Agent skill · research science · jeremylongshore
processing-computer-vision-tasks
Process images using object detection, classification, and segmentation.
Why this skill is useful
Adds specific commands and workflows for processing images using object detection and classification that the AI wouldn't reliably generate on its own.
What it needs
Requires computer-vision-processor, python installed locally. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Computer Vision Processor Process images using object detection, classification, and segmentation pipelines with configurable model backends. Overview This skill empowers Claude to leverage the computer-vision-processor plugin to analyze images, detect objects, and extract meaningful information. It automates computer vision workflows, optimizes performance, and provides detailed insights based on image content. How It Works 1. Analyzing the Request: Claude identifies the need for computer vision processing based on the user's request and trigger terms. 2. Generating Code: Claude generates the appropriate Python code to interact with the computer-vision-processor plugin, specifying the desired analysis type (e.g., object detection, image classification). 3. Executing the Task: The generated code is executed using the /process-vision command, which processes the image and returns the results. When to Use This Skill This skill activates when you need to: Analyze an image for specific objects or features. Classify an image into predefined categories. Segment an image to identify different regions or objects. Examples Example 1: Object Detection User request: "Analyze this image and identify all the cars and pedestrians." The skill will: 1. Generate code to perform object detection on the provided image using the computer-vision-processor plugin. 2. Return a list of bounding boxes and labels for each detected car and pedestrian. Example 2: Image Classification User request: "Classify this image. Is it a cat or a dog?" The skill will: 1. Generate code to perform image classification on the provided image using the computer-vision-processor plugin. 2. Return the classification result (e.g., "cat" or "dog") along with a confidence score. Best Practices Data Validation: Always validate the input image to ensure it's in a supported format and resolution. Error Handling: Implement robust error handling to gracefully manage potential issues during image processing. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/processing-computer-vision-tasks