What problem does it solve? Changing your list, copy, and offer at the same time destroys all learning signal in cold email campaigns. This Skill forces you to isolate one variable per experiment so you actually know what drove the result. ## Core Features & Use Cases - Three Experiment Types: Defines list-only, copy-only, and combined experiments with confidence weighting for each type of learning. - Sample Size & Baseline Rules: Provides minimum sends-per-arm tables, a 1% baseline sanity check, and a 21-day measurement window before evaluating results. - Structured Experiment Plan: Outputs a YAML experiment file with hypothesis, constants, success criteria, and arms for control and variant campaigns. - Use Case: You want to test whether Heads of Marketing respond better than VP Sales. The Skill walks you through locking copy and offer constant, calculating 2,000 sends per arm, launching both campaigns simultaneously in Smartlead, and measuring positive reply rate at day 21. ## Quick Start Ask the AI to design a list-only experiment testing a new target job title against your current baseline campaign.
