Google-Cloud-Vision-API

🥈Silver

Google Cloud Vision API enables developers to understand the content of an image by encapsulating powerful machine learning models in an easy to use REST API. It quickly classifies images into thousands of categories (e.g., "sailboat", "lion", "Eiffel Tower"), detects individual objects and faces within images, and finds and reads printed words contained within images. You can build metadata on your image catalog, moderate offensive content, or enable new marketing scenarios through image sentim

400Updated 4mo ago

Intermediate30min to implementmarketing

Saves ~15 min per use

Quick InstallView Source

git clone https://github.com/virtualforce/Google-Cloud-Vision-API.git

Works with:

Claude

Overview

About This Skill

Google Cloud Vision API enables developers to analyze image content through two core features: TEXT_DETECTION for optical character recognition (OCR) and LABEL_DETECTION for object identification. The API accepts images as base64-encoded strings, Google Cloud Storage files, or public URLs, returning structured JSON responses with extracted text, bounding boxes, and confidence scores. TEXT_DETECTION extracts printed words with precise coordinates, while LABEL_DETECTION identifies entities across thousands of categories including objects, locations, activities, and products. Developers benefit from a simple REST endpoint and optional OAuth 2.0 or API key authentication for production applications.

How to Use

Authenticate using an API key or OAuth 2.0 credentials. Send POST requests to https://vision.googleapis.com/v1/images:annotate with image data (base64, Cloud Storage URI, or public URL) and specify feature type (TEXT_DETECTION or LABEL_DETECTION). Parse the JSON response containing textAnnotations or labelAnnotations with descriptions and bounding box coordinates.

Use Cases

Extract text from street signs, documents, and photographs for data entry automation

Classify product images in e-commerce catalogs by detected objects and attributes

Identify landmarks, animals, and scenes for photo organization and tagging

Build content moderation systems by detecting objects and text in user-uploaded images

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/virtualforce/Google-Cloud-Vision-API

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Analyze the following image [IMAGE_URL] using the Google Cloud Vision API. Provide detailed information about the objects, faces, and text present. Also, classify the image into relevant categories and assess the sentiment expressed in the image. The image is related to [COMPANY]'s [INDUSTRY] marketing campaign.

Example Output

# Image Analysis Report

## Objects Detected
- Sailboat
- Ocean
- Clouds
- People (2)

## Faces Detected
- Face 1: Likely age 30-40, smiling, facing the camera
- Face 2: Likely age 25-35, smiling, facing the camera

## Text Detected
- "Enjoy the Voyage"
- "[COMPANY] Cruises"

## Categories
- Travel
- Vacation
- Leisure
- Outdoor

## Sentiment
- Positive sentiment detected, likely due to the smiling faces and pleasant scenery.