Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Make your first (or next) marketing/growth hire: decide the archetype, source candidates on the right boards, and screen with a paid role-specific test project instead of resumes. Use whenever the user is hiring a marketer, asking "what's my first growth hire", weighing a full-timer vs freelancer vs agency vs consultant, deciding where to post a marketing role, wondering how to evaluate marketing candidates, or considering a Gen Marketer / AI-fluent generalist. Trigger phrases: "first marketing
.claude/skills/whatsuppiyush-hiring-team/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 42% | 0% |
| case-02 | ✗→✓ | ▲ Improved | 54% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 95% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 72% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 36% | 0% |
The discipline of building an early marketing/growth team: choosing the archetype you actually need, sourcing the right candidates cheaply, and screening for how someone thinks and executes rather than how their resume reads.
Reach for this when the user is adding marketing capacity:
Symptoms that point here: "I need a marketer but don't know what kind", "should I hire or outsource", "how do I test a candidate", "our job post got no good applicants".
strategy-fundamentals first. Decide the strategy before you post, because it determines the archetype.Every play above, in full.
Before a full-time commitment, screen marketers with a small, role-specific paid test project that shows how they think and execute against your actual business. You won't find a candidate who checks every box, prioritize the 2-3 functions you most need over well-rounded generalists.
Hiring your first or next marketer and deciding between candidates (or between a hire and a contractor). Define your growth strategy, stage, product type, business model, before you post.
Becomes an interview-test-project prompt: input the role + business context, output a paid take-home brief with a clear rubric for scoring the deliverable.
The old first-marketing-hire choice was a false binary: an expensive senior exec (strategy but no hands-on execution, high cost) or a narrow junior specialist (executes one channel, needs direction). AI opens a third path, the "Gen Marketer": a strategist who uses AI to execute across many functions alone.
Making your first (or early) growth/marketing hire at a startup, especially a lean or AI-native one.
Lower skill value (a hiring-archetype guide); could become a "Gen Marketer scorecard" that defines the cross-functional test project and the AI-fluency signals to verify vs. resume claims.
Different candidate profiles cluster on different platforms, so pick the board (and sourcing trick) that matches the marketer type you defined first. Includes a build-vs-buy alternative: train your existing team instead of hiring.
Once you know the marketer type you need and are ready to source candidates cost-effectively.
evaluate-marketing-candidates.md covers the paid test-project screening once candidates apply.Becomes a source-marketing-hire prompt: input the marketer type + budget, output the ranked board list with costs, a sourcing-trick checklist, and a job-description skeleton.
From God of Skills: a curated, hand-tested directory of AI skills, prompts, templates and image style guides. Source: https://godofskills.com/skills/hiring-team?ref=claude-skill
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 21,159 | 13,785 | -35% | 1 | 1 | 0% | 3,211 | 4,571 | +42% | 0 | 0 | — |
case-02 | fail→pass | 20,773 | 18,537 | -11% | 1 | 1 | 0% | 3,531 | 5,439 | +54% | 0 | 0 | — |
case-03 | pass→pass | 21,972 | 12,885 | -41% | 1 | 1 | 0% | 3,729 | 4,619 | +24% | 0 | 0 | — |
case-04 | pass→pass | 19,848 | 18,987 | -4% | 1 | 1 | 0% | 3,192 | 5,555 | +74% | 0 | 0 | — |
case-05 | pass→fail | 17,643 | 18,369 | +4% | 1 | 1 | 0% | 3,610 | 5,742 | +59% | 0 | 0 | — |
case-06 | pass→pass | 13,147 | 7,858 | -40% | 1 | 1 | 0% | 2,261 | 3,714 | +64% | 0 | 0 | — |
case-07 | fail→pass | 13,481 | 11,785 | -13% | 1 | 1 | 0% | 2,179 | 4,251 | +95% | 0 | 0 | — |
case-08 | fail→fail | 12,027 | 13,987 | +16% | 1 | 1 | 0% | 2,366 | 4,659 | +97% | 0 | 0 | — |
case-09 | pass→pass | 17,105 | 11,541 | -33% | 1 | 1 | 0% | 2,698 | 4,314 | +60% | 0 | 0 | — |
case-10 | fail→pass | 15,293 | 10,813 | -29% | 1 | 1 | 0% | 2,409 | 4,153 | +72% | 0 | 0 | — |
case-11 | pass→pass | 15,508 | 8,426 | -46% | 1 | 1 | 0% | 2,698 | 3,762 | +39% | 0 | 0 | — |
case-12 | fail→pass | 13,973 | 5,893 | -58% | 1 | 1 | 0% | 2,482 | 3,373 | +36% | 0 | 0 | — |
case-17 | fail→pass | 12,471 | 8,448 | -32% | 1 | 1 | 0% | 2,115 | 3,808 | +80% | 0 | 0 | — |
case-13 | pass→pass | 11,084 | 4,399 | -60% | 1 | 1 | 0% | 1,838 | 3,026 | +65% | 0 | 0 | — |
case-14 | fail→pass | 5,699 | 3,066 | -46% | 1 | 1 | 0% | 1,015 | 2,844 | +180% | 0 | 0 | — |
case-15 | pass→pass | 12,419 | 9,080 | -27% | 1 | 1 | 0% | 2,109 | 3,976 | +89% | 0 | 0 | — |
case-16 | pass→pass | 11,894 | 7,066 | -41% | 1 | 1 | 0% | 1,864 | 3,428 | +84% | 0 | 0 | — |
case-18 | pass→pass | 13,882 | 10,297 | -26% | 1 | 1 | 0% | 2,379 | 4,051 | +70% | 0 | 0 | — |
case-19 | pass→pass | 15,038 | 14,614 | -3% | 1 | 1 | 0% | 2,274 | 4,751 | +109% | 0 | 0 | — |
case-20 | pass→pass | 13,401 | 5,939 | -56% | 1 | 1 | 0% | 2,089 | 3,376 | +62% | 0 | 0 | — |
case-21 | pass→pass | 14,095 | 10,457 | -26% | 1 | 1 | 0% | 2,251 | 3,945 | +75% | 0 | 0 | — |
case-22 | pass→pass | 14,942 | 10,259 | -31% | 1 | 1 | 0% | 2,361 | 4,065 | +72% | 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. 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.