Agent skill · research science · datadrivenconstruction
image-to-data
Extract data from construction images using AI Vision. Analyze site photos, scanned documents, drawings.
Why this skill is useful
Provides domain-specific knowledge for extracting structured data from construction images using AI Vision and OCR techniques.
What it needs
Requires python3 installed locally. Requires openai account access. About 6k tokens when loaded. Last updated 2026-02-14. 265 stars on the source repository.
What this skill does
Image To Data Overview Based on DDC methodology (Chapter 2.4), this skill extracts structured data from construction images using computer vision, OCR, and AI models to analyze site photos, scanned documents, and drawings. Book Reference: "Преобразование данных в структурированную форму" / "Data Transformation to Structured Form" Quick Start Common Use Cases Analyze Site Photo Extract Drawing Data Detect Safety Violations Quick Reference Component Purpose ----------- --------- ConstructionImageAnalyzer Main analysis engine OCREngine Text extraction ObjectDetector Object detection TableExtractor Table extraction ProgressAnalyzer Progress analysis ImageAnalysisResult Complete analysis result Resources Book: "Data-Driven Construction" by Artem Boiko, Chapter 2.4 Website: https://datadrivenconstruction.io Next Steps Use cad-to-data for CAD/BIM extraction Use defect-detection-ai for defects Use safety-compliance-checker for safety
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills datadrivenconstruction/image-to-data