skills.rest
nicobailon
nicobailonCOMMUNITY
Explore all skills by this author →
Website𝕏@nicopremeGitHub

gemini

Access Gemini 3 Pro for text, video, document, and image queries via cookies.

1|1|Updated Dec 13, 2025
Search Tags:#multimodal#thinking#gemini#image-generation#video-analysis#cookie-auth#webapi
One-click install
npx skills add https://github.com/nicobailon/gemini-multimodal --skill gemini-nicobailon
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gemini
Source: https://github.com/nicobailon/gemini-multimodal/tree/main
Command: npx skills add https://github.com/nicobailon/gemini-multimodal --skill gemini-nicobailon

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

All-in-one access to Gemini 3 Pro via cookie-based authentication for querying, multimodal analysis, and image generation/editing, eliminating the need for API keys.

Core Features & Use Cases

  • Text Queries: perform complex reasoning with Thinking enabled.
  • Video Analysis: upload MP4s for summaries, timestamps, and insights.
  • YouTube Analysis: analyze videos via YouTube URLs using the YouTube extension.
  • Document & Image Analysis: Q&A and data extraction from PDFs and images.
  • Image Generation & Editing: create or modify images from natural language prompts.
  • Google Search Grounding: grounded results for current information.
  • Thinking Access: optionally reveal the model's reasoning process with --show-thoughts.

Quick Start

Ask Gemini 3 Pro to analyze a video, PDF, or image using browser cookies for authentication.

Frequently Asked Questions about gemini

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

FAQPage Schema
How do I analyze a YouTube video using Gemini without an API key?▼

You can analyze YouTube videos by passing the URL to the Gemini Skill. It uses cookie-based authentication and the YouTube extension to provide summaries, timestamps, and insights without requiring an API key.

Can I generate and edit images from text prompts with Gemini 3 Pro?▼

Yes, Gemini 3 Pro supports image generation and editing from natural language prompts. You can use the --generate-image and --edit flags to create or modify images locally.

How do I view the reasoning process for complex text queries?▼

You can reveal the model's reasoning process by using the --show-thoughts flag. This allows you to see the thinking mechanism behind complex text queries and multimodal analysis.

What is the best way to extract data from PDFs and images without API limits?▼

The Gemini Skill uses cookie-based authentication to perform Q&A and data extraction from PDFs and images. This bypasses standard API limits while providing direct multimodal analysis.

Does Gemini 3 Pro support automatic grounding for current web information?▼

Yes, Gemini 3 Pro includes automatic Google Search grounding. This ensures your text queries and analysis are supplemented with current, up-to-date information from the web.

How do I handle timeouts when uploading large MP4 files for video analysis?▼

The Skill includes retry logic and timeout controls for reliability. You can adjust the processing limits using the --timeout flag when uploading MP4 files for video analysis.

Related Skills

Explore More Software Engineering Skills→
nicobailonnicobailon
3

generate-image

Generate and edit images via Gemini Nano Banana using a CLI script.

Community
Advanced
jiesoujiesou

yt-dlp

Extract YouTube and Bilibili video subtitles and generate structured summaries.

Community
Advanced
jomeswangjomeswang
58

agnes-ai-skill

Execute multimodal AI tasks for text, image, and video generation via agnes-ai-cli.

Community
Intermediate
jangtrinhjangtrinh

ck:ai-multimodal

Process images, audio, video, and documents with Gemini and MiniMax APIs.

Community
Advanced