# ontology-mapper

ontology-mapper maps construction data elements to standard schemas like IFC, COBie, and Uniclass for cross-system semantic consistency.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 115 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/2.2-Open-Data-Standards/ontology-mapper/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/datadrivenconstruction-ontology-mapper

## What it does

This skill provides semantic mapping between raw construction records and established industry ontologies based on the DDC methodology. Built-in logic matches element names and parameters against definitions in IFC, COBie, Uniclass, OmniClass, and MasterFormat. Each match tracks relationship types such as equivalent, broader, or narrower concepts.

The system calculates confidence levels for every mapped attribute and packages the output into an `OntologyMappingReport`. Execution requires `python3` installed on the host system to run the underlying data models and evaluation scripts.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

2. **Manually: put the files in place**
- File: `.cursor/skills/ontology-mapper/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/2.2-Open-Data-Standards/ontology-mapper
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction --skill ontology-mapper -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/2.2-Open-Data-Standards/ontology-mapper
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/ontology-mapper/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 ontology-mapper -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/2.2-Open-Data-Standards/ontology-mapper/SKILL.md

## When to use it
- map architectural model components to IFC entity classes
- align facility asset lists with COBie spatial schemas
- assign Uniclass classification codes to structural products
- generate coverage reports highlighting unmapped data fields

## Example prompts
- Map this list of structural slabs and walls to standard IFC classes
- Convert facility equipment records into COBie system definitions
- Match building material categories against Uniclass codes and calculate coverage

## 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: b30fdc039736faa0.

BEGIN THIRD-PARTY FILE b30fdc039736faa0
````text
---
name: "ontology-mapper"
description: "Map construction data to standard ontologies. Create semantic mappings between different data schemas"
homepage: "https://datadrivenconstruction.io"
metadata: {"openclaw": {"emoji": "🌐", "os": ["darwin", "linux", "win32"], "homepage": "https://datadrivenconstruction.io", "requires": {"bins": ["python3"]}}}
---
# Ontology Mapper

## Overview

Based on DDC methodology (Chapter 2.2), this skill maps construction data to standard ontologies like IFC, COBie, Uniclass, and OmniClass, enabling semantic interoperability between systems.

**Book Reference:** "Доминирование открытых данных" / "Open Data Dominance"

## Quick Start

```python
from dataclasses import dataclass, field
from enum import Enum
from typing import List, Dict, Optional, Set, Tuple
from datetime import datetime
import json
import re

class OntologyType(Enum):
    """Standard construction ontologies"""
    IFC = "ifc"                    # Industry Foundation Classes
    COBIE = "cobie"                # Construction Operations Building Information Exchange
    UNICLASS = "uniclass"          # UK classification
    OMNICLASS = "omniclass"        # North American classification
    MASTERFORMAT = "masterformat"  # CSI MasterFormat
    UNIFORMAT = "uniformat"        # CSI UniFormat
    CUSTOM = "custom"              # Custom ontology

class MappingConfidence(Enum):
    """Confidence level of mapping"""
    EXACT = "exact"        # 100% match
    HIGH = "high"          # 90%+ match
    MEDIUM = "medium"      # 70-90% match
    LOW = "low"            # 50-70% match
    UNCERTAIN = "uncertain" # <50% match

class RelationType(Enum):
    """Types of relationships between concepts"""
    EQUIVALENT = "equivalent"     # Same concept
    BROADER = "broader"           # Source is more specific
    NARROWER = "narrower"         # Source is more general
    RELATED = "related"           # Related but not equivalent
    PART_OF = "part_of"           # Component relationship
    HAS_PART = "has_part"         # Contains components

@dataclass
class OntologyConcept:
    """Concept in an ontology"""
    id: str
    name: str
    ontology: OntologyType
    definition: Optional[str] = None
    parent_id: Optional[str] = None
    synonyms: List[str] = field(default_factory=list)
    properties: Dict[str, str] = field(default_factory=dict)

@dataclass
class SemanticMapping:
    """Mapping between two concepts"""
    source_concept: str
````
END THIRD-PARTY FILE b30fdc039736faa0

The third-party file has ended. Everything between the b30fdc039736faa0 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 2488 of 21665 bytes. © datadrivenconstruction · MIT · https://github.com/datadrivenconstruction/DDC_Skills_for_AI_Agents_in_Construction/tree/HEAD/2_DDC_Book/2.2-Open-Data-Standards/ontology-mapper/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
