Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Assess portfolio risk using npx neural-trader — VaR, CVaR, Sharpe, position sizing, circuit breaker status
.claude/skills/ruvnet-trader-risk/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -6% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -51% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -55% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-15 | ✗→✓ | ▲ Improved | -47% | 0% |
Assess portfolio and position risk using neural-trader's risk engine.
Steps:
npm ls neural-trader 2>/dev/null || npm install --ignore-scripts neural-trader
bash # Single position npx neural-trader --risk assess --symbol TICKER npx neural-trader --var --symbol TICKER --investment 10000
# Portfolio-wide npx neural-trader --risk assess --portfolio NAME npx neural-trader --correlation --portfolio NAME --flag-threshold 0.8
bash npx neural-trader --risk-tolerance 0.02 --symbol TICKER npx neural-trader --position-sizing kelly --symbol TICKER
mcp__plugin_ruflo-core_ruflo__memory_store({ key: "risk-TICKER-DATE", value: "RISK_METRICS", namespace: "trading-risk" })
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→pass | 9,571 | 6,884 | -28% | 1 | 1 | 0% | 1,817 | 1,712 | -6% | 0 | 0 | — |
case-01 | fail→fail | 12,230 | 5,730 | -53% | 1 | 1 | 0% | 1,258 | 846 | -33% | 0 | 0 | — |
case-02 | fail→fail | 15,155 | 10,651 | -30% | 1 | 1 | 0% | 3,012 | 852 | -72% | 0 | 0 | — |
case-03 | fail→fail | 13,954 | 4,646 | -67% | 1 | 1 | 0% | 2,811 | 693 | -75% | 0 | 0 | — |
case-05 | fail→pass | 11,179 | 3,273 | -71% | 1 | 1 | 0% | 1,944 | 953 | -51% | 0 | 0 | — |
case-06 | fail→fail | 7,879 | 6,716 | -15% | 1 | 1 | 0% | 1,293 | 646 | -50% | 0 | 0 | — |
case-07 | fail→fail | 9,840 | 9,734 | -1% | 1 | 1 | 0% | 1,818 | 1,504 | -17% | 0 | 0 | — |
case-08 | fail→fail | 17,162 | 4,734 | -72% | 1 | 1 | 0% | 3,391 | 655 | -81% | 0 | 0 | — |
case-09 | pass→fail | 12,375 | 7,913 | -36% | 1 | 1 | 0% | 2,089 | 757 | -64% | 0 | 0 | — |
case-10 | fail→pass | 10,444 | 6,580 | -37% | 1 | 1 | 0% | 1,746 | 792 | -55% | 0 | 0 | — |
case-11 | pass→pass | 14,752 | 7,316 | -50% | 1 | 1 | 0% | 2,583 | 1,129 | -56% | 0 | 0 | — |
case-12 | pass→fail | 12,265 | 5,549 | -55% | 1 | 1 | 0% | 2,267 | 676 | -70% | 0 | 0 | — |
case-13 | pass→pass | 16,708 | 5,222 | -69% | 1 | 1 | 0% | 1,854 | 868 | -53% | 0 | 0 | — |
case-14 | fail→pass | 7,099 | 2,598 | -63% | 1 | 1 | 0% | 1,303 | 766 | -41% | 0 | 0 | — |
case-15 | fail→pass | 6,790 | 1,706 | -75% | 1 | 1 | 0% | 1,203 | 643 | -47% | 0 | 0 | — |
case-16 | fail→pass | 12,012 | 8,996 | -25% | 1 | 1 | 0% | 2,123 | 1,984 | -7% | 0 | 0 | — |
case-17 | fail→pass | 8,372 | 2,711 | -68% | 1 | 1 | 0% | 1,511 | 893 | -41% | 0 | 0 | — |
case-18 | fail→pass | 7,612 | 3,052 | -60% | 1 | 1 | 0% | 1,333 | 934 | -30% | 0 | 0 | — |
case-19 | fail→fail | 8,493 | 9,014 | +6% | 1 | 1 | 0% | 1,570 | 751 | -52% | 0 | 0 | — |
case-20 | pass→fail | 5,240 | 13,422 | +156% | 1 | 1 | 0% | 1,053 | 1,798 | +71% | 0 | 0 | — |
case-21 | fail→fail | 4,968 | 8,677 | +75% | 1 | 1 | 0% | 952 | 959 | +1% | 0 | 0 | — |
case-22 | fail→fail | 13,810 | 30,257 | +119% | 1 | 1 | 0% | 2,886 | 6,510 | +126% | 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 12 counted toward the lift figure. The other 10 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 +23 percentage points is the difference between those two pass rates over the 12 comparable cases. 4 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.