<< All versions

Skill v1.0.2

currentLLM-judged scan95/100
borghei/claude-skills/growth-marketer

6 files

──Details
PublishedOctober 3, 2026 at 12:10 AM
Content Hashsha256:9a5cde032874dc36...
Git SHA5318eda16c13
Bump Typepatch
Compare with v1.0.1
──Files
Files (1 file, 10.1 KB)
SKILL.md10.1 KBactive
SKILL.md · 220 lines · 10.1 KB

version: "1.0.2" name: growth-marketer description: > Growth marketing covering experimentation, funnel optimization, acquisition channels, retention, and viral growth. Use when designing A/B experiments, optimizing AARRR funnel stages, or prioritizing channels by CAC and LTV. license: MIT + Commons Clause metadata: version: 1.0.0 author: borghei category: marketing-growth updated: 2026-03-31 tags: [growth, experimentation, acquisition, retention, viral]


Growth Marketer

The agent operates as a senior growth marketer, delivering experiment-driven strategies for scalable user acquisition, activation, retention, referral, and revenue optimization.

Clarify First

Before designing experiments or a growth plan, confirm these inputs. If any is unknown or vague, ASK — do not assume:

  • [ ] North Star Metric + current AARRR baselines — the metric and per-stage numbers (Steps 1–2 require these; without a baseline the "biggest lever" is a guess)
  • [ ] Experiment hypothesis + primary/guardrail metrics — the change expected and how it's judged (drives the experiment doc and ship/iterate/kill)
  • [ ] Baseline rate + MDE — current conversion and smallest lift worth detecting (feeds the sample-size calc directly)
  • [ ] Daily eligible traffic — visitors per variant per day (determines whether the test can reach significance and over what duration)

Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.

Workflow

  1. Define North Star Metric - Identify the single metric that reflects customer value and leads to revenue. Checkpoint: the metric must be measurable, actionable, and correlated with retention.
  2. Map the AARRR funnel - Quantify current performance at each stage (Acquisition, Activation, Retention, Referral, Revenue). Checkpoint: every stage has a baseline number and a target.
  3. Identify biggest lever - Find the funnel stage with the largest drop-off or lowest performance vs. benchmark. This becomes the focus area.
  4. Design experiments - Write hypotheses using the format: "If we [change], then [metric] will [direction] by [amount] because [reasoning]." Prioritize using ICE scoring.
  5. Calculate sample size and run - Determine required sample per variant for statistical significance (95% confidence, 80% power). Launch the experiment.
  6. Analyze results - Evaluate lift, p-value, and guardrail metrics. Decision: Ship, Iterate, or Kill.
  7. Model growth trajectory - Forecast user growth incorporating acquisition rate, churn, and viral coefficient. Validate that LTV:CAC > 3:1 for sustainability.

AARRR Funnel (Pirate Metrics)

StageKey QuestionMetricsBenchmark
AcquisitionHow do users find us?Traffic, CAC, channel mixCAC < 1/3 LTV
ActivationGreat first experience?Activation rate, time to value40%+ activation
RetentionDo users come back?D1/D7/D30 retention, churnSaaS: D30 30%
ReferralDo users tell others?Viral coefficient (K), NPSK-factor > 0.5
RevenueHow do we monetize?ARPU, LTV, conversion rateLTV:CAC > 3:1

Experimentation Framework

Experiment Document Template

markdown
# Experiment: Onboarding Checklist v2
## Hypothesis
If we add a progress bar to the onboarding checklist, then activation rate
will increase by 15% because users respond to completion motivation.
## Metrics
-Primary: 7-day activation rate
-Secondary: Time to first value action
-Guardrails: Support ticket volume, bounce rate
## Design
-Type: A/B test
-Sample: 8,200 per variant (5% baseline, 15% MDE, 95% confidence)
-Duration: 14 days
-Segments: New signups only
## Results
| Variant | Users | Activation | Lift | p-value |
|-----------|--------|------------|-------|---------|
| Control | 8,350 | 5.1% | - | - |
| Treatment | 8,280 | 6.2% | +21% | 0.003 |
## Decision: Ship

ICE Prioritization

ExperimentImpact (1-10)Confidence (1-10)Ease (1-10)ICE Score
Onboarding checklist v287924
Referral incentive test68721
Pricing page redesign95620

Sample Size Calculator

python
from scipy import stats
def sample_size(baseline_rate, mde, alpha=0.05, power=0.8):
"""Calculate required sample size per variant for an A/B test.
Args:
baseline_rate: Current conversion rate (e.g. 0.05 for 5%)
mde: Minimum detectable effect as proportion (e.g. 0.15 for 15% lift)
alpha: Significance level (default 0.05)
power: Statistical power (default 0.8)
Returns:
Required users per variant (int)
Example:
>>> sample_size(0.05, 0.15)
8218
"""
effect_size = mde * baseline_rate
z_alpha = stats.norm.ppf(1 - alpha / 2)
z_beta = stats.norm.ppf(power)
n = 2 * ((z_alpha + z_beta) ** 2) * baseline_rate * (1 - baseline_rate) / (effect_size ** 2)
return int(n)

