Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Plan your first hire — whether to hire at all yet, contractor vs employee, what role to hire, and how to do it right when you've never hired before. Use when asked to help me make my first hire, should I hire someone, contractor or employee, or how do I hire for my small business. Produces a readiness and role read (what to hand off first), a contractor-vs-employee decision for your situation, a lightweight hiring process (role definition, sourcing, a fair evaluation, an offer), the obligations
.claude/skills/mohitagw15856-first-hire-plan/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | -31% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 17% | 0% |
| case-03 | ✗→✓ | ▲ Improved | -11% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 31% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 25% | 0% |
Your first hire is a big, nervy step — get the role wrong or the classification wrong and it's costly. This helps you decide whether you're ready, what to hand off first, and whether a contractor or employee fits — then gives a simple, fair hiring process for someone who's never done it, plus the obligations to know about. It flags that employment, tax, and legal rules are local and this isn't legal advice.
Ask for these if not provided:
Ready & role: is now the time] → hire for highest-leverage handoff first]. Contractor vs employee: trade-offs for you] → recommend x]; watch classification rules. Hire process: define role (responsibilities · must-haves · 90-day success]) → source → evaluate (small work sample) → offer. Obligations (verify locally): payroll · tax · insurance · legal duties]. Onboarding: expectations · tools · early wins].
> Not legal or tax advice. Employment, tax, and classification rules vary by location — set up correctly with a local professional.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 38,368 | 22,347 | -42% | 1 | 1 | 0% | 5,683 | 3,912 | -31% | 0 | 0 | — |
case-02 | fail→pass | 31,002 | 28,997 | -6% | 1 | 1 | 0% | 4,281 | 4,996 | +17% | 0 | 0 | — |
case-03 | fail→pass | 36,921 | 27,007 | -27% | 1 | 1 | 0% | 5,255 | 4,669 | -11% | 0 | 0 | — |
case-04 | fail→pass | 25,714 | 23,520 | -9% | 1 | 1 | 0% | 3,120 | 4,095 | +31% | 0 | 0 | — |
case-05 | fail→pass | 23,677 | 22,245 | -6% | 1 | 1 | 0% | 2,980 | 3,726 | +25% | 0 | 0 | — |
case-06 | fail→fail | 24,350 | 24,164 | -1% | 1 | 1 | 0% | 2,941 | 3,951 | +34% | 0 | 0 | — |
case-07 | fail→pass | 24,083 | 26,677 | +11% | 1 | 1 | 0% | 3,131 | 4,401 | +41% | 0 | 0 | — |
case-08 | fail→fail | 42,741 | 20,844 | -51% | 1 | 1 | 0% | 2,770 | 3,576 | +29% | 0 | 0 | — |
case-09 | fail→pass | 22,746 | 22,400 | -2% | 1 | 1 | 0% | 2,926 | 3,983 | +36% | 0 | 0 | — |
case-10 | fail→pass | 27,522 | 25,331 | -8% | 1 | 1 | 0% | 3,508 | 3,856 | +10% | 0 | 0 | — |
case-11 | fail→pass | 25,737 | 19,371 | -25% | 1 | 1 | 0% | 3,203 | 4,052 | +27% | 0 | 0 | — |
case-12 | fail→fail | 29,777 | 24,713 | -17% | 1 | 1 | 0% | 3,890 | 3,896 | +0% | 0 | 0 | — |
case-13 | fail→pass | 25,724 | 24,431 | -5% | 1 | 1 | 0% | 2,999 | 3,656 | +22% | 0 | 0 | — |
case-14 | fail→pass | 27,700 | 27,018 | -2% | 1 | 1 | 0% | 3,274 | 4,462 | +36% | 0 | 0 | — |
case-15 | fail→pass | 23,294 | 23,546 | +1% | 1 | 1 | 0% | 3,049 | 3,994 | +31% | 0 | 0 | — |
case-16 | pass→pass | 23,881 | 25,140 | +5% | 1 | 1 | 0% | 2,799 | 4,368 | +56% | 0 | 0 | — |
case-17 | fail→pass | 20,117 | 15,541 | -23% | 1 | 1 | 0% | 2,481 | 3,247 | +31% | 0 | 0 | — |
case-18 | fail→pass | 19,771 | 19,159 | -3% | 1 | 1 | 0% | 3,226 | 3,358 | +4% | 0 | 0 | — |
case-19 | pass→pass | 26,516 | 15,769 | -41% | 1 | 1 | 0% | 3,448 | 3,538 | +3% | 0 | 0 | — |
case-20 | pass→pass | 30,033 | 24,634 | -18% | 1 | 1 | 0% | 4,208 | 5,318 | +26% | 0 | 0 | — |
case-21 | pass→fail | 20,428 | 25,760 | +26% | 1 | 1 | 0% | 3,668 | 4,581 | +25% | 0 | 0 | — |
case-22 | fail→pass | 26,063 | 21,646 | -17% | 1 | 1 | 0% | 3,317 | 3,714 | +12% | 0 | 0 | — |
case-23 | fail→pass | 26,265 | 21,359 | -19% | 1 | 1 | 0% | 3,338 | 3,586 | +7% | 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. 23 cases were attempted. The headline lift of +65 percentage points is the difference between those two pass rates over the 23 comparable cases. 1 case got worse with the skill loaded, and it is 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.