second-opinion

Evaluate code changes with external LLMs like Codex or Gemini.

Updated Jun 9, 2026
One-click install
npx skills add https://github.com/iiammae/opero --skill second-opinion-iiammae
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: second-opinion
Source: https://github.com/iiammae/opero/tree/main/.agents/skills/second-opinion
Command: npx skills add https://github.com/iiammae/opero --skill second-opinion-iiammae

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @openai/codex, @google/gemini-cli, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides a second opinion on code changes by running them through external LLMs (Codex or Gemini), offering a fresh perspective on potential issues.

Core Features & Use Cases

  • External LLM Code Review: Run code changes through OpenAI Codex or Google Gemini CLI for independent reviews.
  • Scope Customization: Review uncommitted changes, branch diffs, or specific commits based on user input.
  • Use Case: Use this Skill when preparing to merge a pull request and need an additional layer of code analysis before merging.

Quick Start

Use the /second-opinion command to initiate a code review.

Frequently Asked Questions about second-opinion

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

FAQPage Schema
How do I get an LLM code review on uncommitted changes before a merge?

Yes, you can use this Skill for branch diff code analysis by running uncommitted changes, branch diffs, or specific commits through external tools like Codex or Gemini to receive an independent review before merging.

Do I need an API key to run external LLM code analysis on my commits?

To run external LLM code analysis, you need valid API keys or subscriptions because the Skill requires installed tools like OpenAI Codex or Google Gemini CLI to evaluate your code changes independently.

What is the best way to get a second opinion on code from a different LLM?

The best way to get a second opinion on code from a different LLM is using this Skill to pass your code changes to external tools like Codex or Gemini, which provides a fresh perspective on potential issues.

Can I customize the review scope when running code analysis through Gemini or Codex?

Yes, you can customize the code analysis review scope by specifying uncommitted changes, branch diffs, or specific commits as input for the external LLM tools to evaluate.

Why use external LLM tools for code review instead of the default analysis?

Using external LLM tools for code review provides an additional independent review layer, offering a fresh perspective from different models like Codex or Gemini to catch potential issues missed by default analysis.