# nobim-image-generator

The nobim-image-generator Claude Code skill creates visuals from BIM data without BIM software. It runs on requests to generate images or diagrams from Revit or IFC models.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 117 installs · ★ 434 repo stars
- Author: datadrivenconstruction
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/1_DDC_Toolkit/BIM-Visualization/nobim-image-generator/SKILL.md
- Updated: 2026-10-19
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/nobim-image-generator

## What it does

The skill turns BIM data into visualizations without relying on BIM software. It can create a 3D element scatter plot, a floor plan, a category chart, and a volume treemap. Batch processing generates 3D plots and category charts for multiple projects.

The script reads BIM data from the `Elements` sheet in an Excel file. A 3D plot needs the bounding-box center columns `BBox_CenterX`, `BBox_CenterY`, and `BBox_CenterZ`; floor plans use element bounds and the `Level` field. It requires Python 3 and the `pandas`, `matplotlib`, `seaborn`, `plotly`, and `ifcopenshell` libraries.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill nobim-image-generator -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/nobim-image-generator/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/nobim-image-generator/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill nobim-image-generator -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/nobim-image-generator/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill nobim-image-generator -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/nobim-image-generator/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction 1_DDC_Toolkit/BIM-Visualization/nobim-image-generator
```

2. **Manually: put the files in place**
- File: `.github/skills/nobim-image-generator/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill nobim-image-generator -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --path 1_DDC_Toolkit/BIM-Visualization/nobim-image-generator
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/nobim-image-generator/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill nobim-image-generator -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/1_DDC_Toolkit/BIM-Visualization/nobim-image-generator/SKILL.md

## When to use it
- plot model elements in 3D
- draw a floor plan for a selected level
- chart element counts by category
- process BIM project spreadsheets in batches

## Example prompts
- Create a 3D element plot from `model.xlsx`.
- Draw the floor plan for `Level 1` in `building.xlsx`.
- Generate category charts for project spreadsheets in `output`.

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: a4368184fb38a636.

BEGIN THIRD-PARTY FILE a4368184fb38a636
````text
---
name: "nobim-image-generator"
description: "Generate images and visualizations from Revit/IFC files without BIM software. Python-based noBIM tool for batch processing."
homepage: "https://datadrivenconstruction.io"
metadata: {"openclaw": {"emoji": "🖼️", "os": ["win32"], "homepage": "https://datadrivenconstruction.io", "requires": {"bins": ["python3"], "anyBins": ["ifcopenshell"]}}}
---
# noBIM Image Generator

## Business Case

### Problem Statement
Creating visualizations from BIM models typically requires:
- Expensive BIM software licenses
- Manual screenshot capture
- Time-consuming rendering
- Impossible to batch process

### Solution
noBIM tool extracts data and generates visualizations using Python libraries, processing hundreds of projects without BIM software.

### Business Value
- **No license required** - Pure Python solution
- **Batch processing** - Generate images for 1000s of projects
- **Customizable** - Create exactly the visualizations you need
- **Automatable** - Integrate into data pipelines

## Technical Implementation

### Installation
```bash
pip install pandas matplotlib seaborn plotly ifcopenshell
```

### Core Functionality

```python
import pandas as pd
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import numpy as np
from pathlib import Path
from typing import List, Optional, Tuple

class NoBIMVisualizer:
    def __init__(self):
        self.elements = None
        self.project_name = ""

    def load_from_excel(self, xlsx_path: str) -> int:
        """Load BIM data from converted Excel file."""
        self.elements = pd.read_excel(xlsx_path, sheet_name="Elements")
        self.project_name = Path(xlsx_path).stem
        return len(self.elements)

    def generate_3d_scatter(self, output_path: str,
                            color_by: str = "Category",
                            size: Tuple[int, int] = (12, 10)) -> str:
        """Generate 3D scatter plot of elements."""
        if not all(col in self.elements.columns
                   for col in ['BBox_CenterX', 'BBox_CenterY', 'BBox_CenterZ']):
            raise ValueError("Bounding box data required. Export with 'bbox' option.")

        fig = plt.figure(figsize=size)
        ax = fig.add_subplot(111, projection='3d')

        # Get unique categories for coloring
        categories = self.elements[color_by].unique()
        colors = plt.cm.tab20(np.linspace(0, 1, len(categories)))
        color_map = dict(zip(categories, colors))

        for cat in categories:
````
END THIRD-PARTY FILE a4368184fb38a636

The third-party file has ended. Everything between the a4368184fb38a636 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2521 of 9127 bytes. © datadrivenconstruction · MIT · https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/1_DDC_Toolkit/BIM-Visualization/nobim-image-generator/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
