agentsclimarketplace

Ab test setup

Skill bromso/metapowers/plugins/marketing/skills/ab-test-setup

A Claude Code plugin that adds an agentic skills framework, with MCP's and a meta prompting processes. Inspired by "Superpowers" & "Figma Console MCP", but not just for development or design; but for all aspect within the digital production cycle.

Install
npx -y skills add bromso/metapowers --skill ab-test-setup

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Design A/B tests with hypothesis, measurement, and statistical rigor

SKILL.md

2.5 KB, as published. Nobody here has run it

A/B Test Setup

Design rigorous A/B tests for "$ARGUMENTS". Create testable hypotheses, define variants, calculate sample sizes, and plan measurement.

Prerequisites

Read .metapowers/marketing/$ARGUMENTS/00-strategy.md. If this file does not exist, tell the user:

Phase 0 (Strategy) has not been completed for "$ARGUMENTS". Run /marketing:customer-research $ARGUMENTS first, or use --skip-checks to bypass.

If --skip-checks is present in $ARGUMENTS, skip this check and log to .metapowers/marketing/$ARGUMENTS/skip-log.md.

Process

  1. Read context:

    • Read .metapowers/marketing/$ARGUMENTS/00-strategy.md for business context
    • Read .metapowers/marketing/$ARGUMENTS/02-act.md and .metapowers/marketing/$ARGUMENTS/03-convert.md if they exist (for CRO recommendations that need testing)

  2. Define the test:

    • What are you testing? (headline, CTA, layout, pricing, flow)
    • Hypothesis format: "If we [change], then [metric] will [improve/decrease] by [amount], because [rationale]"
    • Primary metric (one clear success metric)
    • Secondary metrics (guard-rail metrics to watch)

  3. Design variants:

    • Control (A): current experience
    • Treatment (B): specific change — one variable only
    • If multivariate: document variable matrix
    • Screenshots or mockups of each variant

  4. Statistical planning:

    • Current baseline metric (conversion rate, click rate, etc.)
    • Minimum detectable effect (MDE): what improvement is meaningful?
    • Required sample size calculation
    • Expected test duration based on traffic
    • Statistical significance threshold (typically 95%)

  5. Implementation plan:

    • Testing tool recommendation (if not already decided)
    • Traffic split: 50/50 or other
    • Segment targeting: who sees the test?
    • QA checklist before launch

  6. Write the artifact — append to .metapowers/marketing/$ARGUMENTS/03-convert.md under a ## A/B Test: [Test Name] section:

    • Hypothesis — structured hypothesis statement
    • Variants — control and treatment descriptions
    • Metrics — primary and secondary
    • Statistical Plan — sample size, duration, significance
    • Implementation — tool, targeting, QA steps
    • Decision Framework — what to do based on results

Output

A/B test plan written to .metapowers/marketing/$ARGUMENTS/03-convert.md. Present the hypothesis and expected timeline to the user.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.