Teardown by Elvar — workflow skill for 3D scenes

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.

One reference picture in, a 3D machine you can take apart out: three.js simulator, live gauges, 60 fps film.

What it does

A Claude Code skill that builds a real machine (an engine, a landing gear, a walking linkage, a robot) as one offline HTML page: the machine runs in the middle, every gauge and chart reads the same model that poses the parts, a button opens each subsystem, and when nobody touches it the page tours itself. The same code records the tour frame by frame to a 60 fps MP4 with a procedural score mastered to -14 LUFS. Its rules: start from one reference picture, write the model as math from real numbers first, drive everything from one input, review stills before any video. Ships 3 machines (a V8, a Cessna 337 landing gear, a Strandbeest). The launch post on X (Oct 30, 2026) drew 3,485 likes, 3,917 bookmarks and 255k views, and its how-to article 665k views; 302 GitHub stars in its first day.

Use when

Not for

Install

Models it drives: claude_opus_5_5

Example output

https://s3.varg.ai/files/4325c578-378d-4c43-ae53-3cc3218df1ea/file_7f71a044d428.mp4 — The Telson SC-8 robotic scorpion from the repo README: claws open, tail strikes, panels read the pose. The full 5.5 s loop, GIF re-encoded to MP4. (credit: Elvar (teardown README), https://github.com/elvarofficial/teardown#readme)

More 3D scenes 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.