gemini-cli

name	gemini-cli
description	Google Gemini CLI orchestration for AI-assisted development. Capabilities: second opinion/cross-validation, real-time web search (Google Search), codebase architecture analysis, parallel code generation, code review from different perspective, image generation, SVG/animation generation, multimodal screenshot-to-code. Actions: query, search, analyze, generate, review, visualize with Gemini. Keywords: Gemini CLI, second opinion, cross-validation, Google Search, web research, current information, parallel AI, code review, architecture analysis, gemini prompt, AI comparison, real-time search, alternative perspective, code generation, image gen, UI mockup, SVG, animation, multimodal. Use when: needing second AI opinion, searching current web information, analyzing codebase architecture, generating code in parallel, getting alternative code review, researching current events/docs, generating UI mockups, creating SVG animations, screenshot-to-code workflows.
allowed-tools	["Bash","Read","Write","Grep","Glob"]

Gemini CLI Integration Skill

This skill enables Codex to effectively orchestrate Gemini CLI (v0.16.0+) with Gemini 3.1 Pro for code generation, review, analysis, image generation, and specialized tasks.

When to Use This Skill

Ideal Use Cases

1. Second Opinion / Cross-Validation

   • Code review after writing code (different AI perspective)
   • Security audit with alternative analysis
   • Finding bugs Codex might have missed

2. Google Search Grounding

   • Questions requiring current internet information
   • Latest library versions, API changes, documentation updates
   • Current events or recent releases

3. Codebase Architecture Analysis

   • Use Gemini's codebase_investigator tool
   • Understanding unfamiliar codebases
   • Mapping cross-file dependencies

4. Parallel Processing

   • Offload tasks while continuing other work
   • Run multiple code generations simultaneously
   • Background documentation generation

5. Specialized Generation

   • Test suite generation
   • JSDoc/documentation generation
   • Code translation between languages

6. Image Generation (Gemini 3.1 Pro)

   • UI component mockups with accompanying React/TSX code
   • Complex SVG diagrams and animations that benefit from visual preview
   • Screenshot-to-code: pass a UI screenshot and get corrected code back

7. SVG / Animation Workflows

   • Complex SVG illustrations requiring visual precision
   • CSS keyframe animations with multimodal verification
   • Architecture diagrams as editable SVG

When NOT to Use

• Simple, quick tasks (overhead not worth it)
• Tasks requiring immediate response (rate limits cause delays)
• When context is already loaded and understood
• Interactive refinement requiring conversation

Core Instructions

1. Verify Installation

command -v gemini || which gemini

2. Basic Command Pattern

gemini "[prompt]" --yolo -o text 2>&1

Key flags:

• --yolo or -y: Auto-approve all tool calls
• -o text: Human-readable output (preferred — avoids JSON envelope overhead)
• -o json: Structured output with stats
• -m gemini-3-flash: Use faster model for simple tasks

3. Critical Behavioral Notes

YOLO Mode Behavior: Auto-approves tool calls but does NOT prevent planning prompts. Gemini may still present plans and ask "Does this plan look good?" Use forceful language:

• "Apply now"
• "Start immediately"
• "Do this without asking for confirmation"

Rate Limits: Free tier has 60 requests/min, 1000/day. CLI auto-retries with backoff. Expect messages like "quota will reset after Xs".

Output Truncation at 65K: Gemini 3.1 Pro and Gemini 3 Flash both cap output at ~65K tokens. Long responses may be silently truncated. Mitigations:

• Set explicit max output tokens in the prompt: "Respond in chunks of no more than 4000 lines."
• Chunk requests that are expected to produce >32K output tokens — split by file, section, or phase.
• Use -o text (not stream-json) to make truncation visible rather than silent.

4. Output Processing

For JSON output (-o json), parse:

{
  "response": "actual content",
  "stats": {
    "models": { "tokens": {...} },
    "tools": { "byName": {...} }
  }
}

Quick Reference Commands

Code Generation

gemini "Create [description] with [features]. Output complete file content." --yolo -o text

Code Review

gemini "Review [file] for: 1) features, 2) bugs/security issues, 3) improvements" -o text

Bug Fixing

gemini "Fix these bugs in [file]: [list]. Apply fixes now." --yolo -o text

Test Generation

gemini "Generate [Jest/pytest] tests for [file]. Focus on [areas]." --yolo -o text

Documentation

gemini "Generate JSDoc for all functions in [file]. Output as markdown." --yolo -o text

Architecture Analysis

gemini "Use codebase_investigator to analyze this project" -o text

Web Research

gemini "What are the latest [topic]? Use Google Search." -o text

Faster Model (Simple Tasks)

gemini "[prompt]" -m gemini-3-flash -o text

Image Generation

gemini "Generate a UI mockup image for [component]. Include React/TSX implementation using Next.js 15, Tailwind, shadcn/ui." --yolo -o text

SVG / Animation

gemini "Create an SVG illustration of [subject]. Output complete SVG markup with embedded CSS animations." --yolo -o text

Error Handling

Rate Limit Exceeded

• CLI auto-retries with backoff
• Use -m gemini-3-flash for lower priority tasks
• Run in background for long operations

Command Failures

• Check JSON output for detailed error stats
• Verify Gemini is authenticated: gemini --version
• Check ~/.gemini/settings.json for config issues

Validation After Generation

Always verify Gemini's output:

• Check for security vulnerabilities (XSS, injection)
• Test functionality matches requirements
• Review code style consistency
• Verify dependencies are appropriate

Integration Workflow

Standard Generate-Review-Fix Cycle

# 1. Generate
gemini "Create [code]" --yolo -o text

# 2. Review (Gemini reviews its own work)
gemini "Review [file] for bugs and security issues" -o text

# 3. Fix identified issues
gemini "Fix [issues] in [file]. Apply now." --yolo -o text

Background Execution

For long tasks, run in background and monitor:

gemini "[long task]" --yolo -o text 2>&1 &
# Monitor with BashOutput tool

Gemini's Unique Capabilities

These tools are available only through Gemini:

1. google_web_search - Real-time internet search via Google
2. codebase_investigator - Deep architectural analysis
3. save_memory - Cross-session persistent memory
4. Image generation - Inline image synthesis (Gemini 3.1 Pro); generate mockups and diagrams alongside code
5. Multimodal input - Accepts screenshot/image input for visual-to-code tasks

Configuration

Project Context (Optional)

Create .gemini/GEMINI.md in project root for persistent context that Gemini will automatically read.

Session Management

List sessions: gemini --list-sessions Resume session: echo "follow-up" | gemini -r [index] -o text

See Also

• reference.md - Complete command and flag reference
• templates.md - Prompt templates for common operations
• templates-creative.md - Image, SVG, and animation prompt templates
• patterns.md - Advanced integration patterns
• tools.md - Gemini's built-in tools documentation