Skip to content
Agentmart
Submit a tool

3d-modeler

Generates 3D interior models from photos and injects them into Mapbox GL JS map instances.

Skill by AQaddora

IndexedMIT★ 3
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/aqaddora-3d-modeler

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Generates 3D interior models from photos and injects them into Mapbox GL JS map instances.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Node.js package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/3d-modeler

What's inside

Skill name
3d-modeler
Description
Generates 3D interior models from photos and injects them into Mapbox GL JS map instances.
License
MIT
Instructions
15 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (3)

  • SKILL.md
  • mapboxInjector.js · scripts/
  • photoTo3D.js · scripts/

SKILL.md (first lines)

# 3D Modeler Skill

This skill allows agents to convert photographs of interiors into 3D models (GLB/GLTF) and inject them into web-based Mapbox 3D styles using Three.js and the Threebox plugin.

## Capabilities
1. **Photo-to-3D Generation**: Uses `photoTo3D.js` to call 3D reconstruction APIs (e.g., Luma AI / Polycam) to process an image and return a URL to a GLB file.
2. **Mapbox Injection Prep**: Uses `mapboxInjector.js` to prepare a GLB file for Mapbox insertion, calculating the necessary MercatorCoordinates and Three.js scale/rotation matrices to align the interior model perfectly with the real-world map.

## Usage
When a user uploads a photo of a room and asks to place it on the map, trigger this skill:
1. Pass the image URL to `photoTo3D.js`. Wait for the 3D generation to complete.
2. Pass the resulting GLB URL and target LngLat coordinates to `mapboxInjector.js` to get the integration payload.
3. Send the payload back to the frontend to render the model inside the Mapbox custom layer.

From AQaddora/pure-skill-suite, MIT.

More from AQaddora/pure-skill-suite

Signals

Stars
3
Forks
0
Open issues
0
Last commit (this folder)
Jun 23, 2026 (4 months ago)
Last release
May 31, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/AQaddora/pure-skill-suite
Website
aqaddoura.com/blog/pure
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from AQaddora

Cite this page

3d-modeler skill. Agent Mart. https://agentmart.dev/skills/aqaddora-3d-modeler (last updated 2026-10-24)