Turn a Winning UGC Ad Into Your Own Product's Version on Any Video Provider — workflow skill for ads & UGC

For AI agents: find the right skill in one call — curl -s "https://varg.ai/how-to/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://varg.ai/how-to/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. From a terminal: curl -fsSL https://varg.ai/install | sh installs the vargai CLI (https://varg.ai/how-to/cli.md): vargai search and vargai install <slug> with no key, every varg model after vargai login.

Copies the beat structure of a winning TikTok or Meta UGC ad and re-renders it with your assets on Arcads, with Dreamina and Runway adapters.

What it does

Drop a reference ad plus your product or app assets into one of five template folders (talking head, product unboxing, faceless lifestyle, app promo, extend and stitch); Claude Code analyzes the reference, checks the active provider's capabilities, writes an adapted prompt and runs generation after you approve it. Providers are JSON specs swapped with one line in .env, and the skill refuses cleanly when a provider cannot do what was asked. Arcads is the default and the only provider verified end to end; Dreamina and Runway specs still have TODOs. Needs Python 3.8+ and an API key for at least one provider; based on the reference-analysis logic of claude-arcads.

Use when

Install

More ads & UGC 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.