A professional-grade computer vision skill for identifying, classifying, and assessing the severity of defects across various industries.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install defect-detector
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install defect-detector using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Defect Detector AI Skill?
The Defect Detector is a sophisticated computer vision tool built for the Openclaw Skills ecosystem, designed to automate the visual inspection process. It enables AI agents to analyze images for specific anomalies, ranging from agricultural crop diseases to structural cracks in buildings and defects in industrial hardware. By leveraging high-performance detection models, the skill provides a bridge between raw pixels and structured data.
This skill is particularly valuable for developers building automated monitoring systems. It doesn't just identify that a problem exists; it provides spatial localization via bounding boxes and segmentation masks, classifies the issue against an extensive library of over 120 types, and quantifies the severity. This level of detail makes it an essential component for any Openclaw Skills implementation focused on quality assurance or precision agriculture.
Defect Detector AI Skill Use Cases
- Agricultural monitoring to detect leaf rust, spots, or pest damage in crops.
- Industrial quality control for identifying surface defects in manufactured parts.
- Infrastructure inspections to locate cracks or structural degradation in buildings.
- Automated environmental surveys that require classification of botanical health issues.
- Smart maintenance systems that trigger repair tickets based on visual severity assessments.
How Defect Detector AI Skill Works
- The skill accepts an image path or buffer as input within the Openclaw Skills environment.
- It initializes a pre-trained YOLOv8 detection model optimized for disease and defect patterns.
- The model scans the image to perform object detection, identifying specific regions of interest.
- It calculates the bounding box coordinates and segmentation masks for each localized defect.
- The system performs a classification check against its internal database of 120+ defect types.
- An area ratio and feature analysis are conducted to assign a severity level (e.g., Mild to Extreme).
- A structured JSON object is returned containing all detection metadata, ready for integration into larger workflows.
Defect Detector AI Skill Setup
To utilize this skill, ensure you have the necessary computer vision dependencies installed in your environment:
pip install ultralytics>=8.0 opencv-python>=4.8 numpy>=1.24
You must also ensure the relevant model weights (e.g., yolov8_disease_v2.pt) are accessible to the detector script.
Defect Detector AI Skill Data Schema & Taxonomy
The Defect Detector provides structured output for seamless integration with other Openclaw Skills. The output schema is organized as follows:
| Attribute | Type | Description |
|---|---|---|
has_defect |
Boolean | True if one or more defects are detected. |
defect_count |
Integer | The total number of unique anomalies found. |
type |
String | The specific name of the disease/defect (e.g., Maize Leaf Spot). |
confidence |
Float | The statistical confidence score (0.0 - 1.0). |
severity |
String | Categorical ranking: Mild, Moderate, Severe, or Extreme. |
bbox |
Array | Spatial coordinates [x1, y1, x2, y2]. |
area_ratio |
Float | Percentage of total image area affected by the defect. |
Defect Detector AI Skill Advanced Features
- Support for custom YOLOv8 model paths to adapt the skill to specific niche industries.
- High-precision segmentation masks for complex shape analysis beyond simple rectangles.
- Automated mapping to knowledge bases for instant generation of remediation solutions.
- Multi-category support with a built-in library of 120+ common disease and defect classifications.
- Scalable architecture suitable for multi-agent Openclaw Skills deployments.
SKILL.md
Loading
Related Openclaw Skills
t-cpm AI Image Filter
An AI-enhanced image recognition and filtering tool that automates content auditing and batch screening based on 3D keyword analysis.
NautilusTrader Skill
A high-performance, Rust-native algorithmic trading framework designed for seamless transition from backtesting to live execution.
Universal Occupation Adapter
A powerful meta-generator that creates professional cognitive frameworks for AI agents based on any occupation name.
Image Search (Google Lens)
A powerful visual discovery tool that leverages Google Lens to identify objects, landmarks, and products directly from images.
Notion Skill for OpenClaw
A powerful integration that enables AI agents to read, write, and manage Notion pages and databases through the official Notion API.
Web Access Skill
A powerful web interaction toolkit that enables AI agents to search, crawl, and interact with dynamic websites using a real browser environment.
Featured*
