skills.rest
levanminhduc
levanminhducCOMMUNITY
Explore all skills by this author →
GitHub

gemini-vision

Analyzes images via Google Gemini Vision for captioning, classification, VQA, and object detection with bounding boxes.

Updated Jul 23, 2025
Search Tags:#captioning#object-detection#gemini-vision#image understanding#visual QA
One-click install
npx skills add https://github.com/levanminhduc/LuongHoaThoNew --skill gemini-vision-levanminhduc
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini-vision
Source: https://github.com/levanminhduc/LuongHoaThoNew/tree/main/.claude/skills/gemini-vision
Command: npx skills add https://github.com/levanminhduc/LuongHoaThoNew --skill gemini-vision-levanminhduc

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires google-genai, requests, Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables image understanding via Gemini Vision, including captioning, classification, QA, and object detection.

Core Features & Use Cases

  • Image captioning & classification: Describe and categorize visuals.
  • Visual QA: Answer questions about image content.
  • Multi-image analysis: Compare and analyze multiple images.

Quick Start

Analyze a local image to generate a caption and a few descriptive tags.

Frequently Asked Questions about gemini-vision

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

FAQPage Schema
How do I analyze images with Gemini Vision to generate captions and detect objects?▼

Image analysis with Gemini Vision processes local files, URLs, or inline image data to generate captions, classify content, and detect objects with bounding boxes. The Skill handles single and multi-image scenarios, returning structured outputs for downstream processing.

Can I use Gemini Vision to answer questions about image content and perform visual QA?▼

Yes, visual question answering (VQA) lets you pose questions about image content and receive accurate answers. Gemini Vision processes your query against the image to extract relevant information for classification, comparison, or detailed analysis.

What file formats and input methods does Gemini Vision support for image analysis?▼

Gemini Vision accepts inline image data, file uploads, and URLs as input. It processes PDFs up to 1,000 pages and handles large image batches up to 3,600 images, supporting standard image formats via the Pillow library.

How do I configure API keys and select the right Gemini model variant for my use case?▼

The Skill looks up API keys from environment variables, the skill directory, or project root. You can select across Gemini model variants and configure structured output handling to match your downstream tooling requirements.

Does Gemini Vision work for document understanding and multi-image comparison workflows?▼

Yes, Gemini Vision handles document understanding for PDFs and supports multi-image analysis scenarios. It can compare, segment, and analyze multiple images together, making it suitable for batch processing and cross-image reasoning.

What dependencies do I need to run Gemini Vision for image analysis?▼

Gemini Vision requires google-genai for API access, requests for HTTP operations, and Pillow for image processing. These handle API authentication, network calls, and image format handling.

Related Skills

Explore More Design & Creative Skills→
secondskysecondsky
204

google-gemini-api

Integrate Google Gemini API via @google/genai SDK for text generation and function calling.

Community
Advanced
babdulhakim2babdulhakim2

sanctions-check

Screen entities against OFAC SDN, UN, EU, and other sanctions lists.

Community
Intermediate
dkyazzentwatwadkyazzentwatwa
86

ocr-document-processor

Extract text from images and scanned PDFs using OCR with structured output.

Community
Advanced
519lab519lab
2

segment-anything-model

Segment objects in images using Meta AI's Segment Anything Model.

Official
Intermediate