ThumbLabv1.0.0

Seven layouts — a cutout of you with a clean outline, split photo, tilted screenshot, versus, before and after, big number and bold text — with highlighted words, badges, arrows and rings.

See what you can make

Made with this SkillUpload-ready thumbnail variants with feed previews

Seven variants from two channels

Open full example

What you get

Upload-ready thumbnail variants with feed previews

What you can make

  • Seven layouts — a cutout of you with a clean outline, split photo, tilted screenshot, versus, before and after, big number and bold text — with highlighted words, badges, arrows and rings.
  • A/B/C variants rendered as 1280 × 720 JPEGs under the 2 MB upload limit, ready for a thumbnail test.
  • Every variant shown in light and dark video feeds at 360, 246, 168 and 120 px, and reviewed for text under the video length, small headlines, word count and headlines that repeat the title.
Explore delivered files5 groups
  • thumbnails/A-….jpg per variant, 1280 × 720, under 2 MB
  • feed-light.png and feed-dark.png at 360, 246, 168 and 120 px
  • sheet.png with every variant
  • review.md with fixes per variant and how to run a test
  • Offline studio to edit text, layouts and order

Good fit

YouTubers, course creators and marketers publishing videos who want thumbnails that are readable in the feed and a few variants to test.

Know the limits

Composes the photos and screenshots you provide. It does not generate faces or photos, remove backgrounds, upscale images or upload; Chinese, Japanese and Korean text needs your own font file.

About this skill

Your agent turns the moment your video is about into two or three thumbnail ideas, each with a 2–5 word headline and a highlighted key word, and lays them out in seven layouts: a cutout of you with a clean outline, a split photo, a tilted screenshot, versus, before and after, a big number or bold text, with badges, arrows and rings. Six punchy backgrounds, any color or a dimmed photo. Renders 1280×720 JPEGs under the 2 MB upload limit, a sheet of all variants and light and dark feed previews at 360, 246, 168 and 120 px, and reviews each variant for text under the video length, headlines too small on phones, too many words and headlines that repeat the title. Includes an offline studio to edit text, layouts and order. Requires Node.js 20+. Chinese, Japanese and Korean text needs your own font file.

FROM PACKAGE TO FIRST RESULT

Your first result, with your agent

Choose a starting point, add the content you already have, then let your agent check the setup and create one result.

View example result

Purchase access is required. Unzip the package into the project folder below, or let your agent follow the installation guide. .agents/skills/thumblab

Your project name, audience and the content or images you already have are enough to start. Your agent will ask for anything essential that is missing.

3. Let your agent guide the first result

Package location: .agents/skills/thumblab

Use ThumbLab to make three thumbnail variants for my new video from my cutout photo and one screenshot, with a short headline on each. Start from examples/buildsmall.json.

Use a new output folder and preserve existing files. Inspect the actual deliverables (thumbnails/A-….jpg per variant, 1280 × 720, under 2 MB, feed-light.png and feed-dark.png at 360, 246, 168 and 120 px, sheet.png with every variant), open the visual result and explain failed checks. An incomplete dependency check is not a successful result. Ask before paid services and do not publish automatically.
Before calling it done
  • Dependencies checked before rendering
  • Actual files open and work with your content
  • Editable source saved in a new folder
Made your first result? Share your experience →
Installation options & technical requirements

Start with your agent

Give this request to Claude Code, Codex or Cursor. Your agent can collect the missing details and guide your first result.

Use ThumbLab to make three thumbnail variants for my new video from my cutout photo and one screenshot, with a short headline on each. Start from examples/buildsmall.json.

Purchase access is required to install the package. Technical commands are available below when you need them.

US$4.99 · MIT licenseNode.js 20+ · no API keyNo API key or paid provider
  1. 01

    Choose your agent

    These steps use a project folder. Open the project in your agent and run terminal commands from its root.

    Codex directory guide

    Package folder .agents/skills/thumblab

  2. 02

    Add the package

    Download and unzip the package into the folder above. Keep all its files together, with SKILL.md directly inside that folder.

    Downloads require a verified account and purchase access. Choose a new folder if this Skill is already installed.

  3. 03

    Run the included sample

    Manual sample commands and technical details

    Read SKILL.md, review the generator and check its runtime requirements before running:

    cd .agents/skills/thumblab
    npm install
    node scripts/render.mjs --input examples/buildsmall.json --output ./thumbnails
    Your first result

    Open feed-light.png and feed-dark.png first: can you tell what each video is about at 168 px? Then read review.md, fix what it flags, and upload up to three variants to test.

    Build Small, Leaf Lab and the presenter are fictional; the illustrations were drawn for these examples, and the screenshot is a real IconForge preview. ThumbLab composes the photos and screenshots you provide; it does not generate faces or photos, remove backgrounds or upload. The feed preview is a neutral mock-up. Chinese, Japanese or Korean text needs a font file passed with --font.

    If thumbnails already exists, change the output to ./thumbnails-2. Existing files are never overwritten.

    Prefer to ask your agent?

    Use ThumbLab to make thumbnails for my video. Ask me for the title, what happens in the video, and my cutout photo or screenshots. Suggest two or three short headlines that add to the title, build each as a variant, show me the feed previews at phone and desktop sizes, fix what the review flags, then render the files.

Reviews

Share your first result

Tried this workflow? Help others decide with an honest review.

Before you choose this Skill

How do I get ThumbLab?

The listed individual package price is USD 4.99. Premium downloads require a confirmed purchase or active membership. Your agent subscription, model access and external provider credits are separate.

Which agents can use this skill?

This release lists Codex, Claude Code, Cursor as intended installation hosts. Check the package’s dependencies and permissions before running it. These labels do not certify that every workflow has been tested in every agent.

What files can this workflow generate?

The documented 1.0.0 workflow lists: thumbnails/A-….jpg per variant, 1280 × 720, under 2 MB; feed-light.png and feed-dark.png at 360, 246, 168 and 120 px; sheet.png with every variant; review.md with fixes per variant and how to run a test; Offline studio to edit text, layouts and order. Some files or exports are optional; follow the package’s setup and inspect the delivered result.

What should I check before using the result?

Build Small, Leaf Lab and the presenter are fictional; the illustrations were drawn for these examples, and the screenshot is a real IconForge preview. ThumbLab composes the photos and screenshots you provide; it does not generate faces or photos, remove backgrounds or upload. The feed preview is a neutral mock-up. Chinese, Japanese or Korean text needs a font file passed with --font.

$4.99One-time purchase