# bim-qto

bim-qto extracts quantities from tabular BIM and CAD exports to prepare grouped takeoff reports for cost estimation.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 215 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/2_DDC_Book/3.2-QTO-Auto-Estimates/bim-qto/SKILL.md
- Updated: 2026-10-19
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/bim-qto

## What it does

The skill provides a Python implementation around the `BIMQuantityTakeoff` class. It identifies common column naming variations for categories, types, levels, volumes, areas, and element counts across Revit and IFC tabular exports.

It aggregates quantities by family type, classification category, or building storey. You can generate cross-tabulation pivot tables across levels and types, or isolate specific building assemblies like walls, slabs, and doors.

Execution relies on local `python3` along with `pandas` and `numpy`. Processing fails if the input data lacks identifiable category or level identifiers.

## Install

### Claude Code (native platform)

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

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

### Codex

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

2. **Manually: put the files in place**
- File: `.agents/skills/bim-qto/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 bim-qto -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/bim-qto/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 2_DDC_Book/3.2-QTO-Auto-Estimates/bim-qto
```

2. **Manually: put the files in place**
- File: `.github/skills/bim-qto/SKILL.md`

### Gemini CLI

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

2. **Platform CLI**
```bash
gemini skills install https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --path 2_DDC_Book/3.2-QTO-Auto-Estimates/bim-qto
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/bim-qto/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 bim-qto -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/2_DDC_Book/3.2-QTO-Auto-Estimates/bim-qto/SKILL.md

## When to use it
- aggregate material volumes across building storeys
- calculate total counts and areas grouped by element type
- generate cross-tabulation pivots for levels and family types
- filter BIM export tables down to specific structural assemblies

## Example prompts
- Group the volume quantities in this BIM export by level and type
- Extract all wall elements from the data and sum their total area
- Generate a quantity takeoff report grouped by element category

## 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: 82f30a7d90e60905.

BEGIN THIRD-PARTY FILE 82f30a7d90e60905
````text
---
name: "bim-qto"
description: "Extract quantities from BIM/CAD data for cost estimation. Group by type, level, zone. Generate QTO reports."
homepage: "https://datadrivenconstruction.io"
metadata: {"openclaw": {"emoji": "⚡", "os": ["win32"], "homepage": "https://datadrivenconstruction.io", "requires": {"bins": ["python3"]}}}
---
# BIM Quantity Takeoff

## Overview
Quantity Takeoff (QTO) extracts measurable quantities from BIM models. This skill processes BIM exports to generate grouped quantity reports for cost estimation.

## Python Implementation

```python
import pandas as pd
import numpy as np
from typing import Dict, Any, List, Optional, Tuple
from dataclasses import dataclass, field
from enum import Enum


class QTOUnit(Enum):
    """Quantity takeoff measurement units."""
    COUNT = "ea"
    LENGTH = "m"
    AREA = "m2"
    VOLUME = "m3"
    WEIGHT = "kg"
    LINEAR_FOOT = "lf"
    SQUARE_FOOT = "sf"
    CUBIC_YARD = "cy"


@dataclass
class QTOItem:
    """Single QTO line item."""
    category: str
    type_name: str
    description: str
    quantity: float
    unit: str
    level: Optional[str] = None
    material: Optional[str] = None
    element_count: int = 0


@dataclass
class QTOReport:
    """Complete QTO report."""
    project_name: str
    items: List[QTOItem]
    total_elements: int
    categories: int
    generated_date: str


class BIMQuantityTakeoff:
    """Extract quantities from BIM data."""

    # Column mappings for different BIM exports
    COLUMN_MAPPINGS = {
        'type': ['Type Name', 'TypeName', 'type_name', 'Family and Type', 'IfcType'],
        'category': ['Category', 'category', 'IfcClass', 'Element Category'],
        'level': ['Level', 'level', 'Building Storey', 'BuildingStorey', 'Floor'],
        'volume': ['Volume', 'volume', 'Volume (m³)', 'Qty_Volume'],
        'area': ['Area', 'area', 'Surface Area', 'Area (m²)', 'Qty_Area'],
        'length': ['Length', 'length', 'Length (m)', 'Qty_Length'],
        'count': ['Count', 'count', 'Quantity', 'ElementCount'],
        'material': ['Material', 'material', 'Structural Material', 'MaterialName']
    }

    def __init__(self, df: pd.DataFrame):
        """Initialize with BIM data DataFrame."""
        self.df = df
        self.column_map = self._detect_columns()

    def _detect_columns(self) -> Dict[str, str]:
        """Detect which columns exist in data."""
        mapping = {}

        for standard, variants in self.COLUMN_MAPPINGS.items():
            for variant in variants:
                if variant in self.df.columns:
                    mapping[standard] = variant
                    break

        return mapping
````
END THIRD-PARTY FILE 82f30a7d90e60905

The third-party file has ended. Everything between the 82f30a7d90e60905 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 2661 of 11582 bytes. © datadrivenconstruction · MIT · https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/2_DDC_Book/3.2-QTO-Auto-Estimates/bim-qto/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
