computer-vision-expert

Design end-to-end computer vision pipelines with YOLO26, SAM 3, and VLMs.

Updated Mar 20, 2026

Search Tags:#segmentation #computer-vision #slam #3d-reconstruction #edge-deployment #real-time-detection #visual-language-models

Ready to run

npx skills add https://github.com/sixscripts-ai/ghostssh --skill computer-vision-expert-sixscripts-ai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: computer-vision-expert
Source: https://github.com/sixscripts-ai/ghostssh/tree/main/skills/computer-vision-expert
Command: npx skills add https://github.com/sixscripts-ai/ghostssh --skill computer-vision-expert-sixscripts-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides expert guidance on designing, implementing, and optimizing state-of-the-art computer vision pipelines, from real-time object detection with YOLO26 to segmentation with SAM 3 and vision-language reasoning for spatial understanding.

Core Features & Use Cases

Unified real-time detection (YOLO26) with edge-friendly deployment and high small-object accuracy.
Promptable segmentation (SAM 3) for text-to-mask and 3D reconstruction with VLMs.
Vision-language reasoning and Visual SLAM for geometric understanding and edge-to-cloud workflows.

Quick Start

Describe your CV project goals and deployment constraints.

Frequently Asked Questions about computer-vision-expert

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I build a real-time computer vision pipeline for edge deployment?▼

Build a real-time computer vision pipeline by combining YOLO26 for detection and SAM 3 for segmentation, then export models using ONNX or TensorRT to satisfy edge deployment constraints and achieve rapid inference.

What is the best way to combine 3D reconstruction with visual SLAM for robotics?▼

Combine 3D reconstruction with Visual SLAM by integrating promptable segmentation outputs from SAM 3 and vision-language models to provide geometric understanding and spatial awareness for autonomous robotics systems.

Can I use YOLO26 and SAM 3 together for industrial inspection tasks?▼

Yes, you can use YOLO26 and SAM 3 together for industrial inspection by chaining real-time object detection with promptable text-to-mask segmentation to identify defects and achieve precise spatial reasoning.

How do visual-language models improve spatial intelligence in autonomous systems?▼

Visual-language models improve spatial intelligence by enabling text-to-mask promptable segmentation and 3D reasoning, allowing autonomous systems to process complex visual scenes and perform geometric understanding tasks.

Does this computer vision pipeline support ONNX and TensorRT exports?▼

Yes, the computer vision pipeline explicitly supports ONNX and TensorRT exports to ensure modular architecture and optimized rapid inference across both edge and cloud deployment environments.

When should I use a vision-language model instead of standard object detection?▼

Use a vision-language model instead of standard object detection when your application requires promptable text-to-mask segmentation, 3D reconstruction, or complex spatial reasoning beyond simple bounding box identification.