second-opinion

Review code changes, branch diffs, or commits using external LLM CLIs.

6.5k|561|Updated Jan 14, 2026
One-click install
npx skills add https://github.com/trailofbits/skills --skill second-opinion-trailofbits
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: second-opinion
Source: https://github.com/trailofbits/skills/tree/main/plugins/second-opinion/skills/second-opinion
Command: npx skills add https://github.com/trailofbits/skills --skill second-opinion-trailofbits

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 an external code review from LLMs (OpenAI Codex or Google Gemini CLI), offering a second opinion for code changes, branch diffs, or specific commits.

Core Features & Use Cases

  • External LLM Code Reviews: Runs code reviews using OpenAI Codex or Google Gemini CLI.
  • Review Scopes: Supports uncommitted changes, branch diffs, or specific commits.
  • Use Case: Use when you need an additional review from a different model before merging a pull request.

Quick Start

To get a review, use the command: /second-opinion

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 AI-powered second opinion on my code changes?

To get a second opinion on code changes, use external LLMs like OpenAI Codex or Google Gemini CLI to review uncommitted diffs or specific commits, providing an independent analysis before merging.

Can I use OpenAI Codex and Google Gemini CLI to review branch diffs?

Yes, you can use OpenAI Codex and Google Gemini CLI to review branch diffs. The Skill operates on uncommitted changes, branch diffs, or specific commits to provide external LLM code analysis.

Do I need to install external LLM CLI tools to run an AI code review?

Yes, you need to install the respective CLI tools and have access to the LLM APIs. The Skill requires dependencies like @openai/codex and @google/gemini-cli to conduct the external code reviews.

When should I use an external LLM for code analysis instead of my default model?

You should use an external LLM for code analysis when you need an additional review from a different model before merging a pull request, ensuring an independent second opinion on your code changes.

What is the best way to review specific commits with an AI before merging?

The best way to review specific commits with an AI is to run an external code review using OpenAI Codex or Google Gemini CLI, which analyzes the commit diff and provides a second opinion.