Segment Anything

Official

Segment any object in images with zero-shot prompts.

Authoragentic-in
Version1.0.0
Installs0

System Documentation

## What problem does it solve? Segmenting objects in images quickly and flexibly using prompts (points, boxes, or masks) and generate all object masks automatically, enabling faster annotation and analysis.

## Core Features & Use Cases

  • Zero-shot segmentation for any object domain with different prompts (points, boxes, or masks).
  • Interactive annotation, data labeling pipelines, and domain-specific segmentation tasks across photography, medicine, and remote sensing.
  • Use cases include building annotation tools, data prep for large models, and automatic mask generation for datasets.

### Quick Start Provide an image and prompt SAM with a point, box, or mask to obtain object segmentation masks.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: Segment Anything
Download link: https://github.com/agentic-in/elephant-agent/archive/main.zip#segment-anything

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.