Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →name: x-scorecard
.claude/skills/x-cmd-scorecard/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -79% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -69% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -57% | 0% |
| case-14 | ✗→✓ | ▲ Improved | -48% | 0% |
name: x-scorecard description: | OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance.
Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
| Tool | Purpose | Install | |------|---------|---------| | x-cmd | Required module runtime | brew install x-cmd |
license: Apache-2.0 compatibility: POSIX Shell
metadata: author: Li Junhao version: "1.0.0" category: x-cmd-extension tags: x-cmd, security, scorecard, openssf, audit]
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 21,665 | 4,811 | -78% | 1 | 1 | 0% | 2,960 | 621 | -79% | 0 | 0 | — |
case-02 | fail→pass | 50,958 | 7,131 | -86% | 1 | 1 | 0% | 2,710 | 848 | -69% | 0 | 0 | — |
case-03 | pass→pass | 25,297 | 2,663 | -89% | 1 | 1 | 0% | 4,287 | 489 | -89% | 0 | 0 | — |
case-04 | fail→fail | 6,960 | 5,540 | -20% | 1 | 1 | 0% | 972 | 976 | +0% | 0 | 0 | — |
case-05 | fail→pass | 22,278 | 3,253 | -85% | 1 | 1 | 0% | 863 | 575 | -33% | 0 | 0 | — |
case-06 | pass→pass | 9,779 | 14,051 | +44% | 1 | 1 | 0% | 1,333 | 782 | -41% | 0 | 0 | — |
case-07 | fail→fail | 7,391 | 8,881 | +20% | 1 | 1 | 0% | 1,246 | 771 | -38% | 0 | 0 | — |
case-08 | fail→pass | 8,227 | 2,659 | -68% | 1 | 1 | 0% | 1,096 | 473 | -57% | 0 | 0 | — |
case-09 | pass→pass | 9,870 | 15,263 | +55% | 1 | 1 | 0% | 1,418 | 707 | -50% | 0 | 0 | — |
case-10 | pass→pass | 9,159 | 5,860 | -36% | 1 | 1 | 0% | 1,028 | 649 | -37% | 0 | 0 | — |
case-11 | pass→pass | 10,487 | 4,144 | -60% | 1 | 1 | 0% | 1,045 | 777 | -26% | 0 | 0 | — |
case-12 | fail→fail | 6,819 | 12,579 | +84% | 1 | 1 | 0% | 1,095 | 722 | -34% | 0 | 0 | — |
case-13 | pass→fail | 17,060 | 9,354 | -45% | 1 | 1 | 0% | 1,281 | 614 | -52% | 0 | 0 | — |
case-14 | fail→pass | 13,277 | 5,743 | -57% | 1 | 1 | 0% | 1,170 | 605 | -48% | 0 | 0 | — |
case-15 | fail→fail | 25,892 | 5,827 | -77% | 1 | 1 | 0% | 1,696 | 1,106 | -35% | 0 | 0 | — |
case-16 | pass→fail | 21,454 | 35,375 | +65% | 1 | 1 | 0% | 1,209 | 822 | -32% | 0 | 0 | — |
case-17 | fail→fail | 6,781 | 8,020 | +18% | 1 | 1 | 0% | 1,071 | 803 | -25% | 0 | 0 | — |
case-18 | pass→pass | 5,054 | 3,638 | -28% | 1 | 1 | 0% | 824 | 657 | -20% | 0 | 0 | — |
case-19 | pass→pass | 8,716 | 1,987 | -77% | 1 | 1 | 0% | 1,247 | 323 | -74% | 0 | 0 | — |
case-20 | pass→pass | 26,336 | 27,433 | +4% | 1 | 1 | 0% | 3,032 | 2,336 | -23% | 0 | 0 | — |
case-21 | pass→pass | 17,058 | 7,502 | -56% | 1 | 1 | 0% | 1,394 | 1,346 | -3% | 0 | 0 | — |
case-22 | pass→pass | 13,506 | 11,035 | -18% | 1 | 1 | 0% | 2,127 | 1,804 | -15% | 0 | 0 | — |
case-23 | pass→pass | 12,958 | 12,501 | -4% | 1 | 1 | 0% | 2,177 | 2,045 | -6% | 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, and 22 counted toward the lift figure. The other 1 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 +13 percentage points is the difference between those two pass rates over the 22 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.