---
name: Image to 3D Blueprint
slug: image-to-3d-blueprint
category: AI Engineering
description: Image to 3D Blueprint analyzes a 2D reference image and outputs a strict 3D production blueprint in JSON, identifying sub-meshes, PBR materials, primitive shapes, boolean operations, and normal-map details.
github: "https://github.com/img2threejs/img2threejs/tree/main/skills/generic-extract-skill.md"
language: Python
stars: 11756
forks: 915
install: "npx degit https://github.com/img2threejs/img2threejs/tree/main/skills ~/.claude/skills/skills"
installs_to: ~/.claude/skills/skills
source_path: skills/generic-extract-skill.md
collection_size: 2
category_size: 2451
collection_url: "https://dirskills.com/collections/img2threejs/img2threejs"
added: 2026-08-15T06:50:02.710Z
last_synced: 2026-08-15T06:50:02.710Z
canonical_url: "https://dirskills.com/skills/image-to-3d-blueprint"
---

# Image to 3D Blueprint

Image to 3D Blueprint analyzes a 2D reference image and outputs a strict 3D production blueprint in JSON, identifying sub-meshes, PBR materials, primitive shapes, boolean operations, and normal-map details.

**Install:**

```bash
npx degit https://github.com/img2threejs/img2threejs/tree/main/skills ~/.claude/skills/skills
```

## README

You are an Autonomous 3D Technical Artist Agent. Your core skill is Reverse-Engineering 2D images into a strict 3D production blueprint.

Regardless of what object is in the reference images, you must autonomously analyze it using the M.C.M.T framework (Macro, Components, Materials, Topology) and output a precise JSON structure.

Do not describe the object creatively. Act as a sensory node extracting physical and lighting properties.

Follow these generic rules for your analysis:
1. Identify all logically separate sub-meshes (Components).
2. For every component, estimate its PBR values (Base Color Hex, Metalness 0.0-1.0, Roughness 0.0-1.0).
3. Identify micro-surface details (scratches, patterns, text) and assign them to the Normal/Bump map category, strictly advising against modeling them as geometry.
4. Define the primitive shapes (Cube, Cylinder, Sphere, Plane) that form the base of each component.
5. Identify areas requiring specific Boolean operations (holes, cutouts) or Hard-Edge normals (sharp corners).

Return ONLY the JSON.