baoyu-danger-gemini-web

Generate text and images via Gemini Web API with session management.

Updated May 18, 2018
One-click install
npx skills add https://github.com/812lcl/dotfiles --skill baoyu-danger-gemini-web-812lcl
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: baoyu-danger-gemini-web
Source: https://github.com/812lcl/dotfiles/tree/main/.agents/skills/baoyu-danger-gemini-web
Command: npx skills add https://github.com/812lcl/dotfiles --skill baoyu-danger-gemini-web-812lcl

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires baoyu-chrome-cdp, and includes scripts (resource) components.

What problem does it solve?

Gemini Web API integration typically requires building a client capable of text and image generation with session management, consent checks, and cookie handling. This skill encapsulates that workflow and provides a ready-to-use CLI client.

Core Features & Use Cases

  • Text generation: Generate coherent text responses via Gemini Web API.
  • Image generation: Create images from prompts or reference inputs.
  • Vision input & multi-turn conversations: Support for reference images and multi-turn sessions, with persistent session state.
  • The solution includes consent checks and session handling to ensure compliant usage.

Quick Start

Run the main script with a prompt to generate content using Gemini Web API.

Frequently Asked Questions about baoyu-danger-gemini-web

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

FAQPage Schema
How do I automate text and image generation using the Gemini Web API?

Automating Gemini Web API text and image generation requires a client to manage sessions, consent checks, and token handling. This script provides a ready-to-use CLI to execute single-turn and multi-turn prompts safely.

Can I use reference images for multi-turn conversations with the Gemini Web API?

Yes, you can use reference images for multi-turn conversations with the Gemini Web API. The script maintains persistent session state to support vision inputs across continuous interactions.

Do I need to handle consent checks and session management manually for Gemini Web API automation?

No, manual consent checks and session management are not required. The script encapsulates cookie handling, token management, and consent compliance to ensure safe automated operation.

What is the best way to maintain persistent session state across multiple Gemini Web API prompts?

The best way to maintain persistent session state is using an automation script that manages cookies and session tokens. This ensures continuous multi-turn conversations without losing context.

Does the Gemini Web API client support both single-turn and multi-turn image generation?

Yes, the Gemini Web API client supports both single-turn image generation from prompts and multi-turn conversations using reference images, handling the necessary token and session logic internally.