- Home
- Skills
- Finance & Accounting
- customer lifetime value analyzer
Works with the AI Agents you already use
customer lifetime value analyzer
- **Analyze retention** through survival curves at the horizon, including Gross Revenue Retention (GRR) and Net Revenue Retention (NRR).
$10
customer lifetime value analyzer
Example session with this skill installed
Analyze the attached cohort data for Q3. We spent $50k on Facebook and $30k on Google. I need to know the LTV/CAC over a 24-month horizon and the payback period. Retention data is in the sheet.
- Read your context and instructions
- Compiled the customer lifetime value
- Generated the data export
The cohort analysis for Q3 acquisition spend is complete. Data was processed using a 24-month finite horizon with a 10% annual discount rate.
Customer Lifetime Value and Acquisition Economics — Q3 Analysis, 2023-10-27
1. Scope, sources and assumptions
- Sources: Q3_Marketing_Data.xlsx (E1), Retention_Export.csv (E2)
- Currency: USD | Scale: 1 | Period Unit: Month
- Horizon: 24 Periods | Discount Rate: 10% (User-supplied)
2. CAC and LTV by cohort
| Cohort | Source | New customers | Spend | CAC | LTV | LTV/CAC | Net value | Verdict |
|---|---|---|---|---|---|---|---|---|
| 2023-07 | 500 | 50,000 | 100.00 | 285.50 | 2.86 | 185.50 | Pass | |
| 2023-07 | 200 | 30,000 | 150.00 | 410.20 | 2.73 | 260.20 | Pass |
3. Retention and payback
| Cohort | Avg churn | Latest churn | Survival at horizon | Simple payback | Payback | Discounted payback | GRR | NRR |
|---|---|---|---|---|---|---|---|---|
| 2023-07 (FB) | 5.0% | 4.8% | 29.2% | 8.0 | 10.5 | 11.2 | 88% | 92% |
| 2023-07 (GOOG) | 3.5% | 3.2% | 42.4% | 9.0 | 11.2 | 12.1 | 91% | 105% |
4. Acquisition sources
| Source | Customers | Spend | CAC | Weighted LTV | LTV/CAC | Net value | Verdict |
|---|---|---|---|---|---|---|---|
| 500 | 50,000 | 100.00 | 285.50 | 2.86 | 92,750 | Pass | |
| 200 | 30,000 | 150.00 | 410.20 | 2.73 | 52,040 | Pass | |
| Overall | 700 | 80,000 | 114.28 | 321.13 | 2.81 | 144,790 | Pass |
6. Undefined metrics and data gaps
Information gap — organizational validation required: Service cost per customer was not provided for the Google cohort; LTV reflects gross margin only.
8. Interpretation and items for human review
- The Facebook cohort shows higher capital efficiency with a shorter payback period despite lower ARPU.
- Google acquisition exhibits 105% NRR, suggesting strong expansion revenue that offsets the higher CAC.
Analytical estimate — validation required: Churn sensitivity indicates that a 20% increase in churn would drop Google LTV/CAC below the 2.0x threshold.
This analysis supports, and does not replace, professional judgment and management's decision. Any change to marketing spend, pricing or channel mix is marked
Management decision required.
Next steps
- Provide service cost data to refine the Google cohort's net margin.
- Run a 36-month horizon comparison to see long-term expansion impact.
- Validate Facebook's expansion revenue assumptions to confirm NRR accuracy.
Q3_Marketing_Data.xlsx
CSV · data export
Example file from a real run - the skill writes it into your workspace.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop guessing if your marketing spend is actually working. Most lifetime value calculations rely on dangerous infinite-horizon shortcuts that hide real churn risks. This skill provides a deterministic engine to compute unit economics with surgical precision.
What it does
- Calculate CAC and LTV by cohort and acquisition source using contribution-adjusted margins.
- Analyze retention through survival curves at the horizon, including Gross Revenue Retention (GRR) and Net Revenue Retention (NRR).
- Determine payback periods including simple, contribution-based, and discounted payback metrics.
- Run sensitivity testing to show how shifts in churn rates or margins impact your LTV/CAC ratios.
- Identify source profitability by aggregating performance across different acquisition channels.
How it works
- The agent extracts cohort data, spend, customer counts, and revenue movements from your documents.
- It generates a structured
request.jsonfile following a strict schema to ensure data integrity. - A deterministic Python script processes the arithmetic using exact decimals to prevent rounding errors.
- The agent generates a comprehensive report with specific sections for CAC, retention, sensitivity, and data gaps.
Frameworks & tools
The skill uses a self-contained Python engine for all calculations. It adheres to a strict input schema for JSON-based data validation and supports multi-language analysis in English and French.
Why this beats prompting it yourself
LLMs frequently hallucinate financial arithmetic and struggle with complex cohort decay. This skill offloads the math to a specialized script, ensuring that LTV is always calculated over a realistic finite horizon rather than a vague perpetuity.
Use cases
- Auditing unit economics for subscription or e-commerce businesses before budget planning.
- Comparing the true payback period of paid social versus organic acquisition channels.
- Stress-testing a business model by seeing where LTV/CAC falls if churn doubles.
- Identifying specific cohorts where high service costs are eroding lifetime value.
Known limitations
Does not support company valuation, DCF modeling, or IFRS/GAAP accounting claims. Only processes one currency and scale per request and requires explicit user targets for benchmarking.
No company valuations or GAAP compliance. Single currency/scale per run. No industry benchmarks provided. Requires finite horizon parameters.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 5 days ago