Frame-Accurate Square Launch Clips in Remotion — 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.

Turn real product screens into a 20 s 1080x1080 launch clip in Remotion, built in gated stages with every event pinned to a frame number.

What it does

Seven gated steps: measure a reference clip in frames with ffmpeg, write a BRIEF.md that pins every coordinate, colour and event frame, build only frames 0-119 and stop for review, check key stills, fix each defect with a four-field prompt (Location, Observed, Change, What stays fixed), place click and hit sounds on the visible press and reveal frames, export and confirm with ffprobe. Each shot follows start state, cursor to action, press, reveal, readable hold. Also maps 20 open-source repos (Penpot, Lottie, GSAP, Three.js, R3F) to the stage where each helps.

Use when

Install

Example output

https://github.com/JuniverseLi/motion-studio-skill/raw/main/assets/launch.gif — example (credit: JuniverseLi)

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.