Gemini

This lets Claude hand off tasks to the Gemini CLI when you explicitly ask for it. It's built around a careful workflow: convert your request to English, run gemini in non-interactive mode with the right flags, and return the output for you to review before applying anything. The skill includes model selection guidance (Flash for speed and iteration, Pro for complex reasoning), supports approval modes and session resuming, and treats all Gemini output as untrusted until you confirm. Useful when you want broad codebase analysis or architectural deep dives and have Gemini CLI installed. The mandatory English translation step is worth noting if you work in other languages.

skills.sh installs: 3.6K
GitHub stars: 369
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add giuseppe-trisciuoglio/developer-kit --skill gemini --agent claude-code

Installs into .claude/skills of the current project.

Files

Gemini CLI Delegation

Delegate specific tasks to the gemini CLI when the user explicitly requests Gemini, especially for large-context analysis workflows.

Overview

This skill provides a safe and consistent workflow to:

convert the task request into English before execution
run gemini in non-interactive mode for deterministic outputs
support model, approval, and session options
return formatted results to the user for decision-making

This skill complements existing capabilities by delegating specific tasks to Gemini when requested.

When to Use

Use this skill when:

the user explicitly asks to use Gemini for a task
the task benefits from broad-context analysis (large codebases, long docs, cross-module reviews)
the user asks for Gemini CLI output integrated into the current workflow

Typical trigger phrases: