cad-skill  by flowful-ai

AI-powered parametric 3D model generation

Created 5 months ago
430 stars

Top 68.3% on SourcePulse

GitHubView on GitHub
Project Summary

This project provides a Claude Code skill for generating parametric 3D-printable models using CadQuery. It empowers users to describe physical objects in natural language, enabling Claude Code to automatically generate parametric scripts, export STL files, render previews, and iterate on designs until satisfactory. This significantly lowers the barrier to entry for custom 3D model creation, benefiting hobbyists, makers, and designers seeking rapid prototyping.

How It Works

The skill integrates Claude Code with the CadQuery library. Users interact with Claude by describing the desired object. Claude then leverages the cad-skill to write and execute CadQuery scripts. The run_cadquery_model.py script acts as a subprocess wrapper, capturing errors, optionally rendering previews using preview.py (via trimesh and pyrender), and emitting JSON results for iterative self-correction. This approach allows for a conversational and iterative design process, translating natural language descriptions into functional 3D models.

Quick Start & Requirements

Installation involves cloning the repository into the Claude skills directory: mkdir -p ~/.claude/skills && git clone https://github.com/flowful-ai/cad-skill ~/.claude/skills/parametric-3d-printing

Key requirements include:

  • Python 3.10-3.12 (CadQuery's OCC kernel lacks wheels for Python 3.13+).
  • pip install -r requirements.txt within a Python virtual environment (example setup provided).
  • The Claude Code environment.

Further details and examples can be found in the write-up "I Taught Claude to Design 3D-Printable Parts. Here's How" and on MakerWorld.

Highlighted Details

  • Enables parametric 3D model generation directly from natural language descriptions via Claude Code.
  • Automates the export of STL files and generation of 6-view PNG rendered previews.
  • Facilitates iterative design refinement through AI-driven feedback loops.
  • Includes utility scripts for headless rendering, mesh validation (mesh_io.py), and STL to 3MF conversion (stl_to_3mf.py).

Maintenance & Community

This project was created by Nicolas Chourrout from Flowful.ai. No specific community channels (like Discord/Slack) or roadmap details are provided in the README.

Licensing & Compatibility

The skill and its scripts are licensed under the PolyForm Noncommercial License 1.0.0. This license permits free use, modification, and distribution strictly for noncommercial purposes. Commercial use is not permitted.

Limitations & Caveats

The project is explicitly incompatible with Python 3.13 and newer due to dependencies on CadQuery's OCC kernel. The PolyForm Noncommercial License restricts its application to non-commercial projects, limiting its adoption in commercial product development or integration. Functionality is dependent on the Claude Code execution environment.

Health Check
Last Commit

2 weeks ago

Responsiveness

Inactive

Pull Requests (30d)
1
Issues (30d)
1
Star History
245 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.