thumbnail-ab-testerlisted
Install: claude install-skill rahulcommercial/claude-code-for-content-creators
# Thumbnail A/B Tester
Generate 3-5 thumbnail concepts, score them, ship the winner.
## When to use
- User has a video and wants 3+ thumbnail variants.
- User wants critique on an existing thumbnail.
- User wants to know which still frame from a clip is strongest.
## Variant generation strategy
For one clip, produce variants across these axes:
| Axis | Option A | Option B | Option C |
|---|---|---|---|
| **Frame** | Hook moment (start) | Climax (mid) | Payoff (end) |
| **Text** | One word | Short phrase | None (visual only) |
| **Face** | Tight crop (eyes visible) | Medium shot | Object only |
| **Contrast** | Dark bg + bright subject | Inverted | High saturation |
Pick one option per axis → 3-5 thumbnails total. Don't generate 30 — too much noise.
## Scoring rubric (0-10 each, sum / 40)
| Factor | What to check |
|---|---|
| **Hook clarity** | Can a viewer read the *story* in < 1 sec? |
| **Face / emotion** | If a face: is the emotion strong & specific? |
| **Text legibility** | Readable at 320px wide (IG feed size)? |
| **Contrast** | Subject pops from background? |
## Heuristics (the boring stuff that matters)
- Faces with **visible eyes** outperform face-from-behind ~2:1 on IG.
- Bright single-colour backgrounds (yellow, red) beat busy stills.
- Text on thumbnail: ≤ 4 words. Beyond that, no one reads.
- Avoid feed-camouflage: if your thumbnail looks like 5 others on the explore grid, it loses.
## When to NOT use a thumbnail
- IG Reels cover image is shown on