Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Use this skill when Storybook is already installed and the user wants a working `preview` file and stories for real components.
.claude/skills/storybookjs-setup/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-06 | ✗→✓ | ▲ Improved | -61% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -63% | 0% |
| case-11 | ✗→✓ | ▲ Improved | -45% | 0% |
| case-12 | ✗→✓ | ▲ Improved | -74% | 0% |
| case-13 | ✗→✓ | ▲ Improved | -63% | 0% |
Prerequisites:
package.json, .storybook/). If not, switch to $storybook:init.next satisfies this — 10.6.0-alpha.x. Any canary build, 0.0.0-pr-*, also qualifies.) If it is older, or upgrade/repair is needed first, switch to $storybook:upgrade, but only if the user explicitly approved a Storybook upgrade.Run npx storybook skills setup from the project root (or the Storybook package in a monorepo).
Follow the printed Markdown precisely. Do not substitute your own plan.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 6,627 | 7,308 | +10% | 1 | 1 | 0% | 254 | 407 | +60% | 0 | 0 | — |
case-02 | fail→fail | 5,607 | 7,875 | +40% | 1 | 1 | 0% | 160 | 440 | +175% | 0 | 0 | — |
case-03 | pass→pass | 14,966 | 3,233 | -78% | 1 | 1 | 0% | 2,735 | 564 | -79% | 0 | 0 | — |
case-04 | fail→fail | 14,376 | 2,359 | -84% | 1 | 1 | 0% | 2,233 | 422 | -81% | 0 | 0 | — |
case-05 | fail→fail | 8,698 | 8,309 | -4% | 1 | 1 | 0% | 1,519 | 514 | -66% | 0 | 0 | — |
case-06 | fail→pass | 16,671 | 5,467 | -67% | 1 | 1 | 0% | 2,738 | 1,074 | -61% | 0 | 0 | — |
case-07 | fail→pass | 15,219 | 4,949 | -67% | 1 | 1 | 0% | 2,408 | 895 | -63% | 0 | 0 | — |
case-08 | pass→pass | 10,121 | 4,499 | -56% | 1 | 1 | 0% | 1,573 | 705 | -55% | 0 | 0 | — |
case-09 | pass→pass | 11,263 | 4,448 | -61% | 1 | 1 | 0% | 1,749 | 463 | -74% | 0 | 0 | — |
case-10 | fail→fail | 30,458 | 4,309 | -86% | 1 | 1 | 0% | 1,957 | 719 | -63% | 0 | 0 | — |
case-11 | fail→pass | 7,565 | 3,281 | -57% | 1 | 1 | 0% | 1,043 | 569 | -45% | 0 | 0 | — |
case-12 | fail→pass | 9,967 | 2,426 | -76% | 1 | 1 | 0% | 1,616 | 424 | -74% | 0 | 0 | — |
case-13 | fail→pass | 10,325 | 3,295 | -68% | 1 | 1 | 0% | 1,573 | 579 | -63% | 0 | 0 | — |
case-14 | fail→fail | 12,660 | 2,115 | -83% | 1 | 1 | 0% | 2,150 | 358 | -83% | 0 | 0 | — |
case-15 | pass→pass | 7,346 | 4,494 | -39% | 1 | 1 | 0% | 960 | 855 | -11% | 0 | 0 | — |
case-16 | fail→pass | 11,728 | 4,590 | -61% | 1 | 1 | 0% | 1,627 | 799 | -51% | 0 | 0 | — |
case-17 | fail→pass | 23,152 | 2,393 | -90% | 1 | 1 | 0% | 3,814 | 417 | -89% | 0 | 0 | — |
case-18 | fail→pass | 12,774 | 4,758 | -63% | 1 | 1 | 0% | 1,978 | 777 | -61% | 0 | 0 | — |
case-19 | fail→pass | 10,587 | 2,891 | -73% | 1 | 1 | 0% | 1,409 | 437 | -69% | 0 | 0 | — |
case-20 | pass→fail | 16,868 | 3,659 | -78% | 1 | 1 | 0% | 2,342 | 491 | -79% | 0 | 0 | — |
case-21 | pass→pass | 10,229 | 8,440 | -17% | 1 | 1 | 0% | 1,484 | 1,963 | +32% | 0 | 0 | — |
case-22 | pass→pass | 18,337 | 5,094 | -72% | 1 | 1 | 0% | 1,267 | 957 | -24% | 0 | 0 | — |
case-23 | fail→pass | 10,186 | 3,265 | -68% | 1 | 1 | 0% | 1,563 | 600 | -62% | 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 21 counted toward the lift figure. The other 2 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 +39 percentage points is the difference between those two pass rates over the 21 comparable cases. 1 case got worse with the skill loaded, and it is 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.