Agent skill · research science · datadrivenconstruction
defect-detection-ai
AI-powered construction defect detection using computer vision. Identify cracks, spalling, corrosion, and other defects in concrete, steel, and building components from images and video.
Why this skill is useful
Adds a complete defect detection system with executable code for identifying construction defects using deep learning models.
What it needs
Requires python3 installed locally. About 7k tokens when loaded. Last updated 2026-02-14. 265 stars on the source repository.
What this skill does
AI Defect Detection Overview This skill implements deep learning-based defect detection for construction quality control. Analyze images and video to automatically identify structural and surface defects, classify severity, and generate inspection reports. Detectable Defects: Concrete: Cracks, spalling, honeycombing, efflorescence Steel: Corrosion, weld defects, deformation Masonry: Mortar deterioration, displacement Finishes: Surface defects, coating failures MEP: Insulation damage, pipe corrosion Quick Start Comprehensive Defect Detection System Object Detection Model Crack Analysis System Inspection Report Generator `python from datetime import datetime import pandas as pd class DefectInspectionSystem: """Complete defect inspection and reporting system""" def init(self, detectionmodel: DefectDetectionModel): self.model = detectionmodel self.crackanalyzer = CrackAnalyzer() self.inspections: List[InspectionResult] = [] def performinspection(self, imagepath: str, location: str, elementtype: str, pixelspermm: float = None) -> InspectionResult: """Perform complete inspection on image""" # Detect defects defects = self.model.detect(imagepath, pixelspermm=pixelspermm) # Additional crack analysis for concrete if elementtype.lower() in ['concrete', 'slab', 'wall', 'column', 'beam']: cracks = self.crackanalyzer.detectcracks(imagepath, pixelspermm or 1.0) # Add detailed crack info to relevant defects for defect in defects: if defect.defecttype == DefectType.CRACK: for crack in cracks: # Check if crack overlaps with defect bbox if self.boxesoverlap(defect.boundingbox, crack['boundingbox']): defect.metadata['crackdetails'] = crack break # Determine overall condition overallcondition = self.assessoverallcondition(defects) # Generate recommendations recommendations = self.generaterecommendations(defects, elementtype) result = InspectionResult( inspectionid=f"INS-{datetime.now().strftime('%Y%m%d%H%M%S')}", imagepath=imagepath, timestamp=datetime.now(), location=location, element …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills datadrivenconstruction/defect-detection-ai