cinetic: directed launch films from code — workflow skill for launch videos

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.

Makes the agent direct a short film: three concepts first, a plan drawn from 273 measured techniques, one beat grid for picture and sound, then pixel and audio-

What it does

pick.py draws a film plan weighted for format and energy so two films do not share the same moves; look comes from three personality words; copy arrives in fragments; timeline.ts drives picture, soundtrack and QA; true motion blur, BT.709, contact sheets, critic passes and a linter of hard bans against the generated look. Remotion by default or HyperFrames. Sound from the earshot kit (already in catalog).

Use when

Not for

Install

Models it drives: remotion, hyperframes

Example output

https://raw.githubusercontent.com/Leonxlnx/cinetic/media/quire-streaks-vertical.mp4 — A vertical launch teaser the skill rendered (repo media branch) (credit: Leon (Leonxlnx) (README), https://github.com/Leonxlnx/cinetic)

More launch videos 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.