← marketplace
marketingconceptsha:265851ea25f2d313manual
ab-testing
Use when planning, designing, or interpreting A/B tests and growth experiments so the agent follows the marketingskills playbook instead of producing generic marketing advice.
source: https://github.com/coreyhaines31/marketingskills/tree/main/skills/ab-testing ↗coreyhaines31/marketingskills· ★ 35k
Install confidence
curl --create-dirs -fsSL https://skillmake.xyz/i/ab-testing -o ~/.claude/skills/ab-testing/SKILL.md
Pinned content
sha:265851ea25f2d313
Generated with
manual
Source
github.com
The file served at /api/marketplace/ab-testing-265851ea/raw matches this hash. Inspect before install, then copy the command.
2,610 chars · ~653 tokens
--- name: ab-testing description: Use when planning, designing, or interpreting A/B tests and growth experiments so the agent follows the marketingskills playbook instead of producing generic marketing advice. source: https://github.com/coreyhaines31/marketingskills/tree/main/skills/ab-testing generated: 2026-06-29T17:58:26.577Z category: concept audience: marketing --- ## When to use - The user asks for help planning, designing, or interpreting A/B tests and growth experiments - A marketing task needs product, audience, positioning, and channel context before execution - The agent should create a repeatable ab testing workflow instead of a one-off generic answer - The work needs clear success metrics, deliverables, and next steps for a growth or GTM motion ## Key concepts ### Core Principles Core part of the ab testing workflow; use it to keep the agent focused on concrete marketing inputs, decisions, and outputs instead of vague recommendations. ### 1. Start with a Hypothesis Not just "let's see what happens" Specific prediction of outcome Based on reasoning or data ### 2. Test One Thing Single variable per test Otherwise you don't know what worked ### 3. Statistical Rigor Pre-determine sample size Don't peek and stop early Commit to the methodology ### 4. Measure What Matters Primary metric tied to business value Secondary metrics for context Guardrail metrics to prevent harm ### Hypothesis Framework Core part of the ab testing workflow; use it to keep the agent focused on concrete marketing inputs, decisions, and outputs instead of vague recommendations. ## API reference ``` npx skills add coreyhaines31/marketingskills --skill ab-testing ``` Install the ab-testing skill from coreyhaines31/marketingskills. ``` npx skills add coreyhaines31/marketingskills --skill ab-testing ``` ## Gotchas - Do not peek at results and stop early; pre-commit the sample size and decision rule before launch. - Avoid testing multiple major changes at once unless the task is explicitly a multivariate test. - Read product-marketing context first when present; otherwise the agent may ask repeated setup questions or make weak positioning assumptions. - Do not ship generic best practices without tying recommendations to the product, audience, channel, and conversion goal. - Separate strategy from execution: clarify the campaign decision before drafting assets or implementation steps. --- Generated by SkillMake from https://github.com/coreyhaines31/marketingskills/tree/main/skills/ab-testing on 2026-06-29T17:58:26.577Z. Verify against source before relying on details.
File: ~/.claude/skills/ab-testing/SKILL.md