Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use when preparing executive reports, evaluating investments, or calculating ROI/break-even/payback period. 30-minute analysis (87.5% time saving). Includes scenario analysis.
.claude/skills/nicepkg-roi-analyzer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | 138% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 77% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 67% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 82% | 0% |
| case-06 | ✗→✓ | ▲ Improved | 60% | 0% |
> Purpose: Deliver rapid, rigorous financial analysis for investment decisions, turning 4 hours of spreadsheet work into 30 minutes of strategic insight with 3-scenario modeling and clear recommendations.
Use this skill when the user's request involves:
You are an executive financial analyst that delivers decision-ready investment analysis in 30 minutes (87.5% time saving vs. spreadsheet work), with 3-scenario modeling, break-even thresholds, and clear INVEST/REVIEW/REJECT recommendations.
Formula: ROI = (Net Profit / Total Investment) × 100%
Targets:
Example:
Investment: 100M KRW
Revenue: 200M KRW
Operating Costs: 50M KRW
Net Profit: 200M - 50M - 100M = 50M KRW
ROI: (50M / 100M) × 100% = 50% ⚠️ REVIEWFormula (Project): Break-Even = Investment / Monthly Net Profit
Formula (Conversion): Break-Even Rate = Investment / Potential Revenue
Targets:
Example:
Phase 0 Investment: 50M KRW
Phase 1 Contract: 200M KRW
Break-Even: 50M / 200M = 25% conversion needed ✅Formula: Payback = Investment / Monthly Net Profit
Targets:
Purpose: Test assumptions and de-risk decisions by modeling multiple outcomes.
Decision Rule: If worst-case ROI ≥ 0%, investment is low-risk
Output Template:
| Case | Assumptions | Revenue | Profit | ROI | Assessment | |------|------------|---------|--------|-----|------------| | Worst | Pessimistic] | | | | ⚠️ Risk level | | Realistic | Expected] | | | | ✅ Target | | Best | Optimistic] | | | | ✅ Upside |
User: "Should we invest 50M KRW in a 1-month Phase 0 trial? Phase 1 contract would be 208M KRW if we convert."
Analysis:
markdown## Phase 0 Investment Analysis **Investment**: 50M KRW (1 month) **Potential Revenue**: 208M KRW (Phase 1, if convert) ### Scenario Analysis | Case | Conversion | Revenue | Profit | ROI | |------|-----------|---------|--------|-----| | **Worst** | 30% | 62.4M | 12.4M | 25% ⚠️ | | **Realistic** | 70% | 145.6M | 95.6M | 191% ✅ | | **Best** | 90% | 187.2M | 137.2M | 274% ✅ | **Break-Even**: 27% conversion rate (very achievable) **Decision**: ✅ INVEST - Realistic ROI 191% is excellent - Even worst-case 25% ROI is profitable - Break-even 27% << realistic 70% (low risk)
| Situation | Primary Metric | Secondary | Why | |-----------|---------------|-----------|-----| | All investments | ROI | Scenario Analysis | Foundation | | Uncertain success | Break-Even | ROI | Risk assessment | | Cash flow critical | Payback Period | ROI | Runway concerns | | Strategic decisions | Scenario Analysis | All others | Risk modeling |
Always Include:
Never:
Use this for leadership presentations:
[Investment amount] achieves [ROI%] ROI at [conversion/growth rate].
Break-even occurs at [threshold], with payback in [months].
Investment is [recommended/not recommended] [because reason].Example:
50M KRW Phase 0 investment achieves 191% ROI at 70% conversion.
Break-even occurs at 27% conversion, with payback in 1 month.
Investment is strongly recommended because worst-case ROI (25%) is still profitable.markdown✅ **INVEST** if: - ROI > 100% (realistic case) - Payback < 18 months - Break-even < 50% of realistic target - Worst-case ROI ≥ 0% (no loss scenario) ⚠️ **REVIEW** if: - ROI 50-100% - Payback 18-36 months - High dependency on single assumption - Requires negotiation to improve terms ❌ **REJECT** if: - ROI < 50% - Payback > 36 months - Break-even requires unrealistic assumptions (>70% of target)
This analyzer integrates with:
For Detailed Formulas: See REFERENCE.md for NPV, LTV, CAC, cohort analysis, sensitivity analysis
For Real-World Examples: See EXAMPLES.md for:
For Advanced Topics: See REFERENCE.md for risk assessment framework, decision trees, contingency planning
After applying this analysis, always reflect:
This reflection creates a virtuous cycle of continuous financial rigor.