Acquisition Channel Analysis

ChannelCACVolumeQualityScalability
Organic Search$20HighHighMedium
Paid Search$50MediumHighHigh
Social Organic$10MediumMediumLow
Social Paid$40HighMediumHigh
Content$15MediumHighMedium
Referral$5LowVery HighMedium
Partnerships$30MediumHighMedium

Retention Benchmarks

CategoryD1D7D30
SaaS60%40%30%
Social50%30%20%
E-commerce25%15%10%
Games35%15%8%

Cohort Analysis Example

Week 0 Week 1 Week 2 Week 3 Week 4
Jan W1 100% 45% 35% 28% 25%
Jan W2 100% 48% 38% 32% 28%
Jan W3 100% 52% 42% 35% 31%
Jan W4 100% 55% 45% 38% 34%
Insight: Week-over-week improvement correlates with onboarding
changes shipped in Jan W3.

Viral Growth

K-Factor = invites per user (i) x conversion rate of invites (c)

  • K > 1: True viral growth (each user brings >1 new user)
  • K = 0.5-1: Viral boost (amplifies paid acquisition)
  • K < 0.5: Minimal viral effect

Growth Forecast Model

python
def growth_forecast(current_users, monthly_growth_rate, months):
"""Forecast user base over time with compound growth.
Example:
>>> growth_forecast(10000, 0.10, 12)[-1]
31384
"""
users = [current_users]
for _ in range(months):
users.append(int(users[-1] * (1 + monthly_growth_rate)))
return users

Troubleshooting

SymptomLikely CauseResolution
K-factor below 0.1 despite referral programInvite UX has too much friction or incentive misaligned with user valueReduce invite flow to one click; align incentive with product value (usage credits > cash)
Activation rate below 20% for new signupsTime-to-value too long or onboarding not guiding users to aha momentMap activation events, identify first value action, build guided onboarding to reach it in under 5 minutes
Growth stalls after initial PLG rampFree tier captures low-intent users who never convert; paid conversion rate below 3%Tighten free tier limits around high-value features, add contextual upgrade prompts at usage gates
A/B test results not reaching significanceSample size too small for the minimum detectable effect being testedUse sample size calculator; increase traffic to test or accept larger MDE
Cohort retention curves flatten at under 15%Product does not build enough habit; no ongoing value loopImplement engagement hooks (notifications, reports, streaks); investigate which features drive retention
Experiments consistently show no liftTesting cosmetic changes rather than meaningful value propositionsFocus experiments on activation flow, pricing, and value communication — not button colors

Success Criteria

  • North Star Metric identified, measurable, and reviewed weekly with cross-functional team
  • Activation rate above 40% for new signups within first 7 days
  • LTV:CAC ratio sustained above 3:1 across all acquisition channels
  • K-factor above 0.5, providing meaningful viral amplification of paid acquisition
  • Experiment velocity of 2+ tests per sprint with documented hypotheses and outcomes
  • D30 retention at or above SaaS benchmark (30%) for primary user segment
  • Growth model accurately forecasts within 15% of actual for 3-month projections

Scope & Limitations

In Scope: AARRR funnel optimization, experiment design and prioritization (ICE/RICE), viral growth modeling, PLG strategy, retention analysis, cohort analysis, growth forecasting, acquisition channel analysis, sample size calculation.

Out of Scope: Brand strategy (see brand-strategist skill), content creation (see content-creator skill), paid ad campaign management (see paid-ads skill), product design and engineering implementation, pricing strategy.

Limitations: Growth loop models use simplified compound growth assumptions — real growth has diminishing returns and market saturation effects. Viral coefficient calculations assume uniform user behavior; actual viral spread varies by segment. Sample size calculator uses normal approximation; for very low conversion rates, exact tests may be needed.


Scripts

ScriptPurposeUsage
scripts/growth_loop_modeler.pyModel viral, PLG, and content growth loops with forecastspython scripts/growth_loop_modeler.py --type viral --users 1000 --k-factor 0.6 --months 12
scripts/viral_coefficient_calculator.pyCalculate K-factor, branching factor, and improvement scenariospython scripts/viral_coefficient_calculator.py --invites 5000 --conversions 800 --users 2000
scripts/experiment_prioritizer.pyPrioritize growth experiments using ICE or RICE scoringpython scripts/experiment_prioritizer.py experiments.json --framework ice --demo
← v1.0.1All versions