Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Img2threejs

ASecurity

Use when converting a static image into optimized Three.js/WebGL code from scratch — geometry, materials, lighting, interactive scene. Triggers on "imagem para 3D", "img2threejs", "image to threejs", "gerar threejs de imagem", "static image to interactive 3D", "webgl from image".

2 stars
0 votes
0 copies
0 views
Added 9/19/2026
ai-agentsjavascriptgojavagitperformance

Security Analysis

A100/100

Scanned 9/19/2026

Install to Claude Code

$npx -y skills add majinmagros/magros.ai-skills --skill img2threejs --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Img2threejs?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Img2threejs
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/majinmagros-img2threejs/badge)](https://www.skillsdirectory.com/skills/majinmagros-img2threejs)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: img2threejs
description: Use when converting a static image into optimized Three.js/WebGL code from scratch — geometry, materials, lighting, interactive scene. Triggers on "imagem para 3D", "img2threejs", "image to threejs", "gerar threejs de imagem", "static image to interactive 3D", "webgl from image".
metadata:
  origin: ECC
  source_docs:
    - https://github.com/mrdoob/three.js
    - https://context7.com/mrdoob/three.js
    - https://threejs.org/docs/
    - https://threejs.org/examples/
---

# img2threejs — Image to Three.js/WebGL Generator

Analisa uma **imagem estática** de um objeto/forma e gera **do zero** todo o código Three.js + WebGL/WebGPU para renderizar um modelo 3D interativo e otimizado no navegador.

## Quando usar (gatilhos concretos)

- "Transforme esta imagem em Three.js"
- "Gere código 3D a partir desta imagem"
- "Crie modelo 3D interativo baseado nesta foto/ilustração"
- Precisa de objeto 3D leve, procedural, sem carregar GLTF/GLB externo
- Quer controle total sobre geometria, materiais, shaders, performance

## Quando NÃO usar

- Carregar modelos 3D prontos (use `GLTFLoader`, `OBJLoader`, `USDZLoader`)
- Fotogrametria / reconstrução 3D realista de múltiplas fotos (use Meshroom, RealityCapture, Polycam)
- Geração de 3D por IA generativa (Meshy, Tripo, CSM, Rodin, Trellis, Hunyuan3D)
- Animações Lottie/SVG 2D (use `motion-design-skill` ou `lottie-web`)
- Vídeo para 3D / NeRF / Gaussian Splatting
- Site 3D completo por composição modular (use `threejs-scene-composer`)

## Pipeline (baseado no vídeo + docs Three.js oficiais)

### 1. Análise da imagem (input)
- Recebe: URL da imagem, base64, ou File object
- Identifica: formas geométricas primárias (cubos, esferas, cilindros, torus, planos), simetrias, cores dominantes, materiais (metal, plástico, vidro, emissivo), iluminação aparente, fundo
- **Limitação**: funciona melhor com objetos "suaves" (formas geométricas, produtos, ícones 3D) — rostos/orgânicos complexos geram geometria pesada/imperfeita

### 2. Geração de código Three.js (output)
Produz arquivo(s) `.js`/`.ts` contendo:

```javascript
// Estrutura padrão gerada
import * as THREE from 'three';
import { OrbitControls } from 'three/addons/controls/OrbitControls.js';

// 1. Scene, Camera, Renderer
const scene = new THREE.Scene();
const camera = new THREE.PerspectiveCamera(45, w/h, 0.1, 1000);
camera.position.set(0, 0, 5);
const renderer = new THREE.WebGLRenderer({ antialias: true, alpha: true });
renderer.setSize(w, h);
renderer.setPixelRatio(Math.min(window.devicePixelRatio, 2));
document.body.appendChild(renderer.domElement);

// 2. Controls (interatividade)
const controls = new OrbitControls(camera, renderer.domElement);
controls.enableDamping = true;

// 3. Lights (baseado na análise da imagem)
const ambient = new THREE.AmbientLight(0xffffff, 0.5);
const keyLight = new THREE.DirectionalLight(0xffffff, 1);
keyLight.position.set(5, 10, 7);
scene.add(ambient, keyLight);
```

## Foto-virando-objeto (Batch 17b, #58)

Fluxo validado em video (Campelo `rvJz-dmQO9Q`): foto 2D (celular ou
busca) -> repo gerador -> objeto 3D procedural -> pagina interativa
(mouse + touch, undo de movimento, contador, sons). Nao exige agente
especifico — qualquer modelo que entenda o repo reproduz. Use para
vitrines interativas (cubo magico, teclado 3D com input real). Feche o
teste no mobile: scroll horizontal do desktop vira vertical no celular.

Attribution

majinmagrosmajinmagros
View sourceMore from majinmagros →
SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Your tool, in front of Claude Code builders.

3 founder slots · $299/mo · GSC-verified traffic · sponsors can never buy grades.

See placements

Related Skills

Caveman

Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.

1023331 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3331 votes

catchup

Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.

611 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →