Douyin Cover Builder — prompt skill for images & thumbnails

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the how-to page.

Writes image-model prompts for Douyin covers: bold title, highlighted keywords, your face bottom right

What it does

From a topic, optional key points, the pose or mood you want, and optionally your photo, it writes a final prompt for an image model plus a short art direction note. Rules cover a fixed layout (title on top, you bottom right, one hero metaphor bottom left), keywords in a contrast colour on a slight upward arc, and a background palette chosen by topic. It defaults to strict 3:4 (1080×1440) and gives a pixel check for the generated file. A prompt template only; it does not generate the image itself.

Use when

Not for

Install

More images & thumbnails skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.