Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Manages organizational risk registers. Performs risk assessments, calculates risk scores, tracks mitigations, and generates risk reports for leadership.
.claude/skills/grcengclub-risk-register-manager/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 45% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -10% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -64% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -41% | 0% |
| case-09 | ✓→✗ | ▼ Worse | 24% | 0% |
Maintains and analyzes organizational risk registers.
The register is user-owned state. Write one file per risk under ./grc-data/risks/, keep it reviewable in Git, and use schemas/risk.schema.json as the contract for JSON or JSON-equivalent YAML.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-08 | pass→pass | 9,789 | 2,536 | -74% | 1 | 1 | 0% | 825 | 670 | -19% | 0 | 0 | — |
case-01 | fail→pass | 12,868 | 32,775 | +155% | 1 | 1 | 0% | 2,331 | 3,385 | +45% | 0 | 0 | — |
case-02 | fail→fail | 14,278 | 3,382 | -76% | 1 | 1 | 0% | 2,140 | 828 | -61% | 0 | 0 | — |
case-03 | fail→pass | 19,173 | 14,279 | -26% | 1 | 1 | 0% | 2,871 | 2,591 | -10% | 0 | 0 | — |
case-04 | fail→pass | 10,995 | 1,831 | -83% | 1 | 1 | 0% | 1,687 | 601 | -64% | 0 | 0 | — |
case-05 | fail→pass | 11,037 | 4,125 | -63% | 1 | 1 | 0% | 1,661 | 981 | -41% | 0 | 0 | — |
case-06 | pass→pass | 9,276 | 4,616 | -50% | 1 | 1 | 0% | 1,406 | 1,050 | -25% | 0 | 0 | — |
case-07 | pass→pass | 5,337 | 2,401 | -55% | 1 | 1 | 0% | 778 | 688 | -12% | 0 | 0 | — |
case-09 | pass→fail | 6,342 | 6,176 | -3% | 1 | 1 | 0% | 899 | 1,119 | +24% | 0 | 0 | — |
case-10 | pass→pass | 9,416 | 5,602 | -41% | 1 | 1 | 0% | 1,452 | 1,222 | -16% | 0 | 0 | — |
case-11 | pass→pass | 9,216 | 5,672 | -38% | 1 | 1 | 0% | 1,441 | 1,230 | -15% | 0 | 0 | — |
case-12 | pass→pass | 4,827 | 4,104 | -15% | 1 | 1 | 0% | 665 | 861 | +29% | 0 | 0 | — |
case-13 | pass→pass | 8,322 | 5,140 | -38% | 1 | 1 | 0% | 1,165 | 1,019 | -13% | 0 | 0 | — |
case-14 | pass→pass | 6,629 | 4,875 | -26% | 1 | 1 | 0% | 1,001 | 976 | -2% | 0 | 0 | — |
case-15 | pass→pass | 6,757 | 5,322 | -21% | 1 | 1 | 0% | 1,028 | 1,121 | +9% | 0 | 0 | — |
case-16 | pass→pass | 11,944 | 12,992 | +9% | 1 | 1 | 0% | 1,836 | 2,474 | +35% | 0 | 0 | — |
case-17 | fail→fail | 14,094 | 10,027 | -29% | 1 | 1 | 0% | 2,050 | 1,778 | -13% | 0 | 0 | — |
case-18 | fail→fail | 7,984 | 7,132 | -11% | 1 | 1 | 0% | 1,210 | 1,321 | +9% | 0 | 0 | — |
case-19 | pass→pass | 9,623 | 6,743 | -30% | 1 | 1 | 0% | 1,593 | 1,253 | -21% | 0 | 0 | — |
case-20 | fail→fail | 9,139 | 4,969 | -46% | 1 | 1 | 0% | 1,322 | 1,131 | -14% | 0 | 0 | — |
case-21 | pass→pass | 9,520 | 3,381 | -64% | 1 | 1 | 0% | 1,377 | 836 | -39% | 0 | 0 | — |
case-22 | pass→pass | 20,537 | 15,367 | -25% | 1 | 1 | 0% | 3,407 | 2,915 | -14% | 0 | 0 | — |
case-23 | pass→pass | 14,471 | 15,346 | +6% | 1 | 1 | 0% | 2,603 | 3,339 | +28% | 0 | 0 | — |
case-24 | pass→pass | 21,318 | 16,936 | -21% | 1 | 1 | 0% | 3,368 | 3,032 | -10% | 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. 24 cases were attempted. The headline lift of +13 percentage points is the difference between those two pass rates over the 24 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.