Email Subject Line Optimizer for ChatGPT: Draft an A/B Test
Draft two subjects for a confirmed email and isolate a wording difference. Specify the audience and evaluation window while leaving unknown performance for measurement.
中文Install in ChatGPT
Use an eligible ChatGPT workspace with permission to create skills and, for uploads, upload permission. The installation path for this text-only adaptation was checked against OpenAI documentation. Workspace runtime verification is pending.
- Download workflows/content-creator-workflow/.claude/skills/email-subject-line-optimizer/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for email-subject-line-optimizer together as a standalone text skill.
- In a ChatGPT workspace with skills and uploads enabled, open Plugins, Skills, Create, and Upload from your computer. Choose a skill package format accepted by the file picker. You can also choose Create with editor and enter the original name, description, and instructions.
- After the scan completes, check that email-subject-line-optimizer appears in Installed. Type @ in a new chat, select the skill, and use the fictional example on this page to check the output.
Example task
A fictional library is reminding registered readers about a free book club at 10 a.m. Saturday. Write one subject that leads with time and one that leads with the event. Describe the comparison.What to check
Both subjects retain the event and Saturday. Keep the body fixed, specify the measure and evaluation window, and label small samples as exploratory.
Original SKILL.md on GitHub · Updated
Frequently asked question
Can the wording alone predict open rate?
It can support a hypothesis. To estimate impact, provide comparable historical data with the same definition, then verify against the current test.