../performance-analyzer/SKILL.md) — go back for deeper performance breakdowns if the ROI math exposed gaps.\n- [budget-optimizer](../../plan/budget-optimizer/SKILL.md) — feed by-influencer and by-tier ROI into the next budget allocation.\n\nTermination note: keep a visited-set of skills invoked this session. If the primary next skill was already run, stop and report the chain complete rather than re-invoking it. Stop after at most 3 hops in a single chain.\n\nFile v14.0.0:_meta.json\n\n{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"roi-calculator\",\n \"version\": \"14.0.0\",\n \"publishedAt\": 1783241157659\n}\n\nFile v14.0.0:references/roi-templates.md\n\n# ROI Calculator — Templates & Benchmarks\n\nFill-in templates for each methodology in [../SKILL.md](../SKILL.md) Instructions, plus the worked example and industry ROAS benchmarks. Each block maps to a numbered step.\n\n## Step 1 — ROI Calculation Inputs\n\n```markdown\n### ROI Calculation Inputs\n\n**Campaign Details**:\n- Campaign: [name]\n- Duration: [dates]\n- Objective: [awareness/consideration/conversion]\n\n**Investment (Total Spend)**:\n| Category | Amount |\n|----------|--------|\n| Influencer fees | $[X] |\n| Product/Gifting | $[X] |\n| Production costs | $[X] |\n| Paid amplification | $[X] |\n| Agency/Tools | $[X] |\n| **Total Investment** | **$[X]** |\n\n**Results Data**:\n| Metric | Value |\n|--------|-------|\n| Total Reach | [X] |\n| Total Impressions | [X] |\n| Total Engagements | [X] |\n| Video Views | [X] |\n| Link Clicks | [X] |\n| Conversions/Sales | [X] |\n| Revenue | $[X] |\n| New Customers | [X] |\n```\n\n## Step 2 — Direct ROI Calculation\n\n```markdown\n## Direct ROI Calculation\n\n### Simple ROI\n\n**Formula**: (Revenue - Investment) / Investment × 100\n\n```\nRevenue: $[X]\nInvestment: $[X]\nProfit: $[X]\n\nROI = ($\n\nArchive v13.0.0: 4 files, 9647 bytes\n\nFiles: references/roi-templates.md (10396b), skill-card.md (2261b), SKILL.md (10740b), _meta.json (134b)","readmeExcerpt":"Skill: Roi Calculator Owner: aaron-he-zhu Summary: Use when the user asks to \"calculate influencer ROI\", \"prove campaign value\", or \"what was our ROAS\"; produces direct ROI/ROAS, earned media value, attributi... Tags: latest:19.0.0 Version history: v19.0.0 | 2026-07-24T15:07:03.940Z | auto **roi-calculator 19.0.0 Changelog** - Added distribution-manifest.json file for new distribution/configuration support. - Updated","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"Calculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach"},{"language":"text","snippet":"What's the ROI of our campaign using direct revenue, EMV, and LTV-based methods?"},{"language":"markdown","snippet":"# ROI Calculation Summary\n\n## Investment & Returns\n\n| Item | Value |\n|------|-------|\n| Total Investment | $25,000 |\n| Direct Revenue | $72,000 |\n| Total Reach | 2,100,000 |\n\n## ROI Results\n\n### Direct ROI\n- **Profit**: $47,000\n- **ROI**: 188%\n- **ROAS**: 2.88:1\n\nFor every $1 spent, you generated $2.88 in revenue.\n\n### Earned Media Value\n- **EMV** (directional scenario at a declared $8 CPM): $16,800\n- **EMV Multiple**: 0.67x\n\n### Cost Efficiency\n- **CPM**: $11.90\n- **CPA**: Unknown (conversion count was not supplied)\n\n## Assessment: Profitable on the supplied direct-revenue basis\n\nDirect revenue exceeds the supplied investment, but no source-dated peer target or incrementality evidence was provided. Do not infer benchmark outperformance or authorize a scale decision from this read alone; obtain verified conversions, attribution evidence, and the campaign owner's precommitted decision rule first."