julien-workflow-advice-gemini

majiayu000's avatarfrom majiayu000

Get Gemini CLI's opinion on code, architecture, or implementation. Use when you want a second AI perspective during coding sessions.

⭐0stars🔀0forks📁View on GitHub🕐Updated Jan 5, 2026
[Code Review]

When & Why to Use This Skill

This Claude skill integrates the Google Gemini CLI to provide expert-level feedback on code quality, architectural decisions, and implementation strategies. By leveraging Gemini's 1M token context window, it offers developers a powerful second AI perspective to validate logic, optimize performance, and refine software architecture directly within their coding sessions, ensuring more robust and maintainable codebases.

Use Cases

  • Automated Code Review: Requesting detailed feedback and actionable improvement suggestions for specific source files to identify bugs or technical debt before a commit.
  • Architectural Decision Support: Comparing different technical approaches or infrastructure choices, such as evaluating Redis versus in-memory caching for specific use cases.
  • Implementation Logic Validation: Getting a second opinion on complex algorithms or new patterns to ensure they align with industry best practices and performance standards.
  • Large-Scale Context Analysis: Utilizing Gemini's massive context window to analyze extensive code files or multi-file modules that require deep situational awareness.
namejulien-workflow-advice-gemini
descriptionGet Gemini CLI's opinion on code, architecture, or implementation. Use when you want a second AI perspective during coding sessions.

Ask Gemini

Get feedback from Google's Gemini CLI on code, architecture decisions, or implementation approaches.

Prerequisites

  • Gemini CLI installed: npm install -g @google/gemini-cli
  • Authenticated: run gemini once to login with Google account
  • Verify: gemini --version

When to Use

  • Want a second opinion on code quality
  • Need architectural review
  • Comparing implementation approaches
  • Code review before commit

How to Invoke

The user will ask something like:

  • "ask gemini what it thinks about this code"
  • "get gemini's opinion on this approach"
  • "demande à gemini de reviewer ce fichier"

Execution

For file review

gemini "Review this code and provide 3 specific improvements: $(cat <file_path>)"

For architectural questions

gemini "<user's question about architecture or approach>"

For comparing approaches

gemini "Compare these two approaches and recommend which is better: Approach A: <desc> vs Approach B: <desc>"

Output Format

Present Gemini's response clearly to the user. If Gemini suggests improvements, summarize them as actionable items.

Examples

File review

User: "demande à gemini ce qu'il pense du semantic-skill-router.py"

gemini "Review this Python script for a semantic routing system. List 3 improvements for production use: $(cat scripts/semantic-skill-router.py)"

Architecture question

User: "ask gemini if I should use Redis or in-memory cache"

gemini "Compare Redis vs in-memory caching for a CLI tool that routes user prompts. Consider: startup time, complexity, persistence needs."

Troubleshooting

Error Cause Fix
gemini: command not found CLI not installed npm install -g @google/gemini-cli
Authentication required Not logged in Run gemini interactively, login with Google
Response timeout Large file or slow network Reduce file size or retry
Rate limit exceeded Too many requests Wait 1 minute, retry

Notes

  • Gemini has 1M token context window
  • Default model: Gemini 2.5 Pro
  • Timeout: allow up to 60s for response
  • If response is cut off, Gemini may still be processing

Skill Chaining

Input Expected

  • File path to review, OR
  • Architecture/design question from user

Output Produced

  • Format: Markdown feedback from Gemini
  • Side effects: None (read-only)

Compatible Skills

  • Can be used alongside julien-workflow-advice-codex for multiple AI opinions
  • Use after writing code, before commit

Tools Used

  • Bash (usage: run gemini CLI command, timeout 60s)