How does resolution control affect token usage?

Resolution settings allow you to choose between Low, Medium, and High quality. Higher resolution provides better OCR and detail but consumes more tokens (e.g., 1,120 tokens per image at high vs 280 at low).

Can this skill generate images or media?

No, this skill is specifically designed for input processing and media analysis. For image generation, you should use the gemini-3-image-generation skill.

What media formats are supported by this skill?

The skill supports common image formats (JPEG, PNG, WebP, HEIC), video files (MP4, MOV, AVI), various audio formats (WAV, MP3, FLAC), and standard PDF documents.

Is a separate API key required?

Yes, you must have a valid Google Gemini API key configured to use this skill's processing capabilities.

What is the maximum duration for video and audio files?

Gemini 3 Pro can process video files up to 1 hour in duration and audio files up to 9.5 hours in length.

Gemini 3 Multimodal Processing

Name: Gemini 3 Multimodal Processing
Author: adaptationio

byadaptationio

0•

数据科学与机器学习

Processes and analyzes multimodal inputs including images, video, audio, and PDFs using the Gemini 3 Pro model.

This skill empowers Claude to interact with and extract insights from a wide range of media formats using Gemini 3 Pro's native multimodal capabilities. It provides a standardized framework for high-resolution image understanding, video analysis of files up to one hour, long-form audio transcription, and deep PDF document extraction. By offering granular control over media resolution and token optimization, it allows developers to efficiently balance processing quality with cost when building applications that require sophisticated media comprehension.

主要功能

01High-resolution image understanding including OCR and object detection

020 GitHub stars

03Long-form audio transcription and speech analysis for up to 9.5 hours

04Native PDF support for multi-page document extraction and analysis

05Comprehensive video processing for scenes, summaries, and timestamps

06Granular resolution control (low/medium/high) for token optimization

使用场景

01Automating data extraction and code generation from UI/UX screenshots

02Generating searchable summaries and action items from video meetings and podcasts

03Analyzing complex research papers and legal contracts in PDF format

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add adaptationio/skrillz gemini-3-multimodal

For use in Claude.ai and ChatGPT

主要功能

01High-resolution image understanding including OCR and object detection

020 GitHub stars

03Long-form audio transcription and speech analysis for up to 9.5 hours

04Native PDF support for multi-page document extraction and analysis

05Comprehensive video processing for scenes, summaries, and timestamps

06Granular resolution control (low/medium/high) for token optimization

使用场景

01Automating data extraction and code generation from UI/UX screenshots

02Generating searchable summaries and action items from video meetings and podcasts

03Analyzing complex research papers and legal contracts in PDF format

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add adaptationio/skrillz gemini-3-multimodal

For use in Claude.ai and ChatGPT