#4343rd of 53 in Skills, plugins and rules
img2threejs
Agent skill that rebuilds an image's object as procedural Three.js code
Live demo ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 18.1k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- Python
25 on 14 Jul 202618,114 on 13 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
img2threejs is a skill for Claude Code, Codex and OpenCode that takes one reference image and generates a TypeScript THREE.Group factory recreating the object from primitives, procedural shaders and generated geometry. It runs a staged pipeline from blockout to optimization, with vision review and Python gate scripts, and outputs pivots, sockets and colliders for animation. A CLI installs it into detected agent hosts.
Who it is for: Three.js developers using coding agents to turn reference images into models
Strengths
- Output is code only: no mesh files or downloaded assets, so models are small and editable
- Generated models include pivots, sockets and colliders for animation
- Quality gates block generation until a detail inventory is complete
- Live gallery with source for each demo model
Weaknesses
- Needs a host agent with vision (Claude Code, Codex or OpenCode); model cost is not stated
- Single image cannot guarantee likeness; unseen areas are low-confidence
- Several gallery demos are still marked placeholder rather than final
- Requires Node.js 18+, Git and Python 3.10+; plugins need a separate CLI
What it needs
- no GPU
- Needs Node.js >= 18, Git, Python >= 3.10, Three.js, Claude Code, Codex or OpenCode
- Models: Claude Code, Codex, OpenCode, Hermes
Also in Skills, plugins and rules
See all 53| Rank | Project | Score |
|---|---|---|
| 1 | skillsAgent skills for planning, TDD, debugging and code review | 94 out of 100 |
| 2 | eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses | 93 out of 100 |
| 3 | cavemanCuts token use in coding agents with terse replies and compressed inputs | 93 out of 100 |
| #4 | ponytailSkill prompt that makes coding agents write less code and add tests | 91 out of 100 |
| #5 | ui-ux-pro-max-skillDesign-system skill that gives coding agents searchable UI styles, palettes and fonts | 90 out of 100 |