Thumbnail A/B Generator
Generate 5 thumbnail variants for a single video using a brand template and a topic prompt — ready for YouTube multi-variant testing.
🧠 Why it works
YouTube rewards multi-variant thumbnail testing but most creators only make one. Generating five variants that each emphasize a different angle (question, number, emotion, curiosity gap, counter-intuitive claim) gives you something to actually test instead of 'this is my thumbnail.'
⚙️ How it works
- Load the brand template — identify the subject slot and text slot coordinates. 2. Generate 5 headline angles from the topic via LLM, each under 5 words and tuned for mobile legibility. 3. For each variant, composite the subject image into the subject slot, render the headline at a legibility-checked font size, and apply an accent color from a rotating palette. 4. Run a quick legibility check — headlines must be readable at 200x120 preview size. 5. Emit the 5 variants as PNG + a caption with the angle rationale for each.
Description
Input: a brand template (PNG with transparent spots for subject and text), a video topic, and an optional subject image. Output: 5 thumbnail variants with different headline angles, color accents, and subject placements — sized to 1280x720 and optimized for mobile-scale legibility.
Install this skill
A Claude skill is a skill.md file with YAML frontmatter and a markdown body.
Drop the file into your tool of choice — or pick a different format if you use Cursor, Windsurf, Copilot, or something else.
mkdir -p ~/.claude/skills/thumbnail-a-b-generator \
&& curl -L https://aidiveforge.com/skill/thumbnail-a-b-generator.skill-md \
-o ~/.claude/skills/thumbnail-a-b-generator/skill.md
Save to ~/.claude/skills/thumbnail-a-b-generator/skill.md
Recommended Use
Sign in to suggestTools and workflow packs this skill pairs well with. Forge picks are auto-generated from category + capability signals; Community picks are added by people who've used the pairing.
Forge Auto-recommended matches
Tools
-
Anime AI Studio enhance 32%
Why: category partial · caps 0/0 · domain design
-
Cleanup.Pictures enhance 32%
Why: category partial · caps 0/0 · domain design
-
Krea 2 enhance 32%
Why: category partial · caps 0/0 · domain design
-
PixAI Edit Pro enhance 32%
Why: category partial · caps 0/0 · domain design
-
doubao.photos enhance 32%
Why: category partial · caps 0/0 · domain design
-
Midjourney enhance 32%
Why: category partial · caps 0/0 · domain design
-
DALL-E 3 enhance 32%
Why: category partial · caps 0/0 · domain design
-
Stable Diffusion enhance 32%
Why: category partial · caps 0/0 · domain design
-
Leonardo AI enhance 32%
Why: category partial · caps 0/0 · domain design
-
Ideogram enhance 32%
Why: category partial · caps 0/0 · domain design
-
Flux enhance 32%
Why: category partial · caps 0/0 · domain design
Report compatibility
Tell the community which tool you used this skill with, and whether it worked.
Suggest a pairing
Recommend a tool or workflow pack that this skill works well with. Up to 5 recommendations per day.