Claude Code skill to delegate prompts to Google Gemini CLI for code analysis, refactoring, codebase investigation, and multi-model collaboration
Enable Claude Code to invoke the Gemini CLI (gemini -p and session resumes) for automated code analysis, refactoring, codebase investigation, and multi-model collaboration workflows.
PATH.gemini --version; resolve any errors before using the skill.This repository is structured as a Claude Code Plugin with a marketplace. You can install it as a plugin (recommended) or extract it as a standalone skill.
Install via Claude Code's plugin system for automatic updates:
/plugin marketplace add integralmedia1/skill-gemini
/plugin install skill-gemini@skill-gemini
Extract the skill folder manually:
git clone --depth 1 [email protected]:integralmedia1/skill-gemini.git /tmp/skill-gemini-temp && \
mkdir -p ~/.claude/skills && \
cp -r /tmp/skill-gemini-temp/plugins/skill-gemini/skills/gemini ~/.claude/skills/gemini && \
rm -rf /tmp/skill-gemini-temp
By default, this skill suppresses debug/progress output (stderr) using 2>/dev/null to avoid bloating Claude Code's context window. If you want to see debug output for troubleshooting, explicitly ask Claude to show it (uses the -d flag).
User prompt:
Use gemini to review this project's authentication logic for security issues.
Claude Code response: Claude will activate the Gemini skill and:
gemini-3.1-pro-preview, gemini-3-pro-preview, gemini-3-flash-preview, etc.) unless already specified in your prompt.plan, auto_edit, yolo, or default) unless already specified.plan for read-only analysis).gemini -m gemini-3-pro-preview \
--approval-mode plan \
-o text \
-p "Review the authentication logic in this project for security vulnerabilities..." 2>/dev/null
Result: Claude will summarize the Gemini analysis output, highlighting key findings and asking if you'd like to continue with follow-up actions.
| Model | Best For |
|---|---|
gemini-3.1-pro-preview | Most capable, complex reasoning |
gemini-3-pro-preview | Default, strong general purpose |
gemini-3-flash-preview | Fast tasks, simple analysis |
gemini-2.5-pro | Fallback for complex tasks |
gemini-2.5-flash | Balanced speed and quality |
| Mode | Behavior |
|---|---|
plan | Read-only, no file modifications (default for analysis) |
auto_edit | Auto-approves file edits, prompts for shell commands |
yolo | Auto-approves all actions (recommended for full delegation) |
default | Prompts for approval on each action |
Gemini sessions persist and can be resumed:
# Resume most recent session
gemini -r latest -p "continue with..."
# List all sessions
gemini --list-sessions
# Resume specific session by index
gemini -r 3 -p "follow up on..."
See plugins/skill-gemini/skills/gemini/SKILL.md for complete operational instructions, CLI options, and workflow guidance.
MIT License - see LICENSE for details.
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub integralmedia1/skill-gemini --plugin skill-geminiIntegral Media brand style guide for HTML documents, reports, presentations, and Google Sheets formatting
Claude Code skill to delegate prompts to OpenAI Codex CLI for code analysis, refactoring, code review, and automated editing
Enables Claude Code to manage Gemini CLI as an intern. Claude acts as manager/architect while Gemini does all coding work.
Integrate Gemini CLI for long-context code exploration from Claude Code and Codex
Use Gemini CLI from Claude Code to review code or delegate tasks.
v9.44.1 — Patch release for Gemini environment/version detection and qwen auth gating. Run /octo:setup.
Persistent file-based planning for AI coding agents. Crash-proof markdown plans (task_plan.md, findings.md, progress.md) that survive context loss and /clear, with an opt-in completion gate and multi-agent shared state. Manus-style. Works with Claude Code, Codex CLI, Cursor, Kiro, OpenCode and 60+ agents via the SKILL.md standard. Includes Arabic, German, Spanish, and Chinese (Simplified and Traditional).
Claude harness - A harness for solo developers (Vibecoders) to handle full-cycle contract development.