Skip to content
TrustedSkillsbeta
Back to all skills

Segment Anything Model

Listed
davila7·vlatest·ai-ml·MIT

Precisely segments images into distinct objects using a powerful, adaptable zero-shot segmentation model.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add davila7/claude-code-templates --skill segment-anything-model -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

davila7

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill failed 2 of 6 checks. A failure is not proof of bad intent; it means something in the code needs a human to look at it before you run it.

  • No undeclared network calls: failed

    Contacts 1 host that is neither well-known infrastructure nor declared in the skill's frontmatter: dl.fbaipublicfiles.com.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

    Hosts contacted

    dl.fbaipublicfiles.comundeclared

    What it found (3 of 4)

    • cli-tool/components/skills/ai-research/multimodal-segment-anything/SKILL.md:58contacts dl.fbaipublicfiles.com
      wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth
    • cli-tool/components/skills/ai-research/multimodal-segment-anything/SKILL.md:61contacts dl.fbaipublicfiles.com
      wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth
    • cli-tool/components/skills/ai-research/multimodal-segment-anything/SKILL.md:64contacts dl.fbaipublicfiles.com
      wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth

  • No pipe-to-shell installers: failed

    Runs code fetched at install time in 4 places.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

    What it found (3 of 4)

    • cli-tool/components/skills/ai-research/multimodal-segment-anything/SKILL.md:45pip install straight from a URL
      pip install git+https://github.com/facebookresearch/segment-anything.git
    • cli-tool/components/skills/ai-research/multimodal-segment-anything/references/advanced-usage.md:10pip install straight from a URL
      pip install git+https://github.com/facebookresearch/segment-anything-2.git
    • cli-tool/components/skills/ai-research/multimodal-segment-anything/references/advanced-usage.md:53pip install straight from a URL
      pip install git+https://github.com/facebookresearch/segment-anything.git

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • Pinned to a commit: passed

    Scanned davila7/claude-code-templates at 79182c51fb.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
79182c51fb
Manifest
cli-tool/components/skills/ai-research/multimodal-segment-anything/SKILL.md
Scanned
3 files, 1,458 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Segment Anything Model (SAM) skill enables AI agents to perform zero-shot image segmentation. This means it can identify and delineate objects within an image without needing prior training on specific object categories. It excels at generating high-quality masks for various objects, even with limited or no context.

When to use it

  • Image Editing: Automatically select and isolate objects in images for editing or manipulation tasks.
  • Object Detection: Quickly identify the boundaries of objects within a scene without needing labeled data.
  • Scientific Research: Segment cells or other features in microscopy images for analysis.
  • Content Moderation: Identify potentially inappropriate content based on object segmentation.

Key capabilities

  • Zero-shot image segmentation
  • High-quality mask generation
  • Object boundary delineation
  • Works with limited context

Example prompts

  • "Segment the cat in this image."
  • "Create a mask around all instances of cars in this photo."
  • "Identify and segment any people present in this picture."

Tips & gotchas

The model's performance can be influenced by image quality; higher resolution images generally yield better results. While zero-shot, providing some initial guidance (e.g., a bounding box) can improve segmentation accuracy.