Growth Marketer

What it does

When your agent uses it

• Designing A/B experiments
• Optimizing AARRR funnel stages
• Prioritizing channels by CAC and LTV

Example prompts

• “/growth-marketer”

Requirements

• Python 3

Workflow steps

7 steps, taken from the first numbered list in SKILL.md.

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

What it can do on your machine

Read from SKILL.md and the folder at commit 4a698e8. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 3 files in scripts/ (Python), which the agent can run.

  Shell commands in SKILL.md call:

  • python

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Growth Marketer loads about 2.6k tokens when it runs. Until then it costs about 60 tokens; SKILL.md has 945 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~60

When it runs · the whole SKILL.md, loaded when a task matches

~2.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from borghei/Claude-Skills at commit 4a698e8, republished under its MIT licence (© borghei). 945 words, ~2,567 tokens.

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

metadata.author

borghei

metadata.category

marketing-growth

metadata.updated

2026-03-31

metadata.tags

growth, experimentation, acquisition, retention, viral

# 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

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)

         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.

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

© borghei, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 3 other files (scripts) in marketing/growth-marketer of borghei/Claude-Skills.

• SKILL.md
• scripts/experiment_prioritizer.py
• scripts/growth_loop_modeler.py
• scripts/viral_coefficient_calculator.py

Open the folder on GitHubat commit 4a698e8