thumbnail-concepts
Installation
SKILL.md
Thumbnail Concepts
Overview
Three thumbnail concepts for one video. A strong thumbnail joins what the viewer already cares about with what is new in this video. So study 50 or more thumbnails across both, and combine one pattern from each into every concept.
Without TubeLab: no outlier ratio and no Content Authenticity filter. You study the most-viewed thumbnails, which show channel size and low-effort bait, not what earned the click.
Workflow
- Clarify scope only if needed. Split the video into two plain lines: its unique angle and the familiar problem. With only a niche and no video, search the niche from two angles instead. If the user wants a title too, follow
title-formulasfirst and design for the chosen title, so the thumbnail shows what the title leaves out. - Run two outlier searches: one for videos with the unique angle, wherever they are, and one for videos on the familiar problem. Ask each for 40 results, the largest page, which costs the same as 20. Add outliers already found in this conversation, if they meet the quality floor in Common Pitfalls.
- View every thumbnail, 50 or more in all. Numbered contact sheets are the quickest way. Leave out the user's own video, and say if a thumbnail fails to load.
- Keep only the thumbnails worth analysing, up to six in each set. A keeper has a clear idea you could reuse: a composition, a prop, a gesture, a word or a visual trick. Drop the plain ones, such as a face beside the title's words, a stock photo or a podcast frame. View each keeper again on its own, at a larger size.
- Before designing anything, write down what works in each set of keepers. Note compositions (how the frame is arranged, the shot, where people and objects sit) and details that pull the eye. Count how many thumbnails in that set use each pattern.
- Look at the channel's recent thumbnails and note what to keep.
- Build each concept from one unique-angle pattern and one familiar-problem pattern. Generate the images if you can, or else write one prompt per concept.