home/categories/llm-ai/cjkihl-cjkihl-packages-skills-gemini-image-analysis-skill-md
llm-aidata-ai

gemini-image-analysis

Analyze one or multiple images with Gemini Flash (vision) via the generateContent REST API. Uses Bun + TypeScript to base64-encode images and print model output. Use for captioning, OCR-like extraction, UI/screenshot analysis, and multi-image comparison.

cjkihl
maintainer
cjkihl
Updated 1/19/2026
Stars
1
Forks
0
quick start

Installation and usage

Analyze one or multiple images with Gemini Flash (vision) via the generateContent REST API. Uses Bun + TypeScript to base64-encode images and print model output. Use for captioning, OCR-like extraction, UI/screenshot analysis, and multi-image comparison.

Installation
$ install --globalskills.sh
Usage

Once installed, you can use this skill by running the following command in your terminal:

skills use gemini-image-analysis