Clay Parable Short — trending format for animation & motion graphics

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.

An old parable retold in 60–80 s as a handmade-looking clay stop-motion: fingerprints, miniature sets, choppy motion, a calm narrator.

What it does

A short moral story (a Zen parable, a fable, a folk tale) retold with one modern twist and narrated line by line, one shot per sentence. It looks like weeks of stop-motion: tiny clay figures with fingerprints on their faces, miniature handmade sets, slightly awkward movement on twos, and close foley for every footstep and squish. The page that made it popular has 233k followers from 52 posts, with reels at 37.4M, 10.5M and 4.8M views, and breakdowns of how to copy it for brands drew hundreds of bookmarks on X in the last week. What agents still get wrong: generated clay comes out too smooth and turns into generic 3D, motion comes out fluid instead of choppy, and characters drift between shots. The route below locks the characters with sheets first and asks for the flaws on purpose.

Status

A format people ask for that has no dedicated skill yet. Make it with the skills on the use-case pages below, or with varg directly.

Example: https://x.com/theodorsan/status/2116199275105275984

How an agent would make it: Claude retells a public-domain parable with one modern twist, one sentence per shot (12–18 shots, 60–80 s) → clay character sheets on gpt_image_2_5 asking for the flaws: thumbprints, uneven surfaces, matte plasticine, visible seams → one still per line on nano_banana_2_1 with the sheets as references, on a miniature handmade set → each still animated 3–6 s on seedance_2_5 or kling_v4: 'stop-motion on twos, slightly choppy, no motion blur, locked camera' → eleven_v4 narrator, close foley (footsteps, squish, drops) and burned yellow captions in hyperframes → 9:16

Models it drives: gpt_image_2_5, nano_banana_2_1, seedance_2_5, kling_v4, eleven_v4, hyperframes

Example output

https://video.twimg.com/amplify_video/2116198520277397504/vid/avc1/720x1280/t5Aw9ZsNRqoTwhF1.mp4 — The clayrified_ reel shown in the breakdown: two monks meet a woman stuck at a muddy crossing, told in clay with captions (credit: @theodorsan, https://x.com/theodorsan/status/2116199275105275984)

More animation & motion graphics 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.