Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Friendly onboarding tour of Claude Code capabilities for users asking what it can do.
| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 2% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -34% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -5% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -44% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -35% | 0% |
Friendly onboarding when users ask about capabilities.
Activate when user says things like:
Give a warm, practical overview:
I'm Claude Code with persistent memory and specialized capabilities. Here's what makes me useful:
I can spawn sub-agents for complex tasks:
explorer - map codebase structurekraken - implement with TDD workflowdebug - investigate issues systematicallyWhat would you like to work on?
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 7,112 | 3,726 | -48% | 1 | 1 | 0% | 1,186 | 1,214 | +2% | 0 | 0 | — |
case-02 | fail→pass | 9,519 | 4,272 | -55% | 1 | 1 | 0% | 1,690 | 1,110 | -34% | 0 | 0 | — |
case-03 | fail→pass | 6,254 | 2,849 | -54% | 1 | 1 | 0% | 1,090 | 1,031 | -5% | 0 | 0 | — |
case-04 | pass→pass | 10,217 | 4,923 | -52% | 1 | 1 | 0% | 1,772 | 1,224 | -31% | 0 | 0 | — |
case-05 | fail→pass | 14,559 | 4,908 | -66% | 1 | 1 | 0% | 2,082 | 1,160 | -44% | 0 | 0 | — |
case-06 | fail→pass | 11,570 | 5,811 | -50% | 1 | 1 | 0% | 2,074 | 1,350 | -35% | 0 | 0 | — |
case-07 | fail→pass | 10,032 | 6,275 | -37% | 1 | 1 | 0% | 1,740 | 1,358 | -22% | 0 | 0 | — |
case-17 | fail→pass | 8,838 | 4,881 | -45% | 1 | 1 | 0% | 1,457 | 1,171 | -20% | 0 | 0 | — |
case-08 | pass→pass | 8,009 | 2,587 | -68% | 1 | 1 | 0% | 1,372 | 791 | -42% | 0 | 0 | — |
case-09 | pass→pass | 10,322 | 5,345 | -48% | 1 | 1 | 0% | 1,741 | 1,216 | -30% | 0 | 0 | — |
case-10 | fail→pass | 8,840 | 3,128 | -65% | 1 | 1 | 0% | 1,581 | 945 | -40% | 0 | 0 | — |
case-11 | pass→pass | 9,417 | 3,093 | -67% | 1 | 1 | 0% | 1,525 | 865 | -43% | 0 | 0 | — |
case-12 | fail→pass | 6,346 | 2,994 | -53% | 1 | 1 | 0% | 922 | 747 | -19% | 0 | 0 | — |
case-13 | pass→pass | 13,860 | 4,589 | -67% | 1 | 1 | 0% | 2,388 | 1,090 | -54% | 0 | 0 | — |
case-14 | fail→pass | 9,244 | 6,477 | -30% | 1 | 1 | 0% | 1,525 | 1,656 | +9% | 0 | 0 | — |
case-15 | fail→pass | 10,451 | 5,868 | -44% | 1 | 1 | 0% | 1,740 | 1,301 | -25% | 0 | 0 | — |
case-16 | fail→pass | 8,098 | 5,198 | -36% | 1 | 1 | 0% | 1,287 | 1,258 | -2% | 0 | 0 | — |
case-18 | pass→pass | 7,556 | 4,933 | -35% | 1 | 1 | 0% | 1,211 | 1,193 | -1% | 0 | 0 | — |
case-19 | pass→pass | 13,468 | 6,880 | -49% | 1 | 1 | 0% | 2,183 | 1,432 | -34% | 0 | 0 | — |
case-20 | pass→pass | 3,040 | 2,438 | -20% | 1 | 1 | 0% | 509 | 773 | +52% | 0 | 0 | — |
case-21 | pass→pass | 13,613 | 11,356 | -17% | 1 | 1 | 0% | 2,302 | 2,269 | -1% | 0 | 0 | — |
case-22 | pass→pass | 3,492 | 3,097 | -11% | 1 | 1 | 0% | 614 | 946 | +54% | 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 +55 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.
| Model | Method | Date | Lift |
|---|---|---|---|
| gemini-3.6-flash | verified | 7/29/2026 | +77% |
Other measured skills in the registry, with their headline benchmark lift.