Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Plan your first 90 days as a new manager — build trust, learn before changing, and avoid the classic first-time-manager mistakes. Use when asked to help me as a new manager, I just became a manager, first-time manager advice, or my first 90 days managing a team. Produces a phased 90-day plan (listen and learn, then set direction, then adjust), how to run your first 1:1s, the mindset shift from doer to enabler, common traps to avoid (doing it all yourself, changing too fast, avoiding hard convers
.claude/skills/mohitagw15856-new-manager-first-90-days/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 9% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 43% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-23 | ✓→✓ | = Same ✓ | 31% | 0% |
| case-04 | ✓→✓ | = Same ✓ | 64% | 0% |
The jump to managing is a role change, not a promotion for doing more of the same — and most first-time managers stumble by either changing everything on day one or staying an individual contributor with a title. This gives a phased first-90-days plan: earn trust and learn first, then set direction, then adjust — plus how to handle the 1:1s, delegation, and hard conversations that define the job.
Ask for these if not provided:
Situation read: inherited/new/former-peers/turnaround → what it means]. Phase 1 (learn, ~weeks 1–4): listen · first 1:1s · understand work/context · no big changes yet. First 1:1s — ask: goals · working style · what they need from you · what's working/not]. Phase 2 (direction, ~weeks 5–8): clarify priorities/expectations · how the team works. Phase 3 (adjust & build, ~weeks 9–12): refine · develop people · early wins. Mindset shift: doer → enabler (your output = the team's). Avoid: doing it all yourself · changing too fast · dodging hard conversations · favoritism. Early wins: remove a blocker · a small improvement].
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-23 | pass→pass | 13,937 | 4,797 | -66% | 1 | 1 | 0% | 1,471 | 1,920 | +31% | 0 | 0 | — |
case-01 | fail→pass | 28,972 | 21,271 | -27% | 1 | 1 | 0% | 3,481 | 3,783 | +9% | 0 | 0 | — |
case-02 | fail→fail | 29,590 | 24,416 | -17% | 1 | 1 | 0% | 3,982 | 4,318 | +8% | 0 | 0 | — |
case-03 | fail→fail | 32,461 | 15,588 | -52% | 1 | 1 | 0% | 3,881 | 3,539 | -9% | 0 | 0 | — |
case-04 | pass→pass | 22,988 | 23,487 | +2% | 1 | 1 | 0% | 3,023 | 4,963 | +64% | 0 | 0 | — |
case-05 | pass→pass | 16,932 | 28,170 | +66% | 1 | 1 | 0% | 2,943 | 6,286 | +114% | 0 | 0 | — |
case-06 | pass→pass | 22,713 | 19,643 | -14% | 1 | 1 | 0% | 2,951 | 4,406 | +49% | 0 | 0 | — |
case-07 | pass→pass | 16,044 | 21,632 | +35% | 1 | 1 | 0% | 2,661 | 4,498 | +69% | 0 | 0 | — |
case-08 | pass→pass | 23,038 | 21,902 | -5% | 1 | 1 | 0% | 2,933 | 3,828 | +31% | 0 | 0 | — |
case-09 | pass→pass | 21,692 | 16,189 | -25% | 1 | 1 | 0% | 2,664 | 3,682 | +38% | 0 | 0 | — |
case-10 | pass→pass | 21,779 | 22,529 | +3% | 1 | 1 | 0% | 2,919 | 3,891 | +33% | 0 | 0 | — |
case-11 | pass→pass | 22,981 | 16,536 | -28% | 1 | 1 | 0% | 2,951 | 3,976 | +35% | 0 | 0 | — |
case-12 | pass→pass | 26,804 | 21,240 | -21% | 1 | 1 | 0% | 3,012 | 3,889 | +29% | 0 | 0 | — |
case-13 | fail→pass | 20,468 | 14,358 | -30% | 1 | 1 | 0% | 2,360 | 3,371 | +43% | 0 | 0 | — |
case-14 | pass→pass | 14,852 | 3,576 | -76% | 1 | 1 | 0% | 1,314 | 1,657 | +26% | 0 | 0 | — |
case-15 | pass→pass | 22,593 | 12,251 | -46% | 1 | 1 | 0% | 2,939 | 3,160 | +8% | 0 | 0 | — |
case-16 | pass→pass | 24,014 | 18,861 | -21% | 1 | 1 | 0% | 3,591 | 3,977 | +11% | 0 | 0 | — |
case-17 | fail→pass | 21,710 | 18,051 | -17% | 1 | 1 | 0% | 2,534 | 2,950 | +16% | 0 | 0 | — |
case-18 | pass→pass | 20,001 | 16,479 | -18% | 1 | 1 | 0% | 2,927 | 3,564 | +22% | 0 | 0 | — |
case-19 | fail→fail | 20,105 | 23,085 | +15% | 1 | 1 | 0% | 3,383 | 3,726 | +10% | 0 | 0 | — |
case-20 | pass→pass | 23,953 | 14,304 | -40% | 1 | 1 | 0% | 3,018 | 3,484 | +15% | 0 | 0 | — |
case-21 | pass→pass | 20,895 | 24,890 | +19% | 1 | 1 | 0% | 2,665 | 3,756 | +41% | 0 | 0 | — |
case-22 | pass→pass | 22,543 | 22,745 | +1% | 1 | 1 | 0% | 2,929 | 3,917 | +34% | 0 | 0 | — |
case-24 | pass→pass | 19,453 | 12,765 | -34% | 1 | 1 | 0% | 2,315 | 2,964 | +28% | 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. The headline lift of +13 percentage points is the difference between those two pass rates over the 24 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.