Replicate Prompt Videos — prompt skill for prompts by model

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 use case 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 use-case page.

Prompt video models like a director: shots, camera motion, four audio layers, dialogue, time-coded beats.

What it does

Prompting techniques for video generation models on Replicate: layered scene description, shot types, camera motion and position, lens language, an escalation pattern, prompting all four audio layers, dialogue syntax that avoids burned-in subtitles, pronunciation, and multi-shot or time-coded prompts. Like its image sibling, it picks the model through the API first.

Use when

Install

Models it drives: veo_3_1, seedance_2, wan-2.2

Example output

https://skills.varg.ai/previews/replicate-prompt-videos.mp4 — 'Detailed prompt' result from Replicate's 'How to prompt Veo 3' guide: a directed noir scene (a man answers a ringing payphone in a green-lit alley, cutting to close-ups); audio not kept (credit: Replicate, https://replicate.com/blog/using-and-prompting-veo-3)

Used for

More prompts by model skills