Agent skill · research science · datadrivenconstruction
rag-construction
Build RAG systems for construction knowledge bases. Create searchable AI-powered construction document systems
Why this skill is useful
Provides domain-specific knowledge for building RAG systems tailored to construction documents, including chunking strategies and document types.
What it needs
Requires python3 installed locally. About 6k tokens when loaded. Last updated 2026-02-14. 265 stars on the source repository.
What this skill does
RAG Construction Overview Based on DDC methodology (Chapter 2.3), this skill builds Retrieval-Augmented Generation (RAG) systems for construction knowledge bases, enabling semantic search and AI-powered question answering over construction documents. Book Reference: "Pandas DataFrame и LLM ChatGPT" / "Pandas DataFrame and LLM ChatGPT" Quick Start `python from dataclasses import dataclass, field from enum import Enum from typing import List, Dict, Optional, Any, Callable from datetime import datetime import json import hashlib import re class DocumentType(Enum): """Types of construction documents""" SPECIFICATION = "specification" DRAWING = "drawing" CONTRACT = "contract" RFI = "rfi" SUBMITTAL = "submittal" CHANGEORDER = "changeorder" MEETINGMINUTES = "meetingminutes" DAILYREPORT = "dailyreport" SAFETYREPORT = "safetyreport" INSPECTION = "inspection" MANUAL = "manual" STANDARD = "standard" class ChunkingStrategy(Enum): """Text chunking strategies""" FIXEDSIZE = "fixedsize" PARAGRAPH = "paragraph" SECTION = "section" SEMANTIC = "semantic" SENTENCE = "sentence" @dataclass class DocumentChunk: """A chunk of document text""" id: str documentid: str content: str metadata: Dict[str, Any] embedding: Optional[List[float]] = None tokencount: int = 0 position: int = 0 @dataclass class Document: """Construction document""" id: str title: str doctype: DocumentType content: str source: str metadata: Dict[str, Any] = field(defaultfactory=dict) chunks: List[DocumentChunk] = field(defaultfactory=list) createdat: datetime = field(defaultfactory=datetime.now) @dataclass class SearchResult: """Search result from vector store""" chunk: DocumentChunk score: float documenttitle: str doctype: DocumentType @dataclass class RAGResponse: """Response from RAG system""" query: str answer: str sources: List[SearchResult] confidence: float tokensused: int class TextChunker: """Split documents into chunks for embedding""" def init( self, strategy: ChunkingStrategy = ChunkingStrategy.PARAGRAPH, chu …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills datadrivenconstruction/rag-construction