Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Operate Spec Kitty team sync, hosted SaaS sync, offline queue, diagnostics, and recovery flows.
.claude/skills/priivacy-ai-spk-team-sync/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -35% | 0% |
| case-02 | ✗→✓ | ▲ Improved | -60% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -13% | 0% |
| case-04 | ✗→✓ | ▲ Improved | -20% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -36% | 0% |
Use this skill when a command touches spec-kitty tracker sync pull / sync push / sync run (local providers), tracker bind / status (hosted SaaS binding), or otherwise SaaS-backed mission data. There is no standalone sync daemon, offline queue, or sync diagnostics command — that transport was removed (issue #5); sync is a tracker capability now.
sync pull/sync push/sync run) or hosted SaaS binding/status.
spec-kitty tracker status before repair commands.spk-team-tracker.spk-team-auth.When testing tracker-backed sync flows from the CLI on this computer, opt into hosted mode with SPEC_KITTY_ENABLE_SAAS_SYNC=1. The flag is the tracker-hosted rollout gate; it does not restore the removed standalone sync daemon, offline queue, or diagnostics transport. Prefer writing it once into .kittify/.kitty.env (repo-scoped) or ${SPEC_KITTY_HOME}/.kitty.env (machine-wide) over a per-shell export — a shell export arms every project that shell subsequently touches, not just the one you're testing. Run spec-kitty doctor env-file to confirm which tier is active.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 19,277 | 11,648 | -40% | 1 | 1 | 0% | 2,433 | 1,581 | -35% | 0 | 0 | — |
case-02 | fail→pass | 14,969 | 7,549 | -50% | 1 | 1 | 0% | 1,830 | 732 | -60% | 0 | 0 | — |
case-03 | fail→pass | 18,461 | 12,498 | -32% | 1 | 1 | 0% | 2,108 | 1,843 | -13% | 0 | 0 | — |
case-04 | fail→pass | 13,247 | 7,295 | -45% | 1 | 1 | 0% | 936 | 752 | -20% | 0 | 0 | — |
case-05 | fail→pass | 12,842 | 7,912 | -38% | 1 | 1 | 0% | 1,294 | 832 | -36% | 0 | 0 | — |
case-06 | fail→pass | 18,233 | 7,449 | -59% | 1 | 1 | 0% | 2,377 | 757 | -68% | 0 | 0 | — |
case-07 | fail→pass | 15,735 | 8,595 | -45% | 1 | 1 | 0% | 1,962 | 901 | -54% | 0 | 0 | — |
case-08 | fail→pass | 18,147 | 9,959 | -45% | 1 | 1 | 0% | 2,234 | 1,347 | -40% | 0 | 0 | — |
case-09 | fail→pass | 14,123 | 9,128 | -35% | 1 | 1 | 0% | 1,546 | 1,140 | -26% | 0 | 0 | — |
case-10 | fail→pass | 16,270 | 9,138 | -44% | 1 | 1 | 0% | 2,022 | 1,171 | -42% | 0 | 0 | — |
case-11 | fail→pass | 34,308 | 9,477 | -72% | 1 | 1 | 0% | 1,957 | 1,177 | -40% | 0 | 0 | — |
case-12 | pass→pass | 14,669 | 8,313 | -43% | 1 | 1 | 0% | 1,647 | 1,037 | -37% | 0 | 0 | — |
case-13 | fail→pass | 14,375 | 6,586 | -54% | 1 | 1 | 0% | 1,785 | 578 | -68% | 0 | 0 | — |
case-14 | fail→pass | 15,000 | 6,659 | -56% | 1 | 1 | 0% | 1,580 | 542 | -66% | 0 | 0 | — |
case-15 | fail→pass | 14,341 | 6,651 | -54% | 1 | 1 | 0% | 1,438 | 565 | -61% | 0 | 0 | — |
case-16 | pass→pass | 13,330 | 7,479 | -44% | 1 | 1 | 0% | 1,581 | 770 | -51% | 0 | 0 | — |
case-17 | fail→pass | 52,319 | 6,916 | -87% | 1 | 1 | 0% | 4,177 | 681 | -84% | 0 | 0 | — |
case-18 | pass→pass | 15,236 | 8,341 | -45% | 1 | 1 | 0% | 1,737 | 906 | -48% | 0 | 0 | — |
case-19 | fail→pass | 14,850 | 7,055 | -52% | 1 | 1 | 0% | 1,425 | 644 | -55% | 0 | 0 | — |
case-20 | fail→pass | 17,581 | 9,507 | -46% | 1 | 1 | 0% | 1,751 | 1,118 | -36% | 0 | 0 | — |
case-21 | pass→pass | 11,489 | 9,232 | -20% | 1 | 1 | 0% | 1,076 | 1,065 | -1% | 0 | 0 | — |
case-22 | fail→pass | 14,268 | 9,633 | -32% | 1 | 1 | 0% | 1,516 | 1,123 | -26% | 0 | 0 | — |
case-23 | pass→pass | 8,839 | 7,380 | -17% | 1 | 1 | 0% | 631 | 729 | +16% | 0 | 0 | — |
case-24 | pass→pass | 11,757 | 9,103 | -23% | 1 | 1 | 0% | 1,130 | 1,012 | -10% | 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. 24 cases were attempted, and 23 counted toward the lift figure. The other 1 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 +75 percentage points is the difference between those two pass rates over the 23 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 | 8/27/2026 | +41% |
| gemini-3.6-flash | verified | 8/13/2026 | +52% |
Other measured skills in the registry, with their headline benchmark lift.