Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Turn 'we're having a baby' into a calm, timed logistics plan — the admin, leave, registrations, and prep that has to happen, sequenced so nothing critical is left to the newborn haze. Use when asked to plan for a new baby, what do I need to do before the baby comes, new baby checklist, or help me prepare for a newborn. Produces a trimester/countdown checklist of the non-obvious admin (leave, benefits, insurance, registration, pediatrician, essentials), what to set up before vs after birth, and a
.claude/skills/mohitagw15856-new-baby-logistics/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-03 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -21% | 0% |
| case-15 | ✗→✓ | ▲ Improved | 44% | 0% |
| case-16 | ✗→✓ | ▲ Improved | 34% | 0% |
| case-20 | ✗→✓ | ▲ Improved | 17% | 0% |
The parenting advice online is endless; the logistics — what admin to do and when — is what actually trips people up, and the newborn fog is the worst time to figure it out. This turns the arrival into a timed plan: the leave and benefits paperwork, the insurance and registration steps, the pediatrician and essentials — sequenced so the important boring stuff is handled before the baby (and sleep deprivation) arrives.
Ask for these if not provided:
Countdown
Don't-forget admin: leave · benefits/allowances · insurance · registration · deadlines]. Lean essentials (first): short real list]. Later: second wave]. Support: meals · help · recovery plan].
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | pass→pass | 29,084 | 30,916 | +6% | 1 | 1 | 0% | 3,797 | 4,942 | +30% | 0 | 0 | — |
case-02 | pass→pass | 27,741 | 28,978 | +4% | 1 | 1 | 0% | 3,601 | 4,700 | +31% | 0 | 0 | — |
case-03 | fail→pass | 32,036 | 29,119 | -9% | 1 | 1 | 0% | 4,158 | 4,874 | +17% | 0 | 0 | — |
case-04 | pass→pass | 15,621 | 10,871 | -30% | 1 | 1 | 0% | 1,699 | 1,861 | +10% | 0 | 0 | — |
case-05 | pass→pass | 23,621 | 26,947 | +14% | 1 | 1 | 0% | 2,855 | 4,284 | +50% | 0 | 0 | — |
case-06 | pass→pass | 20,708 | 31,592 | +53% | 1 | 1 | 0% | 2,399 | 5,281 | +120% | 0 | 0 | — |
case-07 | fail→pass | 20,326 | 6,172 | -70% | 1 | 1 | 0% | 2,440 | 1,916 | -21% | 0 | 0 | — |
case-08 | pass→pass | 14,906 | 22,102 | +48% | 1 | 1 | 0% | 2,293 | 3,482 | +52% | 0 | 0 | — |
case-09 | pass→pass | 20,448 | 22,653 | +11% | 1 | 1 | 0% | 2,413 | 3,471 | +44% | 0 | 0 | — |
case-10 | fail→fail | 25,530 | 20,279 | -21% | 1 | 1 | 0% | 3,101 | 3,987 | +29% | 0 | 0 | — |
case-11 | pass→pass | 22,153 | 22,218 | +0% | 1 | 1 | 0% | 2,637 | 3,589 | +36% | 0 | 0 | — |
case-12 | pass→pass | 19,726 | 18,486 | -6% | 1 | 1 | 0% | 3,416 | 4,037 | +18% | 0 | 0 | — |
case-13 | pass→pass | 17,972 | 22,249 | +24% | 1 | 1 | 0% | 1,975 | 3,636 | +84% | 0 | 0 | — |
case-14 | pass→pass | 20,886 | 23,546 | +13% | 1 | 1 | 0% | 3,251 | 3,828 | +18% | 0 | 0 | — |
case-15 | fail→pass | 25,020 | 27,328 | +9% | 1 | 1 | 0% | 2,930 | 4,221 | +44% | 0 | 0 | — |
case-16 | fail→pass | 24,287 | 22,125 | -9% | 1 | 1 | 0% | 2,858 | 3,835 | +34% | 0 | 0 | — |
case-17 | pass→pass | 21,163 | 24,647 | +16% | 1 | 1 | 0% | 3,094 | 4,081 | +32% | 0 | 0 | — |
case-18 | pass→pass | 26,462 | 22,705 | -14% | 1 | 1 | 0% | 2,897 | 3,778 | +30% | 0 | 0 | — |
case-19 | pass→pass | 30,283 | 32,933 | +9% | 1 | 1 | 0% | 3,878 | 5,106 | +32% | 0 | 0 | — |
case-20 | fail→pass | 30,578 | 30,589 | +0% | 1 | 1 | 0% | 3,943 | 4,612 | +17% | 0 | 0 | — |
case-21 | pass→pass | 16,119 | 23,558 | +46% | 1 | 1 | 0% | 2,568 | 3,909 | +52% | 0 | 0 | — |
case-22 | pass→pass | 25,039 | 29,027 | +16% | 1 | 1 | 0% | 3,211 | 4,513 | +41% | 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 +23 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.