For detailed usage and examples, see related documentation files.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 16,163 | 19,921 | +23% | 1 | 1 | 0% | 2,765 | 4,342 | +57% | 0 | 0 | — |
case-02 | fail→pass | 10,178 | 10,147 | -0% | 1 | 1 | 0% | 1,594 | 3,791 | +138% | 0 | 0 | — |
case-03 | fail→pass | 13,680 | 12,680 | -7% | 1 | 1 | 0% | 2,288 | 4,041 | +77% | 0 | 0 | — |
case-04 | fail→pass | 12,092 | 8,356 | -31% | 1 | 1 | 0% | 1,992 | 3,333 | +67% | 0 | 0 | — |
case-05 | fail→pass | 14,506 | 13,076 | -10% | 1 | 1 | 0% | 2,375 | 4,313 | +82% | 0 | 0 | — |
case-06 | fail→pass | 12,190 | 7,608 | -38% | 1 | 1 | 0% | 2,068 | 3,313 | +60% | 0 | 0 | — |
case-07 | fail→pass | 11,857 | 9,369 | -21% | 1 | 1 | 0% | 2,069 | 3,641 | +76% | 0 | 0 | — |
case-08 | fail→pass | 6,731 | 9,151 | +36% | 1 | 1 | 0% | 1,074 | 3,557 | +231% | 0 | 0 | — |
case-09 | pass→pass | 9,872 | 8,141 | -18% | 1 | 1 | 0% | 1,706 | 3,388 | +99% | 0 | 0 | — |
case-10 | pass→pass | 9,902 | 12,431 | +26% | 1 | 1 | 0% | 1,788 | 4,276 | +139% | 0 | 0 | — |
case-11 | fail→pass | 11,485 | 9,625 | -16% | 1 | 1 | 0% | 1,849 | 3,701 | +100% | 0 | 0 | — |
case-12 | fail→pass | 12,995 | 9,525 | -27% | 1 | 1 | 0% | 2,224 | 3,450 | +55% | 0 | 0 | — |
case-13 | fail→pass | 11,584 | 10,673 | -8% | 1 | 1 | 0% | 1,713 | 3,589 | +110% | 0 | 0 | — |
case-14 | fail→pass | 10,768 | 11,463 | +6% | 1 | 1 | 0% | 1,777 | 3,767 | +112% | 0 | 0 | — |
case-15 | pass→pass | 11,553 | 12,075 | +5% | 1 | 1 | 0% | 1,777 | 3,806 | +114% | 0 | 0 | — |
case-16 | pass→pass | 10,844 | 7,526 | -31% | 1 | 1 | 0% | 1,963 | 3,185 | +62% | 0 | 0 | — |
case-17 | fail→pass | 10,237 | 6,757 | -34% | 1 | 1 | 0% | 1,639 | 2,990 | +82% | 0 | 0 | — |
case-18 | fail→pass | 9,724 | 7,463 | -23% | 1 | 1 | 0% | 1,607 | 3,288 | +105% | 0 | 0 | — |
case-19 | pass→pass | 12,287 | 10,089 | -18% | 1 | 1 | 0% | 2,379 | 3,902 | +64% | 0 | 0 | — |
case-20 | pass→pass | 12,106 | 16,508 | +36% | 1 | 1 | 0% | 2,613 | 5,222 | +100% | 0 | 0 | — |
case-21 | pass→pass | 4,784 | 5,567 | +16% | 1 | 1 | 0% | 1,044 | 2,987 | +186% | 0 | 0 | — |
case-22 | pass→pass | 6,574 | 4,869 | -26% | 1 | 1 | 0% | 1,118 | 2,727 | +144% | 0 | 0 | — |
case-23 | fail→pass | 13,403 | 15,110 | +13% | 1 | 1 | 0% | 2,169 | 4,273 | +97% | 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. 23 cases were attempted. The headline lift of +61 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is 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.