collaborating-with-gemini

Route Claude prompts to the Gemini CLI for cross-model coding collaboration.

11|3|Updated Dec 16, 2025
One-click install
npx skills add https://github.com/GuDaStudio/collaborating-with-gemini --skill collaborating-with-gemini-gudastudio
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: collaborating-with-gemini
Source: https://github.com/GuDaStudio/collaborating-with-gemini/tree/main
Command: npx skills add https://github.com/GuDaStudio/collaborating-with-gemini --skill collaborating-with-gemini-gudastudio

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Delegates coding tasks to Gemini CLI to enable cross-model collaboration and accelerate prototyping, debugging, and code review.

Core Features & Use Cases

  • Multi-turn sessions: Maintain conversation context across interactions via SESSION_ID.
  • Sandboxed execution: Optional sandbox mode for isolated execution.
  • JSON output: Structured responses for easy parsing and integration.
  • Cross-platform: Windows path escaping handled automatically.

Quick Start

Run python scripts/gemini_bridge.py --cd "/path/to/project" --PROMPT "Your task" to start a Gemini-assisted workflow.

Frequently Asked Questions about collaborating-with-gemini

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

FAQPage Schema
How do I use Gemini CLI for coding tasks from another AI model?

Cross-model coding collaboration routes your prompts to the Gemini CLI, enabling prototyping and debugging by returning structured JSON outputs containing session IDs and agent messages.

Can I maintain conversation context across multiple Gemini CLI sessions?

Yes, multi-turn sessions maintain conversation context across interactions via the SESSION_ID flag, allowing continuous debugging and code review workflows with Gemini.

Do I need to install Gemini CLI before running cross-model collaboration scripts?

Yes, Gemini CLI installation is required before executing the bridge script, which accepts --PROMPT, --cd, and --SESSION_ID flags to orchestrate tasks.

What is the best way to execute Gemini CLI prompts in an isolated environment?

Sandboxed execution provides an optional isolated environment for running Gemini CLI tasks, ensuring safe prototyping and algorithm implementation.

Does cross-model collaboration with Gemini CLI work on Windows?

Yes, Windows path escaping is handled automatically when you specify the project directory using the --cd flag in the Gemini bridge script.

Why does my Gemini CLI integration return structured JSON data?

Cross-model coding collaboration outputs structured JSON containing SESSION_ID and agent_messages, ensuring easy parsing and integration for downstream automation workflows.