Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Build comprehensive 3-5 year financial models with revenue projections, cost structures, cash flow analysis, and scenario planning for early-stage startups.
.claude/skills/sickn33-startup-financial-modeling/SKILL.md| Model | Eval pass | Runs |
|---|---|---|
| gemini-3.6-flash | 100% | 32 |
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 68% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 83% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 104% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 189% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 92% | 0% |
Build comprehensive 3-5 year financial models with revenue projections, cost structures, cash flow analysis, and scenario planning for early-stage startups.
resources/implementation-playbook.md.Financial modeling provides the quantitative foundation for startup strategy, fundraising, and operational planning. Create realistic projections using cohort-based revenue modeling, detailed cost structures, and scenario analysis to support decision-making and investor presentations.
Cohort-Based Projections: Build revenue from customer acquisition and retention by cohort.
Formula:
MRR = Σ (Cohort Size × Retention Rate × ARPU)
ARR = MRR × 12Key Inputs:
Operating Expenses Categories:
Components:
Formula:
Runway = Current Cash Balance / Monthly Burn Rate
Monthly Burn = Monthly Revenue - Monthly ExpensesRole-Based Hiring Plan: Track headcount by department and role.
Key Metrics:
Typical Ratios (Early-Stage SaaS):
Conservative Scenario (P10):
Base Scenario (P50):
Optimistic Scenario (P90):
Detailed Projections: 3 Years
High-Level Projections: Years 4-5
Clarify revenue model and pricing.
SaaS Model:
Marketplace Model:
Transactional Model:
Use cohort-based methodology for accuracy.
Monthly Customer Acquisition: Define new customers acquired each month.
Retention Curve: Model customer retention over time.
Typical SaaS Retention:
Revenue Calculation: For each cohort, calculate retained customers × ARPU for each month.
Break down costs by category and behavior.
Fixed vs. Variable:
Scaling Assumptions:
Model headcount growth by role and department.
Inputs:
Example:
Engineer: $150K salary × 1.35 = $202K fully-loaded
Sales Rep: $100K OTE × 1.30 = $130K fully-loadedCalculate monthly cash position and runway.
Monthly Cash Flow:
Beginning Cash
+ Revenue Collected (consider payment terms)
- Operating Expenses Paid
- CapEx
= Ending CashRunway Calculation:
If Ending Cash < 0:
Funding Need = Negative Cash Balance
Runway = 0
Else:
Runway = Ending Cash / Average Monthly BurnTrack metrics that matter for stage.
Revenue Metrics:
Unit Economics:
Efficiency Metrics:
Cash Metrics:
Create three scenarios with different assumptions.
Variable Assumptions:
Fixed Assumptions:
Revenue Drivers:
Key Ratios:
Example Projection:
Year 1: $500K ARR, 50 customers, $100K MRR by Dec
Year 2: $2.5M ARR, 200 customers, $208K MRR by Dec
Year 3: $8M ARR, 600 customers, $667K MRR by DecRevenue Drivers:
Key Ratios:
Example Projection:
Year 1: $5M GMV, 15% take rate = $750K revenue
Year 2: $20M GMV, 15% take rate = $3M revenue
Year 3: $60M GMV, 15% take rate = $9M revenueRevenue Drivers:
Key Ratios:
Revenue Drivers:
Key Ratios:
Pre-Money Valuation: Based on metrics and comparables.
Dilution:
Post-Money = Pre-Money + Investment
Dilution % = Investment / Post-MoneyUse of Funds: Allocate funding to extend runway and achieve milestones.
Example:
Raise: $5M at $20M pre-money
Post-Money: $25M
Dilution: 20%
Use of Funds:
- Product Development: $2M (40%)
- Sales & Marketing: $2M (40%)
- G&A and Operations: $0.5M (10%)
- Working Capital: $0.5M (10%)Identify Key Milestones:
Funding Amount: Ensure runway to achieve next milestone + 6 months buffer.
Pitfall 1: Overly Optimistic Revenue
Pitfall 2: Underestimating Costs
Pitfall 3: Ignoring Cash Flow Timing
Pitfall 4: Static Headcount
Pitfall 5: Not Scenario Planning
Sanity Checks:
Benchmark Against Peers: Compare key metrics to similar companies at similar stage.
Investor Feedback: Share model with advisors or investors for feedback on assumptions.
