Thumbnail Concept Skill for ChatGPT: Write a Visual Brief and A/B Test
Turn a video's subject, audience, and platform into a thumbnail brief. Specify subject placement, color contrast, short text, small-screen legibility, and a test that changes one variable.
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/video-creator-workflow/.claude/skills/thumbnail-concept-generator/SKILL.md from the pinned GitHub source. Keep the name, description, and instructions for thumbnail-concept-generator 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 thumbnail-concept-generator 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 YouTube tutorial fixes a loose bookshelf shelf in three steps. You have a shelf close-up and an after photo. Request two 16:9 concepts with the same layout and different overlay text only.What to check
Each brief should give a clear focal point and short, readable text that matches the tutorial. The A/B test should change text only and compare impression click-through under similar traffic.
Original SKILL.md on GitHub · Updated
Frequently asked question
Does it produce a PNG?
The workflow delivers a visual brief. Use a design tool to create the image from the composition, colors, and text, then preview it at thumbnail size.