Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Guide a first Spec Kitty feature from setup through specify, plan, tasks, implementation, review, accept, merge, and retrospective.
.claude/skills/priivacy-ai-spk-start-first-feature/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | -37% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -33% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -30% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -61% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -30% | 0% |
Use this skill when a user wants to start their first Spec Kitty mission or feature and needs the end-to-end path.
spk-admin-setup-doctor if commands orskills are missing.
/spec-kitty.specify./spec-kitty.plan./spec-kitty.tasks or the outline/packages/finalizesplit when the project uses staged task authoring.
spk-run-next.spk-run-implement-review.spk-gate-accept, then spk-gate-merge.spk-gate-mission-review andspk-gate-retrospective.
complete.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-03 | fail→pass | 13,080 | 5,932 | -55% | 1 | 1 | 0% | 2,399 | 1,505 | -37% | 0 | 0 | — |
case-04 | pass→pass | 14,265 | 12,430 | -13% | 1 | 1 | 0% | 2,749 | 2,792 | +2% | 0 | 0 | — |
case-05 | pass→pass | 9,501 | 6,081 | -36% | 1 | 1 | 0% | 1,890 | 1,423 | -25% | 0 | 0 | — |
case-06 | pass→pass | 14,642 | 20,922 | +43% | 1 | 1 | 0% | 2,751 | 2,581 | -6% | 0 | 0 | — |
case-01 | fail→pass | 11,996 | 6,185 | -48% | 1 | 1 | 0% | 2,383 | 1,589 | -33% | 0 | 0 | — |
case-02 | fail→pass | 13,342 | 6,951 | -48% | 1 | 1 | 0% | 2,402 | 1,685 | -30% | 0 | 0 | — |
case-07 | fail→pass | 8,622 | 1,981 | -77% | 1 | 1 | 0% | 1,513 | 597 | -61% | 0 | 0 | — |
case-08 | fail→pass | 6,027 | 2,722 | -55% | 1 | 1 | 0% | 1,003 | 704 | -30% | 0 | 0 | — |
case-09 | fail→pass | 15,282 | 2,280 | -85% | 1 | 1 | 0% | 1,191 | 655 | -45% | 0 | 0 | — |
case-10 | fail→pass | 8,998 | 2,469 | -73% | 1 | 1 | 0% | 1,539 | 656 | -57% | 0 | 0 | — |
case-11 | fail→pass | 5,943 | 3,151 | -47% | 1 | 1 | 0% | 1,106 | 800 | -28% | 0 | 0 | — |
case-12 | fail→pass | 5,812 | 2,131 | -63% | 1 | 1 | 0% | 954 | 619 | -35% | 0 | 0 | — |
case-13 | fail→pass | 8,873 | 2,579 | -71% | 1 | 1 | 0% | 1,458 | 710 | -51% | 0 | 0 | — |
case-14 | fail→pass | 6,429 | 2,004 | -69% | 1 | 1 | 0% | 1,132 | 622 | -45% | 0 | 0 | — |
case-15 | fail→pass | 7,597 | 2,382 | -69% | 1 | 1 | 0% | 1,298 | 638 | -51% | 0 | 0 | — |
case-16 | fail→pass | 10,254 | 1,363 | -87% | 1 | 1 | 0% | 1,663 | 483 | -71% | 0 | 0 | — |
case-17 | fail→pass | 5,869 | 3,005 | -49% | 1 | 1 | 0% | 1,040 | 919 | -12% | 0 | 0 | — |
case-18 | pass→pass | 9,208 | 4,632 | -50% | 1 | 1 | 0% | 1,558 | 1,058 | -32% | 0 | 0 | — |
case-19 | pass→pass | 8,473 | 2,739 | -68% | 1 | 1 | 0% | 1,383 | 681 | -51% | 0 | 0 | — |
case-20 | pass→pass | 11,254 | 2,694 | -76% | 1 | 1 | 0% | 1,844 | 740 | -60% | 0 | 0 | — |
case-21 | fail→pass | 13,593 | 7,140 | -47% | 1 | 1 | 0% | 2,313 | 1,592 | -31% | 0 | 0 | — |
case-22 | fail→pass | 7,995 | 1,533 | -81% | 1 | 1 | 0% | 1,286 | 522 | -59% | 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 +73 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.