skills.rest
tan-yong-sheng
tan-yong-shengCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ai-vision-cli

Detect objects with bounding boxes in images and videos via CLI or MCP.

72|15|Updated Oct 5, 2025
Search Tags:#image#analysis#ai#video#vision#object-detection
One-click install
npx skills add https://github.com/tan-yong-sheng/ai-vision-mcp --skill ai-vision-cli
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-vision-cli
Source: https://github.com/tan-yong-sheng/ai-vision-mcp/tree/main/skills/ai-vision-cli
Command: npx skills add https://github.com/tan-yong-sheng/ai-vision-mcp --skill ai-vision-cli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyze images and videos with AI vision models to detect objects with bounding boxes, compare multiple images, audit design compliance, and analyze video content using Google Gemini or Vertex AI. Supports CLI and MCP modes to streamline developer workflows.

Core Features & Use Cases

  • Detect objects in images with bounding boxes and confidence scores
  • Compare multiple images to identify visual differences and regressions
  • Audit design quality and accessibility attributes across UI assets
  • Analyze video content frame-by-frame or in segments using Gemini or Vertex AI
  • Operate in both CLI mode and MCP server integration for automation

Quick Start

Install and run ai-vision-cli to analyze an image or video with Google Gemini or Vertex AI.

Frequently Asked Questions about ai-vision-cli

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

FAQPage Schema
How do I detect objects in an image with AI and get bounding boxes?▼

To detect objects in an image with AI, you run a vision CLI that processes the file and returns bounding boxes with confidence scores. This tool analyzes images using Google Gemini or Vertex AI to identify visual content.

Can I use Google Gemini or Vertex AI to analyze video content frame-by-frame?▼

Yes, you can analyze video content using Google Gemini or Vertex AI. This Skill supports processing videos either frame-by-frame or in segments to extract object detection and visual analysis results through a CLI or MCP workflow.

How do I compare multiple images to identify visual regressions?▼

You compare multiple images for visual regressions by running an AI vision analysis tool that detects differences between assets. This Skill identifies visual differences and regressions by processing multiple images simultaneously.

How do I audit design quality and accessibility attributes across UI assets?▼

Auditing design quality and accessibility attributes across UI assets involves running an AI vision model to evaluate your images. This Skill audits design compliance and accessibility attributes using Google Gemini or Vertex AI.

Does this image and video analysis tool support MCP server integration?▼

Yes, this image and video analysis tool supports MCP server integration. It operates in both CLI mode and MCP deployment to streamline developer workflows for object detection and visual content analysis.

Related Skills

Explore More Software Engineering Skills→
hwj123hwjhwj123hwj
4

vertex-video-reader

Analyze video content with Google Cloud Vertex AI's Gemini-3.1-Flash-lite-preview model.

Community
Intermediate
kamp-uskamp-us
25

heal-ci

Classify CI failures from logs and route them to rerun or report via GitHub Actions.

Official
Intermediate
furkankoykiranfurkankoykiran
4

add-mcp

Parse JSON mcpServers configs and generate claude mcp add commands.

Community
Intermediate
BorisserzBorisserz
1

vision-framework

Implement on-device OCR, face detection, barcode detection, and tracking with Vision and CoreML.

Community
Advanced