CAD to Data for Openclaw

A powerful data extraction skill that converts complex CAD and BIM files into structured, actionable data formats based on DDC methodology.

datadrivenconstruction
v2.0.0
Feb 14, 2026
0
1.8k
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install cad-to-data

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install cad-to-data using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is CAD to Data?

The CAD to Data skill is a technical implementation based on the Data-Driven Construction (DDC) methodology, specifically Chapter 2.4. It serves as a bridge between proprietary architectural or engineering files and structured data environments. By utilizing this skill, developers can programmatically access the underlying geometry, properties, and relationships within building information models (BIM) and traditional drafting files.

This utility is essential for teams looking to automate the transition from design to data analysis. Whether you are working with high-fidelity Revit and IFC files or legacy DWG and DGN formats, the skill provides a unified interface to extract element-level details, spatial hierarchies, and material specifications, making it a cornerstone of the Openclaw Skills ecosystem for construction technology.

CAD to Data Use Cases

  • Extracting detailed element properties and quantities from IFC or Revit models for cost estimation.
  • Automating the generation of door, window, or equipment schedules directly from CAD files.
  • Converting legacy DWG floor plans into structured JSON data for spatial analytics or database population.
  • Aggregating material volumes and areas across different levels of a building for sustainability reporting.
  • Building automated validation pipelines to check BIM data integrity against project requirements.

How CAD to Data Works

  1. The CADDataConverter identifies the source file format (e.g., .ifc, .dwg, .rvt) via the input file extension.
  2. The system routes the file to a specialized extractor, such as the IFCExtractor or DWGExtractor, which parses the file's internal schema.
  3. Entities are mapped to a standardized ElementCategory (e.g., WALL, FLOOR, BEAM) to ensure data consistency across different formats.
  4. Geometric data is processed into bounding boxes and 3D points, while metadata and properties are stored in a key-value dictionary.
  5. The CADExtractionResult object compiles the extracted elements, layers, and metadata into a final structured output, such as JSON or a DataFrame.

CAD to Data Setup

To integrate this Openclaw Skills component into your project, ensure you have a Python environment and install the necessary parsing libraries for your specific formats (e.g., ifcopenshell for IFC or ezdxf for DWG).

# Install core dependencies for IFC and DWG support
pip install ifcopenshell ezdxf

Initialize the converter in your script:

from cad_to_data import CADDataConverter, ElementCategory

converter = CADDataConverter()

CAD to Data Data Schema & Taxonomy

The skill produces a highly structured output represented by the CADExtractionResult class. Below is the primary taxonomy for extracted elements:

Object Description
CADElement Contains ID, GUID, Category, Type, and Level.
Properties A dictionary of BIM metadata (e.g., LoadBearing: True).
Quantities Numeric data including Area, Volume, and Perimeter.
Materials List of material names with associated area/volume per element.
Relationships Links between elements, such as a Door being hosted by a Wall.

CAD to Data Advanced Features

  • Multi-format support covering both 3D BIM (IFC, RVT) and 2D CAD (DWG, DXF, DGN).
  • Category-specific filtering to optimize extraction performance for large models.
  • Automated extraction of architectural levels and CAD layers.
  • Built-in reporting engine to generate Markdown-based summaries of file contents.
  • Material-level data extraction for granular environmental and cost impact analysis.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*