Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Smoke-test skill for the starter kit. Confirms the plugin installed and skills load. Use when the user runs /kit-hello or asks to verify the starter kit installation.
.claude/skills/chrisblattman-kit-hello/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 14% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -58% | 0% |
You are confirming the claudeblattman starter kit is installed and working.
/prompt from the Starter Kit page. Say /kit-setup is optional later for Codex/Gemini second opinions.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 6,850 | 3,004 | -56% | 1 | 1 | 0% | 954 | 660 | -31% | 0 | 0 | — |
case-02 | fail→pass | 4,880 | 2,972 | -39% | 1 | 1 | 0% | 684 | 606 | -11% | 0 | 0 | — |
case-03 | fail→pass | 7,506 | 2,793 | -63% | 1 | 1 | 0% | 1,183 | 603 | -49% | 0 | 0 | — |
case-04 | fail→pass | 5,589 | 4,334 | -22% | 1 | 1 | 0% | 811 | 927 | +14% | 0 | 0 | — |
case-05 | fail→pass | 10,710 | 3,674 | -66% | 1 | 1 | 0% | 1,740 | 733 | -58% | 0 | 0 | — |
case-06 | pass→pass | 5,224 | 3,508 | -33% | 1 | 1 | 0% | 778 | 697 | -10% | 0 | 0 | — |
case-07 | fail→pass | 7,955 | 2,957 | -63% | 1 | 1 | 0% | 1,225 | 680 | -44% | 0 | 0 | — |
case-08 | fail→pass | 7,354 | 2,970 | -60% | 1 | 1 | 0% | 1,065 | 670 | -37% | 0 | 0 | — |
case-09 | fail→pass | 8,504 | 3,091 | -64% | 1 | 1 | 0% | 1,251 | 655 | -48% | 0 | 0 | — |
case-10 | fail→pass | 7,209 | 3,834 | -47% | 1 | 1 | 0% | 1,076 | 774 | -28% | 0 | 0 | — |
case-11 | pass→pass | 6,439 | 3,917 | -39% | 1 | 1 | 0% | 888 | 780 | -12% | 0 | 0 | — |
case-12 | fail→pass | 5,258 | 3,508 | -33% | 1 | 1 | 0% | 754 | 733 | -3% | 0 | 0 | — |
case-13 | fail→pass | 3,222 | 4,056 | +26% | 1 | 1 | 0% | 418 | 780 | +87% | 0 | 0 | — |
case-14 | fail→pass | 8,799 | 3,624 | -59% | 1 | 1 | 0% | 1,310 | 685 | -48% | 0 | 0 | — |
case-15 | fail→pass | 3,978 | 6,619 | +66% | 1 | 1 | 0% | 559 | 1,258 | +125% | 0 | 0 | — |
case-16 | fail→pass | 8,063 | 3,149 | -61% | 1 | 1 | 0% | 1,192 | 701 | -41% | 0 | 0 | — |
case-17 | fail→pass | 8,046 | 5,149 | -36% | 1 | 1 | 0% | 1,264 | 953 | -25% | 0 | 0 | — |
case-18 | fail→pass | 3,575 | 3,782 | +6% | 1 | 1 | 0% | 417 | 770 | +85% | 0 | 0 | — |
case-19 | fail→pass | 9,143 | 3,970 | -57% | 1 | 1 | 0% | 1,369 | 801 | -41% | 0 | 0 | — |
case-20 | pass→fail | 7,259 | 3,511 | -52% | 1 | 1 | 0% | 1,334 | 726 | -46% | 0 | 0 | — |
case-21 | pass→fail | 5,792 | 2,762 | -52% | 1 | 1 | 0% | 1,024 | 428 | -58% | 0 | 0 | — |
case-22 | pass→fail | 10,768 | 4,046 | -62% | 1 | 1 | 0% | 1,777 | 840 | -53% | 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 +64 percentage points is the difference between those two pass rates over the 22 comparable cases. 3 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.