Does it support 3D vision tasks?

Absolutely. It covers 3D reconstruction, spatial awareness, monocular depth estimation, and visual SLAM for autonomous systems.

What specific models does this skill support?

It specializes in 2026 state-of-the-art models including YOLO26, Segment Anything Model 3 (SAM 3), Depth Anything V2, and various Vision Language Models like Qwen2-VL.

How does SAM 3 integration work?

It guides you through text-guided segmentation, allowing you to isolate specific objects using natural language prompts instead of manual point clicks.

Can it help with edge deployment?

Yes, it provides specific guidance on optimizing models for hardware like NPUs and TPUs using ONNX, TensorRT, and NMS-free architectures.

Is it compatible with classical CV techniques?

Yes, it bridges modern deep learning with classical geometry, including chessboard and Charuco calibration pipelines for high-precision multi-camera rigs.

Computer Vision Expert

Name: Computer Vision Expert
Author: sickn33

bysickn33

•

34,777

•

Ciencia de Datos y ML

Builds and optimizes state-of-the-art visual intelligence systems using YOLO26, SAM 3, and advanced vision-language models.

This skill transforms Claude into a senior vision systems architect specializing in 2026-era SOTA technologies. It provides expert guidance on implementing NMS-free detection with YOLO26, promptable segmentation via SAM 3, and complex visual reasoning using VLMs. Whether you are designing real-time spatial analysis for robotics or optimizing vision pipelines for edge deployment on NPUs, this skill bridges the gap between modern deep learning and classical geometric calibration to deliver high-performance, production-grade vision solutions.

Características Principales

01Monocular Depth Estimation and 3D Reconstruction

02Text-to-Mask Segmentation with SAM 3

03Visual Grounding and Reasoning with VLMs

04High-Precision Sub-pixel Camera Calibration

0534,777 GitHub stars

06YOLO26 NMS-Free Detection & Edge Optimization

Casos de Uso

01Optimizing vision models for deployment on mobile and IoT edge devices.

02Implementing zero-shot semantic segmentation for complex scene understanding.

03Developing real-time industrial inspection systems with low-latency object detection.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add sickn33/antigravity-awesome-skills computer-vision-expert

For use in Claude.ai and ChatGPT

Características Principales

01Monocular Depth Estimation and 3D Reconstruction

02Text-to-Mask Segmentation with SAM 3

03Visual Grounding and Reasoning with VLMs

04High-Precision Sub-pixel Camera Calibration

0534,777 GitHub stars

06YOLO26 NMS-Free Detection & Edge Optimization

Casos de Uso

01Optimizing vision models for deployment on mobile and IoT edge devices.

02Implementing zero-shot semantic segmentation for complex scene understanding.

03Developing real-time industrial inspection systems with low-latency object detection.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add sickn33/antigravity-awesome-skills computer-vision-expert

For use in Claude.ai and ChatGPT