Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Turn the pre-baby chaos into a staged logistics plan — leave paperwork, insurance deadlines, the hospital-bag/home-setup checklists, and the first-two-weeks operating plan with named owners. Use when asked help me prepare for a baby, what do I need to do before my due date, set up our parental leave plan, or newborn logistics checklist. Produces the countdown timeline by trimester-week, the deadline-driven paperwork list, and the week-1–2 operating plan both partners can run exhausted.
.claude/skills/mohitagw15856-new-parent-logistics/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 11% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 18% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 28% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 73% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 36% | 0% |
The baby-prep industry sells product lists; what new parents actually get wrong are deadlines and decision-making-while-exhausted. The insurance enrollment window (often just 30 days after birth), the leave paperwork that HR needs weeks in advance, the pediatrician who needs booking before the birth — these have real cutoffs, unlike the fifteenth swaddle. This skill builds the plan backwards from the due date and forward through the first two weeks, on the assumption that after the birth nobody is reading anything longer than a checklist.
Ask for these if not provided:
| Item | Real window | Owner | Status | |---|---|---|---|
T-12 weeks: … T-8: … T-4 (plan complete here): … T-2 (luxuries only): …
Night shifts: split] · Meals: plan] · Visitors: policy, verbatim] · Escalation: pediatrician #, nurse line, when-to-call rules posted on the fridge]
The judgment calls made while still sleeping]
> Leave entitlements and insurance windows vary by country, state, and employer — verify each deadline with HR and the insurer; this checklist is a scaffold, not a legal reference.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 26,313 | 22,386 | -15% | 1 | 1 | 0% | 4,455 | 4,954 | +11% | 0 | 0 | — |
case-02 | fail→pass | 20,788 | 18,061 | -13% | 1 | 1 | 0% | 3,661 | 4,316 | +18% | 0 | 0 | — |
case-03 | fail→pass | 18,087 | 16,091 | -11% | 1 | 1 | 0% | 3,053 | 3,923 | +28% | 0 | 0 | — |
case-04 | pass→pass | 17,438 | 14,219 | -18% | 1 | 1 | 0% | 2,917 | 3,624 | +24% | 0 | 0 | — |
case-05 | fail→pass | 16,994 | 21,403 | +26% | 1 | 1 | 0% | 2,537 | 4,398 | +73% | 0 | 0 | — |
case-06 | pass→pass | 23,300 | 27,841 | +19% | 1 | 1 | 0% | 3,420 | 5,081 | +49% | 0 | 0 | — |
case-07 | fail→pass | 15,644 | 14,733 | -6% | 1 | 1 | 0% | 2,572 | 3,494 | +36% | 0 | 0 | — |
case-08 | pass→pass | 18,730 | 18,196 | -3% | 1 | 1 | 0% | 2,873 | 3,872 | +35% | 0 | 0 | — |
case-09 | fail→fail | 15,148 | 17,830 | +18% | 1 | 1 | 0% | 2,514 | 3,569 | +42% | 0 | 0 | — |
case-10 | pass→pass | 15,187 | 21,445 | +41% | 1 | 1 | 0% | 2,429 | 4,132 | +70% | 0 | 0 | — |
case-11 | pass→pass | 14,307 | 15,499 | +8% | 1 | 1 | 0% | 2,416 | 3,479 | +44% | 0 | 0 | — |
case-12 | fail→fail | 19,286 | 16,306 | -15% | 1 | 1 | 0% | 3,081 | 3,718 | +21% | 0 | 0 | — |
case-13 | fail→pass | 15,048 | 18,208 | +21% | 1 | 1 | 0% | 2,449 | 4,020 | +64% | 0 | 0 | — |
case-14 | pass→pass | 22,933 | 18,365 | -20% | 1 | 1 | 0% | 3,493 | 3,954 | +13% | 0 | 0 | — |
case-15 | fail→pass | 16,576 | 17,146 | +3% | 1 | 1 | 0% | 2,525 | 3,600 | +43% | 0 | 0 | — |
case-16 | fail→fail | 12,390 | 17,417 | +41% | 1 | 1 | 0% | 2,159 | 3,867 | +79% | 0 | 0 | — |
case-17 | pass→pass | 15,358 | 22,080 | +44% | 1 | 1 | 0% | 2,463 | 4,129 | +68% | 0 | 0 | — |
case-18 | fail→pass | 19,452 | 17,295 | -11% | 1 | 1 | 0% | 3,105 | 3,730 | +20% | 0 | 0 | — |
case-19 | pass→pass | 17,199 | 16,224 | -6% | 1 | 1 | 0% | 2,655 | 3,410 | +28% | 0 | 0 | — |
case-20 | pass→fail | 15,635 | 27,691 | +77% | 1 | 1 | 0% | 2,528 | 5,590 | +121% | 0 | 0 | — |
case-21 | pass→fail | 15,571 | 18,106 | +16% | 1 | 1 | 0% | 2,596 | 3,962 | +53% | 0 | 0 | — |
case-22 | pass→pass | 13,125 | 14,808 | +13% | 1 | 1 | 0% | 2,105 | 3,207 | +52% | 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 +27 percentage points is the difference between those two pass rates over the 22 comparable cases. 2 cases got worse with the skill loaded, and they are 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.