},{"language":"markdown","snippet":"### ROI Calculation Inputs\n\n**Campaign Details**:\n- Campaign: [name]\n- Duration: [dates]\n- Objective: [awareness/consideration/conversion]\n\n**Investment (Total Spend)**:\n| Category | Amount |\n|----------|--------|\n| Influencer fees | $[X] |\n| Product/Gifting | $[X] |\n| Production costs | $[X] |\n| Paid amplification | $[X] |\n| Agency/Tools | $[X] |\n| **Total Investment** | **$[X]** |\n\n**Results Data**:\n| Metric | Value |\n|--------|-------|\n| Total Reach | [X] |\n| Total Impressions | [X] |\n| Total Engagements | [X] |\n| Video Views | [X] |\n| Link Clicks | [X] |\n| Conversions/Sales | [X] |\n| Revenue | $[X] |\n| New Customers | [X] |"},{"language":"markdown","snippet":"## Direct ROI Calculation\n\n### Simple ROI\n\n**Formula**: (Revenue - Investment) / Investment × 100"},{"language":"text","snippet":"### Return on Ad Spend (ROAS)\n\n**Formula**: Revenue / Investment"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: roi-calculator\nslug: aaron-roi-calculator\ndisplayName: \"ROI Calculator · ROI 计算\"\nsummary: \"活动投入产出核算:成本归集、收益口径与 ROI 及 STAR 回报(R)证据汇总\"\ndescription: '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'\nversion: \"19.0.0\"\nlicense: Apache-2.0\ncompatibility: \"Claude Code and compatible agent-skill hosts\"\nhomepage: \"https://github.com/aaron-he-zhu/aaron-marketing-skills\"\nwhen_to_use: \"Use when measuring or projecting influencer campaign ROI, justifying or defending budgets, comparing ROI across campaigns or channels, evaluating individual influencer or tier value, or preparing executive-level ROI numbers. Activate when the user supplies spend and results data and wants ROI, ROAS, EMV, CPA/CAC, attribution, or LTV impact computed.\"\nargument-hint: \" [revenue] [results data]\"\nmetadata: {\"author\": \"aaron-he-zhu\", \"version\": \"19.0.0\", \"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\"}}\n---\n\n# ROI Calculator\n\nThis skill helps you calculate and communicate the return on investment for influencer marketing campaigns using various methodologies appropriate for your goals and available data.\n\n> **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/`.\n\n## Quick Start\n\nShortest invocation:\n\n```\nCalculate ROI for our influencer campaign: $25K spend, $72K revenue, 2.1M reach\n```\n\nCommon scenario — compare methods before reporting:\n\n```\nWhat's the ROI of our campaign using direct revenue, EMV, and LTV-based methods?\n```\n\n## Skill Contract\n\n- **Reads**: campaign spend breakdown, results data (reach, impressions, engagements, clicks, conversions, revenue, new customers), AOV and repeat-rate data if LTV is in scope, any prior performance output from `performance-analyzer`.\n- **Writes**: ROI calculation file at `memory/influencer/roi-calculator/YYYY-MM-DD-.md` containing direct ROI/ROAS, EMV, cost-efficiency metrics, attribution-modeled revenue, LTV-based ROI, by-influencer ROI, and a summary report block.\n- **Promotes**: only with separate authorization, durable headline numbers with their attribution window, source, and uncertainty; a calculation request alone does not authorize hot-cache writes.\n- **Done when**:\n 1. At least one ROI methodology is compute"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn73qjxwmbna25qq8q051epqt980sys5\",\n \"slug\": \"roi-calculator\",\n \"version\": \"19.0.0\",\n \"publishedAt\": 1784905623940\n}"},{"path":"references/roi-templates.md","content":"# ROI Calculator — Templates & Benchmark Inputs\n\nFill-in templates for each methodology in [../SKILL.md](../SKILL.md) Instructions, plus the worked example and benchmark-evidence contract. Each block maps to a numbered step.