Install any skill in seconds. Free to start, no credit card required.
Get Started Free →高级财务建模套件,包含DCF估值、敏感性分析、蒙特卡洛模拟和场景规划。当用户需要对企业、项目或并购交易进行投资分析、股权估值、IRR/MOIC计算、WACC建模,或要求建立DCF模型、运行概率模拟、制作敏感性表格时,请主动使用此技能。
.claude/skills/ethanyoq-creating-financial-models/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-09 | ✗→✓ | ▲ Improved | 83% | 0% |
| case-14 | ✗→✓ | ▲ Improved | 56% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 2% | 0% |
| case-02 | ✓→✓ | = Same ✓ | 47% | 0% |
A comprehensive financial modeling toolkit for investment analysis, valuation, and risk assessment using industry-standard methodologies.
"Build a DCF model for this technology company using the attached financials"
"Run a Monte Carlo simulation on this acquisition model with 5,000 iterations"
"Create sensitivity analysis showing impact of growth rate and WACC on valuation"
"Develop three scenarios for this expansion project with probability weights"
示例输出格式(DCF 汇总): | 指标 | 数值 | |------|------| | 企业价值(EV) | $450M | | 净债务 | $80M | | 股权价值 | $370M | | 隐含 EV/EBITDA | 12.5x |
暂无可执行脚本。DCF 计算和敏感性分析由 Claude 直接以表格/代码块形式输出。 如需 Python 脚本版本,请在请求中注明,Claude 将即时生成。
所有模型输出均基于用户提供的假设,不构成投资建议。重大决策前请结合专业判断。
The model automatically performs:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | pass→pass | 29,748 | 11,292 | -62% | 1 | 1 | 0% | 2,935 | 2,984 | +2% | 0 | 0 | — |
case-01 | fail→fail | 19,924 | 23,063 | +16% | 1 | 1 | 0% | 3,573 | 5,808 | +63% | 0 | 0 | — |
case-02 | pass→pass | 6,680 | 5,103 | -24% | 1 | 1 | 0% | 1,326 | 1,947 | +47% | 0 | 0 | — |
case-03 | pass→pass | 7,924 | 9,227 | +16% | 1 | 1 | 0% | 1,663 | 2,992 | +80% | 0 | 0 | — |
case-05 | fail→fail | 8,200 | 7,750 | -5% | 1 | 1 | 0% | 1,435 | 2,606 | +82% | 0 | 0 | — |
case-06 | pass→pass | 8,862 | 9,395 | +6% | 1 | 1 | 0% | 1,515 | 2,783 | +84% | 0 | 0 | — |
case-07 | pass→pass | 17,368 | 22,778 | +31% | 1 | 1 | 0% | 3,196 | 5,978 | +87% | 0 | 0 | — |
case-08 | fail→fail | 22,585 | 23,893 | +6% | 1 | 1 | 0% | 4,686 | 5,894 | +26% | 0 | 0 | — |
case-09 | fail→pass | 6,576 | 6,994 | +6% | 1 | 1 | 0% | 1,333 | 2,437 | +83% | 0 | 0 | — |
case-10 | pass→pass | 9,708 | 11,079 | +14% | 1 | 1 | 0% | 2,084 | 3,341 | +60% | 0 | 0 | — |
case-11 | pass→pass | 14,878 | 17,527 | +18% | 1 | 1 | 0% | 2,355 | 4,158 | +77% | 0 | 0 | — |
case-12 | pass→pass | 12,934 | 10,949 | -15% | 1 | 1 | 0% | 2,260 | 3,117 | +38% | 0 | 0 | — |
case-13 | pass→pass | 7,179 | 7,946 | +11% | 1 | 1 | 0% | 1,415 | 2,495 | +76% | 0 | 0 | — |
case-14 | fail→pass | 6,323 | 6,190 | -2% | 1 | 1 | 0% | 1,486 | 2,320 | +56% | 0 | 0 | — |
case-15 | fail→pass | 17,313 | 3,208 | -81% | 1 | 1 | 0% | 3,513 | 1,610 | -54% | 0 | 0 | — |
case-16 | pass→pass | 10,161 | 13,482 | +33% | 1 | 1 | 0% | 2,143 | 3,943 | +84% | 0 | 0 | — |
case-17 | pass→pass | 13,973 | 12,018 | -14% | 1 | 1 | 0% | 2,201 | 3,425 | +56% | 0 | 0 | — |
case-18 | pass→pass | 18,174 | 19,187 | +6% | 1 | 1 | 0% | 2,913 | 4,667 | +60% | 0 | 0 | — |
case-19 | pass→pass | 15,770 | 17,244 | +9% | 1 | 1 | 0% | 2,736 | 4,061 | +48% | 0 | 0 | — |
case-20 | fail→fail | 9,278 | 7,909 | -15% | 1 | 1 | 0% | 1,868 | 2,543 | +36% | 0 | 0 | — |
case-21 | fail→fail | 12,943 | 10,804 | -17% | 1 | 1 | 0% | 2,496 | 2,896 | +16% | 0 | 0 | — |
case-22 | pass→pass | 15,375 | 22,681 | +48% | 1 | 1 | 0% | 3,123 | 5,537 | +77% | 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 +14 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.