For detailed model structures and advanced techniques:
references/model-templates.md - Complete financial model templates by business modelreferences/unit-economics.md - Deep dive on CAC, LTV, payback, and efficiency metricsreferences/fundraising-scenarios.md - Modeling funding rounds and dilutionWorking financial models with formulas:
examples/saas-financial-model.md - Complete 3-year SaaS model with cohort analysisexamples/marketplace-model.md - Marketplace GMV and take rate projectionsexamples/scenario-analysis.md - Three-scenario framework with sensitivitiesTo create a startup financial model:
For complete templates and formulas, reference the references/ and examples/ files.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | pass→pass | 13,710 | 5,772 | -58% | 1 | 1 | 0% | 2,394 | 4,138 | +73% | 0 | 0 | — |
case-12 | pass→pass | 10,175 | 4,728 | -54% | 1 | 1 | 0% | 1,845 | 3,829 | +108% | 0 | 0 | — |
case-22 | pass→pass | 18,818 | 14,383 | -24% | 1 | 1 | 0% | 3,090 | 5,423 | +76% | 0 | 0 | — |
case-01 | fail→pass | 15,843 | 11,357 | -28% | 1 | 1 | 0% | 3,039 | 5,095 | +68% | 0 | 0 | — |
case-02 | pass→pass | 4,969 | 4,683 | -6% | 1 | 1 | 0% | 1,011 | 3,972 | +293% | 0 | 0 | — |
case-03 | pass→pass | 10,123 | 3,964 | -61% | 1 | 1 | 0% | 1,906 | 3,791 | +99% | 0 | 0 | — |
case-04 | fail→pass | 16,211 | 11,309 | -30% | 1 | 1 | 0% | 2,836 | 5,182 | +83% | 0 | 0 | — |
case-05 | pass→pass | 15,976 | 15,209 | -5% | 1 | 1 | 0% | 2,766 | 5,724 | +107% | 0 | 0 | — |
case-06 | fail→pass | 11,470 | 5,385 | -53% | 1 | 1 | 0% | 1,893 | 3,856 | +104% | 0 | 0 | — |
case-07 | fail→fail | 13,030 | 7,480 | -43% | 1 | 1 | 0% | 2,412 | 4,346 | +80% | 0 | 0 | — |
case-08 | pass→pass | 11,065 | 8,607 | -22% | 1 | 1 | 0% | 1,986 | 4,550 | +129% | 0 | 0 | — |
case-09 | pass→pass | 9,914 | 4,992 | -50% | 1 | 1 | 0% | 1,788 | 3,953 | +121% | 0 | 0 | — |
case-10 | pass→pass | 8,568 | 6,588 | -23% | 1 | 1 | 0% | 1,580 | 4,222 | +167% | 0 | 0 | — |
case-13 | pass→pass | 13,820 | 8,467 | -39% | 1 | 1 | 0% | 2,594 | 4,708 | +81% | 0 | 0 | — |
case-14 | fail→pass | 8,364 | 7,056 | -16% | 1 | 1 | 0% | 1,410 | 4,073 | +189% | 0 | 0 | — |
case-15 | pass→pass | 11,535 | 4,479 | -61% | 1 | 1 | 0% | 1,936 | 3,806 | +97% | 0 | 0 | — |
case-16 | fail→pass | 12,966 | 7,326 | -43% | 1 | 1 | 0% | 2,326 | 4,465 | +92% | 0 | 0 | — |
case-17 | pass→pass | 12,141 | 4,978 | -59% | 1 | 1 | 0% | 2,008 | 3,851 | +92% | 0 | 0 | — |
case-18 | pass→pass | 16,028 | 11,240 | -30% | 1 | 1 | 0% | 2,574 | 4,883 | +90% | 0 | 0 | — |
case-19 | pass→pass | 13,512 | 5,592 | -59% | 1 | 1 | 0% | 2,169 | 3,938 | +82% | 0 | 0 | — |
case-20 | pass→pass | 22,826 | 15,317 | -33% | 1 | 1 | 0% | 4,106 | 5,990 | +46% | 0 | 0 | — |
case-21 | pass→pass | 13,533 | 8,361 | -38% | 1 | 1 | 0% | 2,288 | 4,444 | +94% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +23 percentage points is the difference between those two pass rates over the 22 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.