Cold Email A/B Testing

What it does

Generates cold email variants before launch while respecting minimum volume thresholds per variant, then after sending calculates the winner with a z-test and delivers clear optimization recommendations for the next round.

When to use it

• When you want to test different subject lines or openers in a cold email campaign.
• When you need to know if a variant truly wins or the difference is noise.
• When you iterate campaigns continuously and want a repeatable process.

Steps

1. Define how many variants you want to test and the test's goal.
2. The assistant validates each variant has minimum volume before launch.
3. The send plan is built respecting those thresholds.
4. Results are monitored as opens and replies come in.
5. At close, statistical significance is calculated with a z-test.
6. The winning variant recommendation is delivered as a draft for your next campaign.

The skill

---
name: cold-email-ab-testing
description: Full-lifecycle A/B testing for cold email: pre-launch variant generation with minimum thresholds and post-launch statistical analysis.
---

# Cold Email A/B Testing

## 1. What it does

- Generates cold email variants before launch while respecting minimum volume thresholds per variant, then after sending calculates the winner with a z-test and delivers clear optimization recommendations for the next round.

## 2. When to use it

- When you want to test different subject lines or openers in a cold email campaign.
- When you need to know if a variant truly wins or the difference is noise.
- When you iterate campaigns continuously and want a repeatable process.

## 3. Step by step

- Define how many variants you want to test and the test's goal.
- The assistant validates each variant has minimum volume before launch.
- The send plan is built respecting those thresholds.
- Results are monitored as opens and replies come in.
- At close, statistical significance is calculated with a z-test.
- The winning variant recommendation is delivered as a draft for your next campaign.

## 4. Safety rules

- Safety rules: everything ships as a draft first; nothing is sent, published, or paid for without your explicit approval; no data, numbers, or results are ever invented; no credentials or secrets are typed into chat.

## 5. Best practices

- Always review the full draft before approving any send, publish, or payment.
- If real information (data, numbers, results) is missing, ask for it to be flagged as pending instead of invented.
- Keep credentials and keys out of chat; set them in environment variables or your secrets manager.

## 6. GoHighLevel integration

- Where relevant, results can be saved as contacts, tags, tasks, or notes inside your GoHighLevel sub-account.
- No automation inside GHL (workflow, campaign, trigger) activates without your review first.

For Claude Code, save it as ~/.claude/skills/cold-email-ab-testing/SKILL.md. In Cursor, ChatGPT or another assistant, paste it as project instructions.