youtube-thumbnail-design Skill (inference.sh) for Claude Code: What It Does and How to Install It

Guides Claude through YouTube thumbnail design: size specs, safe zones, contrast, text and face rules, and A/B variants made with image models.

Installs: 58.9K; on skills.sh
Stars: 17; on GitHub
Updated: Aug 2026; last repo commit

This skill gives Claude rules for YouTube thumbnails and prompts to generate them. It states the specs (1280 x 720 minimum, 16:9, under 2 MB), a 120px legibility test, safe zones for the timestamp and chapter markers, and color, text and face-expression rules.

Images come from falai/flux-dev-lora and bytedance/seedream-4-5, run through the belt CLI. It needs belt installed and signed in.

Good for

YouTube creators who want better thumbnail briefs
Marketers and designers who make video cover images

Install youtube-thumbnail-design

Claude Code

Copy this prompt.

Install the youtube-thumbnail-design skill in Claude Code. Run this command:

npx skills add https://github.com/inference-sh/skills --skill youtube-thumbnail-design

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

Pick one route for the skill, then install the belt CLI with one of the belt routes and run belt login. Every command in SKILL.md is a belt app run call, and its allowed-tools line is Bash(belt *), so the skill does nothing without belt. The folder holds 1 file, SKILL.md (repo tree). It runs belt in a shell, so there is no Claude app upload route.

Built from the package data we hold. Not yet tested by us.

What's in the skill

When it loads

YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image

Sections in SKILL.md

Quick Start
Specifications
The 120px Test
Safe Zones
Color Strategy
High-Contrast Pairs That Work
Color Rules
Text on Thumbnails
When to Use Text
When NOT to Use Text
Text Rules
Face Expression Psychology
Face Composition Rules
Thumbnail Patterns by Content Type
Tutorial / How-To
Before/After

Key facts

Author: inference.sh (owner of the repo; plugin.json lists inference.sh as author)
License: MIT per plugin.json and the README badge; the repo has no LICENSE file
Installs on skills.sh (101-skills/superpowers listing): 58,882 (Nov 2, 2026)
GitHub stars: 797 for the whole repo (Nov 2, 2026)
Last repo commit: Oct 15, 2026
Audits on skills.sh (101-skills/superpowers listing): Gen Agent Trust Hub: pass, Socket: warn, Snyk: pass
What it includes: 1 file: SKILL.md (from the repo tree)
Needs: The inference.sh belt CLI, signed in with belt login
Allowed tools: Bash(belt *)

What it includes

belt app run falai/flux-dev-lora at 1280 by 720
The Quick Start makes one thumbnail from a style prompt.
Try: “Make a thumbnail for my video on home espresso mistakes”
Runs code · Generate a thumbnail
Prompts with flux-dev-lora and bytedance/seedream-4-5
Two example prompts for faces that fill 30 to 50 percent of the frame.
Runs code · Face-forward and face-looking-at-subject
1280 x 720 minimum, 1920 x 1080 recommended, 2 MB, JPG, GIF or PNG
A short spec table.
Specifications
Check legibility at 120px wide; keep corners clear of timestamp and chapters
Avoid bottom-right and bottom-left for key elements.
120px test and safe zones
Up to 3 colors, high contrast, text of at most 6 words
Includes six color pairs and when to skip text.
Color and text rules
Tutorial, before/after, review and listicle prompts
Four ready prompts for common video types.
Runs code · Patterns by content type
Change one variable at a time and generate variants A and B
Variants run with --no-wait.
Runs code · A/B testing
A 10-item checklist to run before upload
Counted from the SKILL.md checklist.
Thumbnail checklist

From the official docs

Permissions

Medium risk

This skill makes your agent run belt app run commands that send your prompts and files to inference.sh and use credits on your account. Check the price of an app with belt app pricing before you start a large batch.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Each run uses inference.sh credits
SKILL.md does not list a price for the apps it calls. The belt README shows belt balance to check credits and belt app pricing to see the cost formula before a run. github.com
Your prompts and files go to inference.sh
Every belt app run sends its input to an inference.sh app. The belt README says local file paths in an input are uploaded by the CLI. github.com
You must install the belt CLI first
The belt README gives a download-and-review install script, Homebrew, npm and Scoop. cli-install.md in the repo says the installer downloads a binary and checks its SHA-256 checksum. The belt skill named in SKILL.md can also run brew install and npm install -g. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	SKILL.md describes no read-only mode.
Talks to	inference.sh (belt app run calls). cli.inference.sh and dist.inference.sh (belt installer)
Sign-in and keys	Run belt login to sign in to inference.sh. SKILL.md does not say where belt keeps the login.
Scopes	Runs belt app run commands in your shell (allowed-tools: Bash(belt *)) Uploads the inputs you give it, including local files, to inference.sh

Questions

What does the youtube-thumbnail-design skill do?

It teaches Claude how to design a YouTube thumbnail and gives prompts to generate one. It covers size specs, safe zones, a 120px test, color and text rules, face expressions, patterns by video type and A/B testing.

How do I install it?

Use the install box at the top of this page for the skill. You also need the belt CLI from inference.sh, installed with one of the belt routes in the box, and a belt login. There is no Claude app upload route because the skill runs belt in a shell.

Does it need an account or API key?

It needs an inference.sh sign-in through belt login. SKILL.md names no separate API key. The belt README shows belt balance for credits and belt app pricing for the cost of an app.

Is it safe?

It runs belt app run commands through your shell. Each run sends your prompt and any files or URLs you give it to inference.sh and uses credits. The belt CLI has to be installed first, so read its install steps before you run them.

Is there another copy of this skill?

skills.sh also lists this skill under 101-skills/superpowers, a repo whose plugin.json names inference.sh as author and inference-sh/skills as the repository. This page links to inference-sh/skills, the repo the plugin.json points to.

Who publishes this skill?

inference.sh, in its own repo github.com/inference-sh/skills. The repo's plugin.json lists inference.sh as author and https://inference.sh as homepage.

Will it publish thumbnails to YouTube?

SKILL.md defines no upload step. It generates images with belt app run.

Which other skills does it point to?

Its Related Skills section lists ai-image-generation, image-upscaling and prompt-engineering from inference-sh/skills. They are optional.

Information

updated Nov 2, 2026

Repository: inference-sh/skills
Folder: guides/design/youtube-thumbnail-design

inference-sh/skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 6

youtube-thumbnail-design SKILL.md · github.com
belt CLI README · github.com
cli-install.md · github.com
README · github.com
plugin.json · github.com
belt skill SKILL.md · github.com