ltv-caclisted

# LTV / CAC Compute LTV, CAC payback, and LTV/CAC ratio with the four canonical formulas side by side. Anchor the verdict on Skok's 3:1 rule, layer on a16z NDR, Sequoia contribution-margin, and Tunguz AI-inference adjustments. Output a styled Excel workbook with a sensitivity heatmap and a 36-month synthetic cohort projection. ## Step 1: Ask the user up to 6 inputs Ask in order. The first 3 are required; the rest have defaults. 1. **ARPU** (monthly revenue per customer, $), e.g. `200` 2. **Customer churn rate** (monthly, decimal), e.g. `0.03` for 3%/mo 3. **CAC** (customer acquisition cost, $), e.g. `1500` 4. **Net revenue expansion** (monthly, decimal, optional), e.g. `0.005` for 0.5%/mo. Default `0`. If they have NDR > 100%, this is positive. 5. **Gross margin** (decimal, optional), e.g. `0.78`. Default `0.78` (78%, typical SaaS). 6. **Inference / variable cost per customer per month** ($, optional), only relevant for AI products. Default `0`. If the user is hesitant on inputs, suggest they start with the example fixture (`examples/inputs.json`). ## Step 2: Run ```bash python skills/ltv-cac/run.py \ --arpu 200 \ --churn 0.03 \ --cac 1500 \ --expansion 0.005 \ --gross-margin 0.78 \ --inference-cost 0 \ --out-dir /tmp/ltv-cac-<client>-<date> ``` Or load all inputs from a JSON file: ```bash python skills/ltv-cac/run.py --inputs path/to/inputs.json --out-dir /tmp/ltv-cac ``` ## Step 3: KPIs the user gets **Verdict sheet (the headline)** - **Skok basic L