Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Explain Spec Kitty mission types, step contracts, action indices, and when to choose each mission workflow.
.claude/skills/priivacy-ai-spk-mission-types/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-02 | ✗→✓ | ▲ Improved | -64% | 0% |
| case-01 | ✗→✓ | ▲ Improved | -26% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -73% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -71% | 0% |
| case-06 | ✗→✓ | ▲ Improved | -75% | 0% |
Use this skill when the user asks which kind of mission to run or how mission types differ.
documentation, research, or custom/team workflow.
spec-kitty-mission-system skill for detailed step-contract,procedure, action-index, and template-resolution mechanics.
Mission types define workflow behavior. Skills explain how to operate that behavior; they do not redefine the mission DAG.
software-dev: default feature/change workflow with tasks and WP iteration.research: evidence-gathering workflow before or during product decisions.plan: planning-only workflow.documentation: documentation-oriented workflow.| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-02 | fail→pass | 12,613 | 3,293 | -74% | 1 | 1 | 0% | 2,242 | 804 | -64% | 0 | 0 | — |
case-01 | fail→pass | 7,687 | 4,713 | -39% | 1 | 1 | 0% | 1,442 | 1,071 | -26% | 0 | 0 | — |
case-03 | pass→pass | 9,657 | 3,206 | -67% | 1 | 1 | 0% | 1,699 | 757 | -55% | 0 | 0 | — |
case-04 | fail→pass | 14,926 | 3,010 | -80% | 1 | 1 | 0% | 2,534 | 688 | -73% | 0 | 0 | — |
case-05 | fail→pass | 12,449 | 2,596 | -79% | 1 | 1 | 0% | 2,244 | 655 | -71% | 0 | 0 | — |
case-06 | fail→pass | 17,270 | 3,899 | -77% | 1 | 1 | 0% | 3,583 | 902 | -75% | 0 | 0 | — |
case-07 | pass→pass | 10,812 | 2,296 | -79% | 1 | 1 | 0% | 1,992 | 603 | -70% | 0 | 0 | — |
case-08 | fail→pass | 8,561 | 2,650 | -69% | 1 | 1 | 0% | 1,384 | 600 | -57% | 0 | 0 | — |
case-09 | pass→pass | 8,970 | 3,643 | -59% | 1 | 1 | 0% | 1,554 | 753 | -52% | 0 | 0 | — |
case-10 | fail→pass | 9,925 | 2,378 | -76% | 1 | 1 | 0% | 1,660 | 639 | -62% | 0 | 0 | — |
case-11 | pass→pass | 13,034 | 3,143 | -76% | 1 | 1 | 0% | 2,255 | 714 | -68% | 0 | 0 | — |
case-12 | pass→pass | 12,616 | 1,828 | -86% | 1 | 1 | 0% | 2,036 | 512 | -75% | 0 | 0 | — |
case-13 | pass→pass | 14,027 | 5,030 | -64% | 1 | 1 | 0% | 2,184 | 568 | -74% | 0 | 0 | — |
case-14 | pass→pass | 15,780 | 1,511 | -90% | 1 | 1 | 0% | 2,659 | 463 | -83% | 0 | 0 | — |
case-15 | pass→pass | 8,451 | 2,484 | -71% | 1 | 1 | 0% | 1,470 | 637 | -57% | 0 | 0 | — |
case-16 | fail→pass | 7,656 | 2,351 | -69% | 1 | 1 | 0% | 1,341 | 561 | -58% | 0 | 0 | — |
case-17 | fail→pass | 10,480 | 2,043 | -81% | 1 | 1 | 0% | 1,670 | 536 | -68% | 0 | 0 | — |
case-18 | fail→pass | 4,695 | 2,490 | -47% | 1 | 1 | 0% | 761 | 631 | -17% | 0 | 0 | — |
case-19 | fail→pass | 10,924 | 1,764 | -84% | 1 | 1 | 0% | 1,849 | 433 | -77% | 0 | 0 | — |
case-20 | fail→pass | 13,701 | 2,084 | -85% | 1 | 1 | 0% | 2,397 | 521 | -78% | 0 | 0 | — |
case-21 | pass→pass | 8,993 | 3,443 | -62% | 1 | 1 | 0% | 1,717 | 808 | -53% | 0 | 0 | — |
case-22 | fail→pass | 5,528 | 2,131 | -61% | 1 | 1 | 0% | 888 | 562 | -37% | 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 +59 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.