mcpField
S
segment-image

segment-image

github.com/b-open-ioCreative & media943 installsUpdated 5w ago
Repository

About segment-image

segment-image is a skill for identifying objects and creating image masks with Gemini vision. It is intended for image analysis and object extraction tasks, with a command-line script and a custom segmentation prompt option.

Key features

  1. 01Identify objects in images
  2. 02Create masks for selected objects
  3. 03Segment images into regions
  4. 04Set a custom segmentation prompt
  5. 05Choose an output directory

Use cases

  1. 01Identify people or vehicles in a photo
  2. 02Create masks for objects in an image
  3. 03Separate an image into regions
  4. 04Extract objects for further use

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/b-open-io/gemskills --skill segment-image

After installing, type/segment-imagein Claude Code to confirm it loaded.

Bundled files.clawnet/unsigned-skill.jsonscripts/segment.ts

Details

From the project README

Segment Image

Segment and identify objects in images using Gemini's vision capabilities.

When to Use

Use this skill when the user asks to:

  • Identify objects in an image
  • Generate masks for specific objects
  • Segment an image into regions
  • Extract objects from an image

Usage

bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/segment-image/scripts/segment.ts <input-image> [options]
Options
  • --prompt <text> - Custom segmentation prompt
  • --output <dir> - Output directory for mask files
Examples
# Segment all objects
bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/segment-image/scripts/segment.ts photo.jpg

# Segment with custom prompt
bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/segment-image/scripts/segment.ts photo.jpg --prompt "identify all people and vehicles"

# Save masks to directory
bun run --cwd ${CLAUDE_PLUGIN_ROOT} ${CLAUDE_PLUGIN_ROOT}/skills/segment-image/scripts/segment.ts photo.jpg --output ./masks

Context Discipline

Do not read generated mask images back into context. The script outputs file paths. Ask the user to visually inspect the masks. To inspect programmatically, optimize the images first (via the optimize-images skill).

Model

Uses gemini-3.5-flash (Gemini 3 Flash) for image segmentation.

Last verified: February 2026. If a newer generation exists, STOP and suggest a PR to b-open-io/gemskills. See the ask-gemini skill's references/gemini-api.md for current models and Google's official gemini-api-dev skill for the canonical source.

Comments

Markdown supported