second-opinion

Fetch alternative model perspectives via /codex, /gemini, /ollama, and /llm-compare commands.

19|1|Updated Dec 16, 2025
One-click install
npx skills add https://github.com/gopherguides/gopher-ai --skill second-opinion-gopherguides
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: second-opinion
Source: https://github.com/gopherguides/gopher-ai/tree/main/plugins/llm-tools/skills/second-opinion
Command: npx skills add https://github.com/gopherguides/gopher-ai --skill second-opinion-gopherguides

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Proactively surface second opinions from another model when users face architectural decisions, complex trade-offs, or security-sensitive code reviews, helping verify approaches before committing to a design.

Core Features & Use Cases

  • Proposes cross-model perspectives for strategic design input or contentious patterns.
  • Provides concrete commands to obtain perspectives: /codex review, /gemini <specific question>, /ollama <question>, /llm-compare <question>.
  • Includes guidance on privacy-sensitive contexts (e.g., using /ollama to keep data local) when needed.

Quick Start

Ask for a second opinion when you want a broader perspective on a design decision.

Frequently Asked Questions about second-opinion

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

FAQPage Schema
How do I get a second opinion from another LLM during a code review?

Use commands like /codex review, /gemini <question>, or /llm-compare <question> to fetch alternative perspectives from multiple models during a code review without interrupting your ongoing chat workflow.

What is the best way to sanity-check an architectural design decision?

Requesting a second opinion proactively surfaces alternative perspectives from multiple models to verify approaches and identify trade-offs before you commit to an architectural design decision.

Can I use local models for security reviews to keep data private?

Yes, you can use the /ollama <question> command to route your security review query to a local model, keeping sensitive data private while still obtaining architectural perspectives.

Does multi-model comparison work without interrupting my current chat workflow?

Yes, multi-model comparison integrates seamlessly with your current chat workflow, fetching diverse perspectives on complex trade-offs without interrupting ongoing development tasks.

When do I need a cross-model perspective for software engineering trade-offs?

You need a cross-model perspective when facing contentious patterns, security-sensitive code reviews, or performance trade-offs, ensuring strategic design input is verified across multiple models.