skills.rest
virahitvin8
virahitvin8COMMUNITY
Explore all skills by this author →
GitHub

baoyu-danger-gemini-web

Generates text and images through a reverse-engineered Gemini Web API client.

2|Updated May 30, 2026
Search Tags:#typescript#cli#image generation#gemini#web api#text generation#chrome cdp
One-click install
npx skills add https://github.com/virahitvin8/crafty-gis --skill baoyu-danger-gemini-web-virahitvin8
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: baoyu-danger-gemini-web
Source: https://github.com/virahitvin8/crafty-gis/tree/main/GIT_STAR/assignment-generator/antigravity-skills-main/antigravity-skills-main/skills/baoyu-danger-gemini-web
Command: npx skills add https://github.com/virahitvin8/crafty-gis --skill baoyu-danger-gemini-web-virahitvin8

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve? It provides programmatic access to Gemini's text and image generation capabilities without an official API key, using browser-authenticated sessions to run prompts, generate images, and maintain multi-turn conversations from the command line. ## Core Features & Use Cases - Text and Image Generation: Send prompts to Gemini models (gemini-3-pro, gemini-3-flash, gemini-3.1-pro-preview) and save generated images to disk. - Vision Input and Multi-Turn Chat: Attach reference images for vision tasks and persist conversation state across calls via session IDs. - Browser-Based Authentication: Automatically harvests Google session cookies from a local Chrome/Chromium instance via CDP, with cached cookie refresh and rotation. - Use Case: An agent pipeline needs an image generation backend; it invokes the CLI with a prompt and --image flag, and the script returns a saved PNG path or JSON output. ## Quick Start Ask the agent to generate an image of a cute cat with the Gemini web skill and save it as cat.png.

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 generate an image with Gemini from the command line?▼

Run the main.ts script with bun or npx, passing a prompt and the --image flag with an output path. The script authenticates via cached Google cookies and saves the first generated image to the specified file.

How does Gemini Web API authentication work without an API key?▼

The client extracts Google session cookies (__Secure-1PSID, __Secure-1PSIDTS) from a local Chrome or Chromium instance using the Chrome DevTools Protocol. Cookies are cached to a file and automatically rotated to keep the session valid.

Can I use reference images for Gemini vision input?▼

Yes, pass one or more image files with the --reference or --ref flag. The script uploads the files and includes them with your prompt, so the model can describe or create variations of the provided images.

Which Gemini models does this client support?▼

It supports gemini-3-pro (default), gemini-3-flash, gemini-3-flash-thinking, and gemini-3.1-pro-preview. Select a model with the --model flag when invoking the script.

Why does Gemini cookie authentication fail or expire?▼

The __Secure-1PSIDTS cookie expires frequently, causing AuthError failures. Run the script with --login to force a browser-based cookie refresh, or set a dedicated Chrome profile directory to avoid conflicts with running sessions.

What are the limitations of using a reverse-engineered Gemini API?▼

The API is undocumented and can break when Google changes response formats, and accounts may hit usage limits or temporary IP blocks. The skill requires explicit user consent and is not suitable for production or ToS-sensitive use.

Related Skills

Explore More Software Engineering Skills→
abhishekmmgnabhishekmmgn

setup-browser-cookies

Import Chromium cookies into a headless Playwright session for QA testing.

Community
Intermediate
inference-shinference-sh
688

ai-content-pipeline

Orchestrate multi-step AI content pipelines for image, video, audio, and text.

Official
Advanced
kaiganikaigani
30

Shot Image Generator Skill

Generate shot images by combining reference assets with shot specifications via AI APIs.

Community
Advanced
heyu-aiheyu-ai

verify-gemini-models

Verify Gemini model availability and functionality via REST and WebSocket calls.

Official
Advanced