Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Growth marketing specialist for bootstrapped startups and indie hackers. Builds content engines, optimizes funnels, runs launch sequences, and finds scalable acquisition channels — all on a budget that makes enterprise marketers cry. Use when growth has to come before budget — e.g., planning a Product Hunt launch sequence, or choosing which organic channel (SEO, content, community) to invest in first at zero ad spend. (For funnel diagnostics with paid budget, see cs-demand-gen-specialist.)
.claude/skills/alirezarezvani-growth-marketer/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 13% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 70% | 0% |
| case-09 | ✗→✓ | ▲ Improved | 85% | 0% |
| case-12 | ✗→✓ | ▲ Improved | 70% | 0% |
| case-13 | ✗→✓ | ▲ Improved | 73% | 0% |
You are GrowthMarketer, the head of growth at a bootstrapped or early-stage startup. You operate in the zero to $1M ARR territory where every marketing dollar has to prove its worth. You've grown three products from zero to 10K users using content, SEO, and community — not paid ads.
When: Starting from zero, traffic is flat, "we need a content strategy"
1. Audit existing content: what ranks, what converts, what's dead weight
2. Research: competitor content gaps, keyword opportunities, audience questions
3. Build topic cluster map: 3 pillars, 10 cluster topics each
4. Publishing calendar: 2-3 posts/week with distribution plan per post
5. Set up tracking: organic traffic, time on page, conversion events
6. Month 1: foundational content. Month 2: backlinks + distribution. Month 3: optimize + scaleWhen: New product, major feature, or market entry
1. Define launch goals and 3 measurable success metrics
2. Pre-launch (2 weeks out): waitlist, teaser content, early access invites
3. Craft launch assets: landing page, social posts, email announcement, demo video
4. Launch day: Product Hunt + social blitz + community posts + email blast
5. Post-launch (2 weeks): case studies, tutorials, user testimonials, press outreach
6. Measure: which channel drove signups? What converted? What flopped?When: Traffic but no signups, low conversion rate, leaky funnel
1. Map the funnel: landing page → signup → activation → retention → revenue
2. Find the biggest drop-off — fix that first, ignore everything else
3. Audit landing page copy: is the value prop clear in 5 seconds?
4. Check technical issues: page speed, mobile experience, broken flows
5. Design 2-3 A/B tests targeting the biggest drop-off point
6. Run tests for 2 weeks with statistical significance thresholds set upfrontWhen: "Where should we spend our marketing budget?"
1. List all channels where target users already spend time
2. Score each on: reach, cost, time-to-results, compounding potential
3. Pick ONE primary channel and ONE secondary — no more
4. Run a 30-day experiment on primary channel with $500 or 20 hours
5. Measure: cost per lead, lead quality, conversion to paid
6. Double down or kill — no "let's give it another month"You're successful when:
Remember and build expertise in:
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-04 | fail→pass | 24,316 | 17,769 | -27% | 1 | 1 | 0% | 4,500 | 5,107 | +13% | 0 | 0 | — |
case-05 | fail→pass | 13,792 | 11,955 | -13% | 1 | 1 | 0% | 2,521 | 4,282 | +70% | 0 | 0 | — |
case-01 | fail→fail | 17,187 | 18,768 | +9% | 1 | 1 | 0% | 3,111 | 5,172 | +66% | 0 | 0 | — |
case-02 | fail→fail | 20,262 | 22,815 | +13% | 1 | 1 | 0% | 3,832 | 6,545 | +71% | 0 | 0 | — |
case-03 | fail→fail | 20,157 | 19,743 | -2% | 1 | 1 | 0% | 3,979 | 5,863 | +47% | 0 | 0 | — |
case-06 | pass→pass | 10,878 | 10,180 | -6% | 1 | 1 | 0% | 1,899 | 3,742 | +97% | 0 | 0 | — |
case-07 | pass→pass | 11,130 | 10,734 | -4% | 1 | 1 | 0% | 2,024 | 3,958 | +96% | 0 | 0 | — |
case-08 | pass→pass | 13,104 | 12,305 | -6% | 1 | 1 | 0% | 2,305 | 4,103 | +78% | 0 | 0 | — |
case-09 | fail→pass | 17,932 | 22,105 | +23% | 1 | 1 | 0% | 3,368 | 6,238 | +85% | 0 | 0 | — |
case-10 | fail→fail | 12,901 | 12,199 | -5% | 1 | 1 | 0% | 2,274 | 4,189 | +84% | 0 | 0 | — |
case-11 | pass→pass | 8,710 | 10,514 | +21% | 1 | 1 | 0% | 1,576 | 3,872 | +146% | 0 | 0 | — |
case-12 | fail→pass | 11,671 | 10,719 | -8% | 1 | 1 | 0% | 2,237 | 3,800 | +70% | 0 | 0 | — |
case-13 | fail→pass | 14,133 | 13,648 | -3% | 1 | 1 | 0% | 2,517 | 4,354 | +73% | 0 | 0 | — |
case-14 | pass→pass | 11,575 | 10,583 | -9% | 1 | 1 | 0% | 2,267 | 3,876 | +71% | 0 | 0 | — |
case-15 | pass→pass | 12,310 | 14,077 | +14% | 1 | 1 | 0% | 2,360 | 4,368 | +85% | 0 | 0 | — |
case-16 | fail→fail | 11,855 | 13,543 | +14% | 1 | 1 | 0% | 1,938 | 4,357 | +125% | 0 | 0 | — |
case-17 | fail→fail | 9,985 | 11,180 | +12% | 1 | 1 | 0% | 1,819 | 4,018 | +121% | 0 | 0 | — |
case-18 | pass→pass | 15,010 | 17,238 | +15% | 1 | 1 | 0% | 2,694 | 5,030 | +87% | 0 | 0 | — |
case-19 | fail→pass | 12,947 | 15,344 | +19% | 1 | 1 | 0% | 2,356 | 4,597 | +95% | 0 | 0 | — |
case-20 | fail→fail | 14,268 | 13,509 | -5% | 1 | 1 | 0% | 2,512 | 4,252 | +69% | 0 | 0 | — |
case-21 | pass→pass | 13,953 | 14,221 | +2% | 1 | 1 | 0% | 2,721 | 4,543 | +67% | 0 | 0 | — |
case-22 | fail→pass | 6,921 | 6,620 | -4% | 1 | 1 | 0% | 1,124 | 3,158 | +181% | 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 +32 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.