gemini-files

Upload images, audio, video, and documents to the Google Gemini File API.

4|2|Updated Jan 29, 2026
One-click install
npx skills add https://github.com/akrindev/google-studio-skills --skill gemini-files
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: gemini-files
Source: https://github.com/akrindev/google-studio-skills/tree/main/skills/gemini-files
Command: npx skills add https://github.com/akrindev/google-studio-skills --skill gemini-files

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the process of uploading various file types to the Gemini File API, making them readily available for analysis and processing by Gemini models.

Core Features & Use Cases

  • File Upload: Upload images, audio, video, and documents (like PDFs) to the Gemini File API.
  • Status Checking: Monitor the processing status of uploaded files.
  • File Management: Organize and reference uploaded files for use in other Gemini skills.
  • Use Case: Upload a product image and then use the gemini-text skill to generate a product description based on that image.

Quick Start

Use the gemini-files skill to upload the file named 'report.pdf'.

Frequently Asked Questions about gemini-files

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

FAQPage Schema
How do I upload files to the Gemini API for multimodal analysis?

To upload files to the Gemini API for multimodal analysis, use a file management interface that sends images, audio, video, and documents directly to the Gemini File API. This makes assets available for subsequent processing.

What file formats are supported by the Gemini File API?

The Gemini File API supports diverse file formats, including images, audio, video, and documents like PDFs. This allows pre-uploading various multimodal assets for batch operations and content processing.

Can I check the processing status of a document uploaded to the Gemini File API?

Yes, you can check the processing status of an uploaded document on the Gemini File API. The system provides status monitoring and options to wait for processing completion before analysis.

What is the best way to manage multiple files for Gemini batch operations?

The best way to manage multiple files for Gemini batch operations is to pre-upload assets to the Gemini File API. You can then list, organize, and reference uploaded files for subsequent multimodal analysis.

Why pre-upload images and audio to the Gemini API instead of processing them directly?

Pre-uploading images and audio ensures files are fully processed and available. This facilitates batch operations and allows referencing uploaded assets across different Gemini skills for multimodal analysis.