Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Calculate portfolio risk metrics including VaR, CVaR, Sharpe, Sortino, and drawdown analysis. Use when measuring portfolio risk, implementing risk limits, or building risk monitoring systems.
.claude/skills/itamarzand88-risk-metrics-calculation/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 6% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -19% | 0% |
| case-17 | ✓→✓ | ＝ Same ✓ | 15% | 0% |
| case-01 | ✓→✓ | ＝ Same ✓ | 15% | 0% |
<!-- source: wshobson-risk-metrics-calculation — https://raw.githubusercontent.com/wshobson/agents/main/plugins/quantitative-trading/skills/risk-metrics-calculation/SKILL.md -->
Comprehensive risk measurement toolkit for portfolio management, including Value at Risk, Expected Shortfall, and drawdown analysis.
| Category | Metrics | Use Case | | ----------------- | --------------- | -------------------- | | Volatility | Std Dev, Beta | General risk | | Tail Risk | VaR, CVaR | Extreme losses | | Drawdown | Max DD, Calmar | Capital preservation | | Risk-Adjusted | Sharpe, Sortino | Performance |
Intraday: Minute/hourly VaR for day traders
Daily: Standard risk reporting
Weekly: Rebalancing decisions
Monthly: Performance attribution
Annual: Strategic allocationDetailed pattern documentation lives in references/details.md. Read that file when the navigation tier above is insufficient.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-17 | pass→pass | 14,265 | 14,167 | -1% | 1 | 1 | 0% | 2,776 | 3,182 | +15% | 0 | 0 | — |
case-01 | pass→pass | 15,664 | 14,512 | -7% | 1 | 1 | 0% | 3,005 | 3,462 | +15% | 0 | 0 | — |
case-02 | pass→pass | 7,015 | 5,703 | -19% | 1 | 1 | 0% | 1,345 | 1,564 | +16% | 0 | 0 | — |
case-03 | pass→pass | 9,293 | 7,732 | -17% | 1 | 1 | 0% | 1,832 | 1,997 | +9% | 0 | 0 | — |
case-04 | fail→pass | 8,093 | 7,566 | -7% | 1 | 1 | 0% | 1,553 | 1,982 | +28% | 0 | 0 | — |
case-05 | pass→pass | 8,120 | 6,331 | -22% | 1 | 1 | 0% | 1,718 | 1,724 | +0% | 0 | 0 | — |
case-06 | pass→pass | 6,815 | 4,444 | -35% | 1 | 1 | 0% | 1,409 | 1,338 | -5% | 0 | 0 | — |
case-16 | pass→pass | 6,013 | 2,602 | -57% | 1 | 1 | 0% | 1,278 | 992 | -22% | 0 | 0 | — |
case-07 | pass→pass | 6,404 | 6,982 | +9% | 1 | 1 | 0% | 1,283 | 1,683 | +31% | 0 | 0 | — |
case-08 | pass→pass | 11,098 | 7,786 | -30% | 1 | 1 | 0% | 1,992 | 1,809 | -9% | 0 | 0 | — |
case-09 | pass→pass | 12,393 | 12,156 | -2% | 1 | 1 | 0% | 2,228 | 2,793 | +25% | 0 | 0 | — |
case-10 | fail→pass | 11,425 | 10,385 | -9% | 1 | 1 | 0% | 2,164 | 2,304 | +6% | 0 | 0 | — |
case-11 | pass→pass | 8,017 | 2,150 | -73% | 1 | 1 | 0% | 1,513 | 866 | -43% | 0 | 0 | — |
case-12 | fail→pass | 6,834 | 3,179 | -53% | 1 | 1 | 0% | 1,333 | 1,074 | -19% | 0 | 0 | — |
case-13 | pass→pass | 6,721 | 1,965 | -71% | 1 | 1 | 0% | 1,388 | 825 | -41% | 0 | 0 | — |
case-14 | pass→pass | 3,762 | 2,352 | -37% | 1 | 1 | 0% | 674 | 837 | +24% | 0 | 0 | — |
case-15 | pass→pass | 5,362 | 3,236 | -40% | 1 | 1 | 0% | 1,017 | 1,100 | +8% | 0 | 0 | — |
case-18 | pass→pass | 2,823 | 2,181 | -23% | 1 | 1 | 0% | 572 | 917 | +60% | 0 | 0 | — |
case-19 | pass→pass | 3,500 | 2,047 | -42% | 1 | 1 | 0% | 691 | 837 | +21% | 0 | 0 | — |
case-20 | pass→pass | 13,776 | 12,411 | -10% | 1 | 1 | 0% | 3,685 | 3,548 | -4% | 0 | 0 | — |
case-21 | pass→pass | 15,340 | 15,479 | +1% | 1 | 1 | 0% | 2,754 | 3,467 | +26% | 0 | 0 | — |
case-22 | pass→pass | 11,956 | 11,697 | -2% | 1 | 1 | 0% | 2,526 | 2,971 | +18% | 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.