Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use this skill when asked to "create a plugin", "build a new plugin", "make a Claude Code plugin", "scaffold plugin", "plugin structure", "add commands/agents/skills/hooks to plugin", or when helping with plugin development.
.claude/skills/dicklesworthstone-plugin-creator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -49% | 0% |
| case-03 | ✓→✓ | = Same ✓ | -30% | 0% |
| case-04 | ✓→✓ | = Same ✓ | -22% | 0% |
| case-05 | ✓→✓ | = Same ✓ | -43% | 0% |
| case-06 | ✓→✓ | = Same ✓ | 9% | 0% |
This skill provides automated assistance for the described functionality.
Step-by-step for Claude]
## Output
## Error Handling
See `{baseDir}/references/errors.md` for comprehensive error handling.
## Examples
See `{baseDir}/references/examples.md` for detailed examples.
## Resources
- Project documentation
- Related skills and commands| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 13,235 | 12,744 | -4% | 1 | 1 | 0% | 1,811 | 929 | -49% | 0 | 0 | — |
case-02 | fail→fail | 6,793 | 5,297 | -22% | 1 | 1 | 0% | 1,088 | 974 | -10% | 0 | 0 | — |
case-03 | pass→pass | 7,991 | 6,446 | -19% | 1 | 1 | 0% | 1,362 | 955 | -30% | 0 | 0 | — |
case-04 | pass→pass | 10,933 | 7,017 | -36% | 1 | 1 | 0% | 1,889 | 1,482 | -22% | 0 | 0 | — |
case-05 | pass→pass | 10,488 | 4,526 | -57% | 1 | 1 | 0% | 1,496 | 859 | -43% | 0 | 0 | — |
case-06 | pass→pass | 9,941 | 9,824 | -1% | 1 | 1 | 0% | 1,695 | 1,849 | +9% | 0 | 0 | — |
case-07 | fail→fail | 17,109 | 7,588 | -56% | 1 | 1 | 0% | 2,508 | 1,513 | -40% | 0 | 0 | — |
case-08 | fail→fail | 15,029 | 9,122 | -39% | 1 | 1 | 0% | 2,767 | 1,583 | -43% | 0 | 0 | — |
case-09 | pass→pass | 9,455 | 8,493 | -10% | 1 | 1 | 0% | 1,419 | 1,390 | -2% | 0 | 0 | — |
case-10 | pass→pass | 7,634 | 4,722 | -38% | 1 | 1 | 0% | 890 | 778 | -13% | 0 | 0 | — |
case-11 | pass→pass | 6,995 | 6,602 | -6% | 1 | 1 | 0% | 1,084 | 1,152 | +6% | 0 | 0 | — |
case-12 | pass→pass | 5,705 | 4,142 | -27% | 1 | 1 | 0% | 1,044 | 818 | -22% | 0 | 0 | — |
case-13 | pass→pass | 6,188 | 6,393 | +3% | 1 | 1 | 0% | 1,082 | 1,102 | +2% | 0 | 0 | — |
case-14 | pass→pass | 10,891 | 6,481 | -40% | 1 | 1 | 0% | 1,663 | 1,361 | -18% | 0 | 0 | — |
case-15 | pass→pass | 7,627 | 3,448 | -55% | 1 | 1 | 0% | 1,035 | 667 | -36% | 0 | 0 | — |
case-16 | fail→fail | 9,799 | 17,003 | +74% | 1 | 1 | 0% | 1,720 | 2,701 | +57% | 0 | 0 | — |
case-17 | pass→pass | 5,463 | 8,039 | +47% | 1 | 1 | 0% | 721 | 882 | +22% | 0 | 0 | — |
case-18 | pass→pass | 4,713 | 15,899 | +237% | 1 | 1 | 0% | 730 | 3,409 | +367% | 0 | 0 | — |
case-19 | fail→fail | 13,715 | 21,108 | +54% | 1 | 1 | 0% | 2,789 | 4,309 | +54% | 0 | 0 | — |
case-20 | pass→pass | 3,669 | 4,098 | +12% | 1 | 1 | 0% | 552 | 606 | +10% | 0 | 0 | — |
case-21 | pass→pass | 9,325 | 6,740 | -28% | 1 | 1 | 0% | 1,455 | 1,177 | -19% | 0 | 0 | — |
case-22 | pass→pass | 8,481 | 6,243 | -26% | 1 | 1 | 0% | 1,402 | 1,001 | -29% | 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 +5 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.
Other measured skills in the registry, with their headline benchmark lift.