Agent skill · data analytics · datadrivenconstruction
data-type-classifier
Classify construction data by type (structured, unstructured, semi-structured). Analyze data sources and recommend appropriate storage/processing methods
Why this skill is useful
Provides domain-specific knowledge on data classification and storage recommendations for construction data types that the AI wouldn't reliably generate on its own.
What it needs
Requires ifcopenshell, python3, tesseract installed locally. About 6k tokens when loaded. Last updated 2026-02-14. 265 stars on the source repository.
What this skill does
Data Type Classifier Overview Based on DDC methodology (Chapter 2.1), this skill classifies construction data by type, analyzes data sources, and recommends appropriate storage, processing, and integration methods. Book Reference: "Типы данных в строительстве" / "Data Types in Construction" Quick Start `python from dataclasses import dataclass, field from enum import Enum from typing import List, Dict, Optional, Any, Tuple from datetime import datetime import json import re import mimetypes class DataStructure(Enum): """Data structure classification""" STRUCTURED = "structured" # Tables, databases, spreadsheets SEMISTRUCTURED = "semistructured" # JSON, XML, IFC UNSTRUCTURED = "unstructured" # Documents, images, videos GEOMETRIC = "geometric" # CAD, BIM geometry TEMPORAL = "temporal" # Time-series, schedules SPATIAL = "spatial" # GIS, coordinates class DataFormat(Enum): """Common construction data formats""" # Structured CSV = "csv" EXCEL = "excel" SQL = "sql" PARQUET = "parquet" # Semi-structured JSON = "json" XML = "xml" IFC = "ifc" BCF = "bcf" # Unstructured PDF = "pdf" DOCX = "docx" IMAGE = "image" VIDEO = "video" # Geometric DWG = "dwg" DXF = "dxf" RVT = "rvt" NWD = "nwd" OBJ = "obj" STL = "stl" # Schedule MPP = "mpp" P6 = "p6" XER = "xer" class StorageRecommendation(Enum): """Storage system recommendations""" RELATIONALDB = "relationaldatabase" DOCUMENTDB = "documentdatabase" OBJECTSTORAGE = "objectstorage" GRAPHDB = "graphdatabase" TIMESERIESDB = "timeseriesdatabase" VECTORDB = "vectordatabase" FILESYSTEM = "filesystem" DATALAKE = "datalake" @dataclass class DataCharacteristics: """Characteristics of a data source""" hasschema: bool hasrelationships: bool isqueryable: bool isbinary: bool hasgeometry: bool hastemporal: bool hastextcontent: bool avgrecordsize: Optional[int] = None # bytes estimatedvolume: Optional[str] = None # small/medium/large/huge updatefrequency: Optional[str] = None @dataclass class DataClassification: """Classification result for a data s …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills datadrivenconstruction/data-type-classifier