Run email A/B tests with statistical rigor. Use when testing subject lines, content variants, send times, CTAs, or measuring experiment significance.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# A/B Testing
Test email variations systematically to improve open rates, click rates, and conversions with statistical confidence.
## When to use this skill
- Setting up your first email A/B test
- Open rates or click rates are flat and you want data-driven improvements
- Deciding between subject line variations, send times, or content approaches
- Determining if your test results are statistically significant or just noise
- Planning a testing program across campaigns or sequences
- Evaluating whether to use A/B testing, multivariate testing, or bandit algorithms
- Measuring the true incremental lift of your email program with holdout groups
## Related skills
- `email-copywriting` - writing the actual content variations to test
- `template-design` - HTML template variations for layout and visual tests
- `spam-filter-avoidance` - ensure test variants don't accidentally trigger spam filters
- `sender-reputation` - monitor whether testing impacts your sending reputation
- `email-sequences` - testing within drip campaigns and automated sequences
---
## What to test (in priority order)
…
The line at the top of this page pins the label git:20260330.20e817f, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_qsj5uoidulglelvi
GET https://markdownregistry.com/api/v1/resolve?ref=chunkydotdev/email-skills/ab-testing
GET https://markdownregistry.com/api/v1/blob/097833968850e01ea0dec0b426f38e61b675ad91fe90843768370846a9650921
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
chunkydotdev/email-skills · plugins/molted/skills/molted/SKILL.md · Add email (sending, replying, reading a test inbox) to an agent you're building, using Molted's agent-native email…
chunkydotdev/email-skills · skills/compliance/email-security/SKILL.md · Protect email pipelines from injection attacks, phishing, content manipulation, and AI agent exploitation. Use when…
chunkydotdev/email-skills · skills/content/spam-filter-avoidance/SKILL.md · Avoid triggering spam filters with your email content. Use when emails land in spam, auditing content for filter…
chunkydotdev/email-skills · skills/content/template-design/SKILL.md · Build HTML email templates that render everywhere. Use when designing email layouts, fixing Outlook rendering…
chunkydotdev/email-skills · skills/deliverability/email-warmup/SKILL.md · Ramp sending volume on new domains and IPs. Use when launching a new sending domain, switching providers, moving to a…
chunkydotdev/email-skills · skills/deliverability/inbox-placement/SKILL.md · Understand what determines inbox vs spam placement. Use when emails land in spam, investigating Gmail Promotions tab…
chunkydotdev/email-skills · skills/deliverability/sender-reputation/SKILL.md · Monitor and protect your email sender reputation. Use when deliverability drops, investigating spam placement, checking…
chunkydotdev/email-skills · skills/diagnostics/email-diagnostics/SKILL.md · Diagnose email problems and plan email infrastructure. Use when emails land in spam, bounce rates spike, deliverability…
coreyhaines31/marketingskills · skills/ab-testing/SKILL.md · When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program…
sickn33/agentic-awesome-skills · plugins/agentic-awesome-skills-claude/skills/ab-testing/SKILL.md · When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.
ericrisco/rsc-harness · skills/ab-testing/SKILL.md · Use when designing or analyzing a controlled experiment — falsifiable hypothesis, sample size from an MDE, reading…
cesarjoquin/marketing-skills · skills/ab-testing/SKILL.md · When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program…
growthack88/growth-marketing-os · skills/community/ab-testing/SKILL.md · When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program…
francostino/opencode-skills-collection · bundled-skills/ab-testing/SKILL.md · When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program.
wankimmy/bossku-superpowers · skills/ab-testing/SKILL.md · When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program…