\n\n## Step 1 — ROI Calculation Inputs\n\n```markdown\n### ROI Calculation Inputs\n\n**Campaign Details**:\n- Campaign: [name]\n- Duration: [dates]\n- Objective: [awareness/consideration/conversion]\n\n**Investment (Total Spend)**:\n| Category | Amount |\n|----------|--------|\n| Influencer fees | $[X] |\n| Product/Gifting | $[X] |\n| Production costs | $[X] |\n| Paid amplification | $[X] |\n| Agency/Tools | $[X] |\n| **Total Investment** | **$[X]** |\n\n**Results Data**:\n| Metric | Value |\n|--------|-------|\n| Total Reach | [X] |\n| Total Impressions | [X] |\n| Total Engagements | [X] |\n| Video Views | [X] |\n| Link Clicks | [X] |\n| Conversions/Sales | [X] |\n| Revenue | $[X] |\n| New Customers | [X] |\n```\n\n## Step 2 — Direct ROI Calculation\n\n```markdown\n## Direct ROI Calculation\n\n### Simple ROI\n\n**Formula**: (Revenue - Investment) / Investment × 100\n\n```\nRevenue: $[X]\nInvestment: $[X]\nProfit: $[X]\n\nROI = ($[Revenue] - $[Investment]) / $[Investment] × 100\nROI = [X]%\n```\n\n### Return on Ad Spend (ROAS)\n\n**Formula**: Revenue / Investment\n\n```\nROAS = $[Revenue] / $[Investment]\nROAS = [X]:1\n\nInterpretation: For every $1 spent, generated $[X] in revenue\n```\n\n### Direct ROI Summary\n\n| Metric | Value | Declared target (source/date) | Comparison |\n|--------|-------|-------------------------------|------------|\n| ROI % | [X]% | [X]% ([source], [date]) | [above/below/equal/pending] |\n| ROAS | [X]:1 | [X]:1 ([source], [date]) | [above/below/equal/pending] |\n| Profit | $[X] | Not applicable | Descriptive |\n\n**Assessment**: [Profitable/Break-even/Loss]\n```\n\n## Step 3 — Earned Media Value (EMV)\n\n```markdown\n## Earned Media Value Calculation\n\n### EMV Methodology\n\nEMV estimates the equivalent paid media cost to achieve the same results.\n\n### Impression-Based EMV\n\n**Formula**: Impressions × declared comparable CPM / 1000\n\n| Platform | Impressions | CPM | EMV |\n|----------|-------------|-----|-----|\n| Instagram | [X] | $[X] | $[X] |\n| TikTok | [X] | $[X] | $[X] |\n| YouTube | [X] | $[X] | $[X] |\n| **Total** | **[X]** | - | **$[X]** |\n\n### Engagement-Based EMV\n\n**Formula**: Engagements × Cost per Engagement\n\n| Engagement Type | Volume | CPE | EMV |\n|-----------------|--------|-----|-----|\n| Likes | [X] | $[X] | $[X] |\n| Comments | [X] | $[X] | $[X] |\n| Shares | [X] | $[X] | $[X] |\n| Saves | [X] | $[X] | $[X] |\n| Video Views | [X] | $[X] | $[X] |\n| **Total** | - | - | **$[X]** |\n\n### Combined EMV\n\n| Method | Value |\n|--------|-------|\n| Impression EMV | $[X] |\n| Engagement EMV | $[X] |\n| **Average EMV** | **$[X]** |\n\n### EMV ROI\n\n```\nEMV Generated: $[X]\nInvestment: $[X]\nEMV Multiple: [X]x\n\nFor every $1 spent, earned $[X] in equivalent media value\n```\n\n### EMV Caveats\n\n⚠️ **Note**: EMV is an estimate and varies by methodology. Use for directional comparison, no"},{"path":"skill-card.md","content":"## Description:\n\nCalculates influencer campaign ROI and ROAS, earned media value, attribution-modeled revenue, LTV-based ROI, and stakeholder-ready summaries from supplied campaign performance data.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[aaron-he-zhu](https://clawhub.ai/user/aaron-he-zhu)\n\n### License/Terms of Use:\n\nApache-2.0\n\n## Use Case:\n\nMarketing teams, creators, and operators use this skill to calculate or project influencer campaign returns, compare ROI methods, evaluate individual creators or tiers, and prepare numbers for budget justification or reporting.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Campaign, ecommerce, analytics, or CRM inputs may contain sensitive business performance information.