second-opinion

Execute external LLM code reviews using Codex CLI and Gemini CLI.

17|Updated May 24, 2014
One-click install
npx skills add https://github.com/blacktop/dotfiles --skill second-opinion-blacktop
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: second-opinion
Source: https://github.com/blacktop/dotfiles/tree/main/ai/skills/second-opinion
Command: npx skills add https://github.com/blacktop/dotfiles --skill second-opinion-blacktop

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill provides an external, AI-driven code review to identify potential issues and offer alternative perspectives on code changes, enhancing code quality and reducing risks.

Core Features & Use Cases

  • Multi-Model Review: Leverages Codex CLI, Gemini CLI, or both for comprehensive code analysis.
  • Flexible Scope: Analyzes uncommitted changes, branch diffs, specific commits, or GitHub pull requests.
  • Use Case: Before merging a critical feature branch, use this Skill to get an independent review from both Codex and Gemini, focusing on security and performance, to catch any overlooked vulnerabilities or inefficiencies.

Quick Start

Use the second-opinion skill to get a review of your uncommitted changes using both Codex and Gemini.

Frequently Asked Questions about second-opinion

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

FAQPage Schema
How do I run an AI code review on uncommitted changes before merging?

To perform an AI code review on uncommitted changes, use this Skill to execute external LLM analysis via Codex CLI and Gemini CLI. It evaluates code changes to identify potential issues in correctness, security, performance, and maintainability.

Can I review branch diffs and specific commits with external LLMs?

Yes, you can review branch diffs and specific commits with external LLMs. This Skill supports analyzing various scopes including uncommitted changes, branch diffs, individual commits, and GitHub pull requests using Codex CLI and Gemini CLI.

What is the benefit of using multiple LLMs for code analysis?

Using multiple LLMs for code analysis provides an independent, external perspective on code changes. By leveraging both Codex and Gemini, you get a comprehensive review that catches overlooked vulnerabilities and inefficiencies, enhancing overall code quality and reducing risks.

Does this AI code review tool work with GitHub pull requests?

Yes, this AI code review tool works with GitHub pull requests. It executes external LLM code reviews using Codex CLI and Gemini CLI to analyze pull requests and identify potential issues across correctness, security, performance, and maintainability.

What do I need to set up before using external LLMs to review code?

You need to have Codex CLI and Gemini CLI available in your environment to use this Skill. These external tools are leveraged to execute the AI-driven code reviews across various scopes like uncommitted changes, branch diffs, commits, and pull requests.

When should I use an external LLM code review instead of standard linters?

You should use an external LLM code review when you need an independent perspective on potential issues related to correctness, security, performance, and maintainability. It is ideal before merging critical feature branches to catch overlooked vulnerabilities that standard linters might miss.