Verified:GitHub

segment-anything-model

Segment images with point, box, or mask prompts to produce object masks.

2|Updated Apr 12, 2026

Search Tags:#zero-shot #computer-vision #mask-generation #image-segmentation #segment-anything #onnx-deployment

One-click install

npx skills add https://github.com/Clay-HHK/claude-config --skill segment-anything-model-clay-hhk

Or copy as Structured Prompt for Agent▼

Please help me install this Agent Skill.
Skill: segment-anything-model
Source: https://github.com/Clay-HHK/claude-config/tree/main/skills/AI-research-SKILLs/18-multimodal/segment-anything
Command: npx skills add https://github.com/Clay-HHK/claude-config --skill segment-anything-model-clay-hhk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Segment objects in images without dataset-specific training, enabling fast interactive annotation, automated mask generation, and dataset creation across diverse visual domains.

Core Features & Use Cases

Zero-shot segmentation: Produce high-quality masks on new domains using point, box, or mask prompts.
Automatic mask generation: Generate many object masks for dataset creation or pre-processing.
Deployment & optimization: Supports multiple ViT model sizes (vit_b/l/h), ONNX export, and strategies for GPU/CPU memory and speed tuning.
Use cases: Interactive annotation tools, medical and satellite image segmentation, object extraction pipelines, and preparing training data for downstream models.

Quick Start

Segment objects in image.jpg by providing point or box prompts and return the best mask as a binary PNG.

Frequently Asked Questions about segment-anything-model

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

FAQPage Schema

How do I segment objects in images without dataset-specific training?▼

Automatic mask generation produces multiple object masks from a single image, making it ideal for creating datasets or pre-processing pipelines without manual prompting.

Can I export image segmentation models for ONNX deployment?▼

Yes, you can export the image segmentation models to ONNX for deployment, utilizing multiple ViT model sizes and batching strategies to tune GPU or CPU memory and speed.

Does zero-shot image segmentation work for medical and satellite imagery?▼

Zero-shot image segmentation works for medical and satellite imagery by handling domain-specific tasks, allowing precise object extraction and annotation without custom training data.

What is the best way to generate multiple object masks for dataset creation?▼

Automatic mask generation produces multiple object masks from a single image, making it ideal for creating datasets or pre-processing pipelines without manual prompting.