\n\nMitigation: Review supplied data before use and authorize memory saves or connector-backed pulls only when those numbers may be reused for future campaign analysis.\n\nRisk: ROI, attribution, or benchmark comparisons may overstate campaign performance when conversions, targets, or comparison baselines are unverified.\n\nMitigation: Use source-dated targets and attribution windows, label each figure as measured, user-provided, calculated, or estimated, and avoid attributable-return claims when conversions are unverified.\n\nRisk: Earned media value is directional and can vary by methodology.\n\nMitigation: Present EMV as an estimate, disclose the CPM or engagement assumptions used, and avoid treating EMV as absolute revenue.\n\n## Reference(s):\n\n- [ROI templates and benchmark inputs](references/roi-templates.md)\n- [ClawHub skill page](https://clawhub.ai/aaron-he-zhu/skills/roi-calculator)\n- [Project homepage](https://github.com/aaron-he-zhu/aaron-marketing-skills)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, files, guidance]\n\n**Output Format:** [Markdown calculation summaries and optional memory files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May save ROI calculation files only after user authorization; can use connector-backed campaign data when available.]\n\n## Skill Version(s):\n\n19.0.0 (source: frontmatter and release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."},{"path":"distribution-manifest.json","content":"{\n \"capabilities\": [\n \"inline-delivery\",\n \"canonical-state-read\"\n ],\n \"capability_ceiling\": \"lite\",\n \"catalog_sha256\": \"6f0256cf52710f2916ecebaea0f3110c9313099ec4a69a11cac72ba9b2f3b940\",\n \"files\": [\n {\n \"bytes\": 11428,\n \"mode\": \"0644\",\n \"path\": \"SKILL.md\",\n \"sha256\": \"67510ab1308579d799525c21277cdb6ec6f3962dcb00463d4e1f7a640cf80311\"\n },\n {\n \"bytes\": 12637,\n \"mode\": \"0644\",\n \"path\": \"references/roi-templates.md\",\n \"sha256\": \"2f58cf3247a96e888243d286f153a1d854a29d6916c27e047d171da97562cf14\"\n }\n ],\n \"files_sha256\": \"5c32d263a53936794c87e0c24680f95bd8983d4d38d17f06aebd012f75f087d9\",\n \"hash_algorithm\": \"sha256\",\n \"kind\": \"standalone-skill\",\n \"manifest_excludes\": [\n \"distribution-manifest.json\"\n ],\n \"manifest_path\": \"distribution-manifest.json\",\n \"package_ceiling\": {\n \"max_bytes\": 1000000,\n \"max_files\": 64\n },\n \"profile\": \"lite\",\n \"profile_definition_sha256\": \"4598e1f7bba667ef928ea2a60a6252ad9348086e9eecab29437db442df2a568e\",\n \"schema_version\": \"1.1\",\n \"source\": {\n \"commit\": \"f552620c278afddcb25d09637a0cfcc1ce48faf4\",\n \"repository\": \"aaron-he-zhu/aaron-marketing-skills\"\n }\n}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Use when the user asks to \"calculate influencer ROI\", \"prove campaign value\", or \"what was our ROAS\"; produces direct ROI/ROAS, earned media value, attributi... Skill: Roi Calculator Owner: aaron-he-zhu Summary: Use when the user asks to \"calculate influencer ROI\", \"prove campaign value\", or \"what was our ROAS\"; produces direct ROI/ROAS, earned media value, attributi... Tags: latest:19.0.0 Version history: v19.0.0 | 2026-07-24T15:07:03.940Z | auto **roi-calculator 19.0.0 Changelog** - Added distribution-manifest.json file for new distribution/configuration support. - Updated","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1648,"uniquenessScore":48,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T03:32:47.787Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-11T03:32:47.787Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-11T05:43:13.007Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}