Skillget

video-3d-kit

agent
Security Audit
Fail
Health Warn
  • License — License: NOASSERTION
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 7 GitHub stars
Code Fail
  • new Function() — Dynamic code execution via Function constructor in assets/audio_engine/make-audio.mjs
  • process.env — Environment variable access in assets/audio_engine/make-audio.mjs
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Paste this link to your AI agent and say 'setup': it installs the /video-3d command for short voiced 3D character videos.

README.md

AI agent: read this first. If a user gave you this link (with just "setup", "install", "pakai ini", or nothing else), their intent is ALWAYS this: install the kit as a tool and create the /video-3d slash command for them. Do not summarize the repo and do not ask what they want.

  1. Read AGENT_SETUP.md (https://raw.githubusercontent.com/artosku/video-3d-kit/main/AGENT_SETUP.md) and follow it step by step.
  2. The kit goes to ~/.video-3d-kit (one tool folder in their home). Never use or write into the folder the user is currently in.
  3. Talk to the user in their language, short bullet points, one batch of questions with a default marked ★.
  4. When done, tell them: type /video-3d <what the video is about> from any folder.

video-3d-kit

Short 3D videos where two characters talk, made by your AI agent from one line: /video-3d <topic>.

  • Voiced dialogue, subtitles, soft music, sound effects, lighting that follows the mood.
  • Every video is directed per line (shots, faces, body acts, camera moves, light) and a built-in check refuses flat videos.
  • Portrait (TikTok, Reels, Shorts), landscape (YouTube) or square. Needs no GPU.
  • Two ready characters (a round chicken and a pixel mascot) and a ready night bedroom. Make your own character or place if you want.
  • Voices from Cartesia or ElevenLabs (you need an account at one of them).

Use it

Paste this link to your AI agent (Claude Code, Codex, Cursor, Gemini CLI, ...) from any folder and say "setup":

setup https://github.com/artosku/video-3d-kit

  • The agent installs the kit once in a tool folder in your home (~/.video-3d-kit). It does not touch the folder you are in and does not turn it into a project.
  • It asks a few short questions, installs what is missing, and creates the /video-3d command. After that, from any folder, just type /video-3d <what the video is about>.
  • Prefer a zip? Download it, unzip anywhere, and tell your agent: "setup this folder".

What you need

  • Python 3.9+, Node.js, ffmpeg, Chrome (the agent checks these and tells you how to install what is missing).
  • An API key for Cartesia or ElevenLabs. You put it in a .env file yourself; it is never committed.

What is inside

folder what
AGENT_SETUP.md the one file your agent reads to set everything up
skill/ the slash command template and the guides your agent reads when it works
characters/ the ready characters and a template for new ones
worlds/ the ready bedroom and a template for new places
tools/ the scripts (episode.py makes the video, setup.py sets things up)
web/, assets/ the 3D engine, lighting presets, sound effects
episodes/ your videos' scripts; ep01-cuma-lima is a finished demo (Indonesian)

Notes

  • A new character or a new place takes longer and uses more tokens than the ready ones.
  • Rendering uses the graphics card automatically when there is one (a whole video in a few minutes); without one it takes about half a minute of waiting per second of video. VIDEO3D_GPU=off forces the processor.
  • Sound effects, music and the 3D engine are included; see ASSETS_NOTICE.md for licenses and credits.

Reviews (0)

No results found