home / skills / onewave-ai / claude-skills / email-subject-line-optimizer

email-subject-line-optimizer skill

safe

This skill helps craft high-performing email subject lines, predict open rates, and guide A/B testing with proven copyframes.

npx playbooks add skill onewave-ai/claude-skills --skill email-subject-line-optimizer

Review the files below or copy the command above to add this skill to your agents.

Files (1)

SKILL.md

1.4 KB

---
name: email-subject-line-optimizer
description: A/B test subject line variations using proven copywriting frameworks. Predict open rates based on historical performance.
---

# Email Subject Line Optimizer
A/B test subject line variations using proven copywriting frameworks. Predict open rates based on historical performance.

## Instructions

You are an expert at email marketing and copywriting. Create high-performing subject lines, predict open rates, and provide A/B testing recommendations.

### Output Format

```markdown
# Email Subject Line Optimizer Output

**Generated**: {timestamp}

---

## Results

[Your formatted output here]

---

## Recommendations

[Actionable next steps]

```

### Best Practices

1. **Be Specific**: Focus on concrete, actionable outputs
2. **Use Templates**: Provide copy-paste ready formats
3. **Include Examples**: Show real-world usage
4. **Add Context**: Explain why recommendations matter
5. **Stay Current**: Use latest best practices for marketing

### Common Use Cases

**Trigger Phrases**:
- "Help me with [use case]"
- "Generate [output type]"
- "Create [deliverable]"

**Example Request**:
> "[Sample user request here]"

**Response Approach**:
1. Understand user's context and goals
2. Generate comprehensive output
3. Provide actionable recommendations
4. Include examples and templates
5. Suggest next steps

Remember: Focus on delivering value quickly and clearly!

Overview

This skill A/B tests email subject line variations using proven copywriting frameworks and predicts open rates based on historical performance. It generates high-performing, copy-paste-ready subject lines, ranks them by predicted open rate, and delivers clear A/B test plans. Use it to reduce guesswork and accelerate subject line optimization for campaigns.

How this skill works

The skill analyzes historical open-rate data and campaign metadata, then applies proven frameworks (curiosity, urgency, benefit, personalization) to produce variant subject lines. It scores each variant with a predicted open-rate model calibrated to your past performance and suggests head-to-head A/B test pairings. Recommendations include sample audience splits, statistical confidence targets, and rollout steps to validate winners.

When to use it

Before sending a major campaign to maximize initial open rates
When open rates are declining and you need fresh subject line strategies
To validate whether personalization or urgency drives better engagement
When you have historical campaign data and want data-driven predictions
To create testable subject line libraries for automated sending tools

Best practices

Provide at least 6–12 past campaigns with open rates for accurate predictions
Test single-variable changes first (e.g., personalization vs no personalization)
Run A/B tests long enough to reach statistical confidence, typically 1,000+ recipients per variant
Keep subject lines under 50 characters for mobile visibility and include a clear value proposition
Track downstream metrics (clicks, conversions) to ensure open rate gains translate to results

Example use cases

Generate 8 subject line variants for a product launch and predict open rates for each
Compare personalization vs urgency frameworks for a re-engagement campaign
Create an A/B test plan with audience splits and confidence thresholds for a newsletter
Audit past campaign subject lines and recommend highest-impact changes
Build a reusable subject line template library tailored to your brand voice

FAQ

What input data improves prediction accuracy?

Provide historical open rates, send times, subject lines, audience segments, and campaign context; more rows across varied campaigns improve model calibration.

How many variants should I test at once?

Start with 2–4 variants per test to preserve traffic per variant; larger variant sets require more recipients to reach confidence.