Install any skill in seconds. Free to start, no credit card required.
Get Started Free →M&A deal modeling: accretion/dilution analysis, LBO models, DCF valuation, comparable company analysis, precedent transactions, and synergy estimation. Full three-statement merger models.
.claude/skills/mkurman-merger-model/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 134% | 0% |
| case-11 | ✗→✓ | ▲ Improved | 39% | 0% |
| case-16 | ✓→✗ | ▼ Worse | 22% | 0% |
| case-17 | ✓→✗ | ▼ Worse | 16% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 22% | 0% |
A merger model estimates the financial impact of an acquisition or merger: purchase price, financing mix, pro forma statements, synergies, accretion/dilution, leverage, and returns. Use it for M&A analysis, not just valuation in isolation.
Use this skill when:
A proper merger model usually includes:
pythondef accretion_dilution(acquirer_net_income, target_net_income, acquirer_shares, new_shares_issued, after_tax_synergies=0.0): pro_forma_income = acquirer_net_income + target_net_income + after_tax_synergies pro_forma_shares = acquirer_shares + new_shares_issued base_eps = acquirer_net_income / acquirer_shares pro_forma_eps = pro_forma_income / pro_forma_shares accretion_pct = (pro_forma_eps / base_eps - 1) * 100 return { 'base_eps': round(base_eps, 4), 'pro_forma_eps': round(pro_forma_eps, 4), 'accretion_pct': round(accretion_pct, 2), } print(accretion_dilution( acquirer_net_income=900, target_net_income=220, acquirer_shares=300, new_shares_issued=50, after_tax_synergies=40, ))
textUses: - equity purchase price - debt repayment / assumption - fees and expenses Sources: - cash on balance sheet - new debt - stock issuance
Always reconcile sources == uses.
pythondef rough_lbo_irr(entry_ebitda, entry_multiple, debt_pct, ebitda_growth, exit_multiple, years): entry_ev = entry_ebitda * entry_multiple debt = entry_ev * debt_pct equity = entry_ev - debt exit_ebitda = entry_ebitda * ((1 + ebitda_growth) ** years) remaining_debt = debt * 0.65 # simple placeholder assumption exit_ev = exit_ebitda * exit_multiple exit_equity = exit_ev - remaining_debt irr = (exit_equity / equity) ** (1 / years) - 1 return round(irr * 100, 2)
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 14,243 | 6,902 | -52% | 1 | 1 | 0% | 1,017 | 2,381 | +134% | 0 | 0 | — |
case-02 | pass→pass | 9,430 | 6,844 | -27% | 1 | 1 | 0% | 1,767 | 2,152 | +22% | 0 | 0 | — |
case-03 | pass→pass | 7,390 | 7,879 | +7% | 1 | 1 | 0% | 1,689 | 2,610 | +55% | 0 | 0 | — |
case-04 | pass→pass | 13,104 | 10,596 | -19% | 1 | 1 | 0% | 2,407 | 2,810 | +17% | 0 | 0 | — |
case-05 | pass→pass | 9,924 | 7,027 | -29% | 1 | 1 | 0% | 1,689 | 2,134 | +26% | 0 | 0 | — |
case-06 | pass→pass | 10,674 | 9,091 | -15% | 1 | 1 | 0% | 1,779 | 2,221 | +25% | 0 | 0 | — |
case-07 | pass→pass | 11,400 | 8,737 | -23% | 1 | 1 | 0% | 2,098 | 2,557 | +22% | 0 | 0 | — |
case-08 | pass→pass | 10,475 | 13,684 | +31% | 1 | 1 | 0% | 1,724 | 3,133 | +82% | 0 | 0 | — |
case-09 | pass→pass | 10,300 | 6,150 | -40% | 1 | 1 | 0% | 1,815 | 1,903 | +5% | 0 | 0 | — |
case-10 | pass→pass | 15,251 | 12,370 | -19% | 1 | 1 | 0% | 2,334 | 2,850 | +22% | 0 | 0 | — |
case-11 | fail→pass | 13,645 | 13,279 | -3% | 1 | 1 | 0% | 2,216 | 3,091 | +39% | 0 | 0 | — |
case-12 | pass→pass | 10,680 | 8,099 | -24% | 1 | 1 | 0% | 1,714 | 2,140 | +25% | 0 | 0 | — |
case-13 | pass→pass | 17,119 | 18,617 | +9% | 1 | 1 | 0% | 3,378 | 4,410 | +31% | 0 | 0 | — |
case-14 | pass→pass | 13,237 | 13,065 | -1% | 1 | 1 | 0% | 2,096 | 3,134 | +50% | 0 | 0 | — |
case-15 | pass→pass | 13,593 | 16,116 | +19% | 1 | 1 | 0% | 2,356 | 3,832 | +63% | 0 | 0 | — |
case-16 | pass→fail | 13,381 | 11,889 | -11% | 1 | 1 | 0% | 2,256 | 2,744 | +22% | 0 | 0 | — |
case-17 | pass→fail | 12,870 | 10,283 | -20% | 1 | 1 | 0% | 2,132 | 2,476 | +16% | 0 | 0 | — |
case-18 | pass→pass | 14,168 | 16,298 | +15% | 1 | 1 | 0% | 2,574 | 3,978 | +55% | 0 | 0 | — |
case-19 | pass→pass | 18,276 | 20,131 | +10% | 1 | 1 | 0% | 3,400 | 5,018 | +48% | 0 | 0 | — |
case-20 | pass→pass | 16,421 | 19,410 | +18% | 1 | 1 | 0% | 3,068 | 4,557 | +49% | 0 | 0 | — |
case-21 | pass→pass | 16,408 | 13,122 | -20% | 1 | 1 | 0% | 2,556 | 2,994 | +17% | 0 | 0 | — |
case-22 | pass→pass | 12,801 | 11,620 | -9% | 1 | 1 | 0% | 2,123 | 3,058 | +44% | 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, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of -33 percentage points is the difference between those two pass rates over the 21 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
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.