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 use this skill?
Automate construction quality control with the Defect Detection AI skill. Identify cracks, corrosion, and structural defects in images and video for improved site safety.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/datadrivenconstruction/defect-detection-aiWhat This Skill Does
The Defect Detection AI skill for OpenClaw is a sophisticated computer vision tool engineered specifically for the construction industry. By leveraging deep learning models, this skill processes images and video feeds to identify, classify, and evaluate structural and surface anomalies. It is capable of detecting a wide range of defects across diverse materials, including concrete (cracks, spalling, efflorescence), steel (corrosion, weld defects), masonry (mortar deterioration), and various finishes or MEP components. The skill goes beyond simple detection by outputting metadata such as confidence levels, bounding boxes for localized defects, and severity estimations to assist project managers and site engineers in making data-driven maintenance decisions.
Installation
To integrate this skill into your OpenClaw environment, execute the following command in your terminal:
clawhub install openclaw/skills/skills/datadrivenconstruction/defect-detection-ai
Ensure that you have the necessary dependencies, including PyTorch and torchvision, installed in your host environment to support the underlying neural network operations.
Use Cases
- Automated Site Audits: Scan drone footage or handheld photos of concrete structures to identify spalling before it becomes a safety hazard.
- Quality Assurance (QA): Monitor steel fabrication to flag corrosion or weld inconsistencies prior to component installation.
- Preventive Maintenance: Track the degradation of masonry and MEP components over time by uploading periodic inspection images to identify maintenance priorities.
Example Prompts
- "OpenClaw, analyze the image at site_a_beam_04.jpg and list all detected cracks along with their severity level."
- "Process the video file from yesterday's masonry wall inspection and summarize any instances of mortar deterioration."
- "Run a scan on this folder of steel pipe images; create a report highlighting any corrosion detected with a confidence score above 85%."
Tips & Limitations
For optimal results, ensure images have high resolution and consistent lighting conditions. The model's accuracy is highly dependent on image clarity; blurred or poorly lit footage will result in lower confidence scores. While the tool provides automated severity estimation, it is intended as an assistive technology for inspection professionals and should always be validated by a licensed structural engineer when assessing critical load-bearing components.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-datadrivenconstruction-defect-detection-ai": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: file-read
Related Skills
data-lineage-tracker
Track data origin, transformations, and flow through construction systems. Essential for audit trails, compliance, and debugging data issues.
cwicr-cost-calculator
Calculate construction costs using DDC CWICR resource-based methodology. Break down costs into labor, materials, equipment with transparent pricing.
data-anomaly-detector
Detect anomalies and outliers in construction data: unusual costs, schedule variances, productivity spikes. Statistical and ML-based detection methods.
historical-cost-analyzer
Analyze historical construction costs for benchmarking, trend analysis, and estimating calibration. Compare projects, track escalation, identify patterns.
df-merger
Merge pandas DataFrames from multiple construction sources. Handle different schemas, keys, and data quality issues.