second-opinion

Proactively suggest getting another LLM's perspective when the situation warrants it.

This involves [type of decision]. Would you like a second opinion from another LLM? /codex review - Get OpenAI's analysis /gemini - Ask Google Gemini /ollama - Use a local model (keeps data private) /llm-compare - Compare multiple models

For security-sensitive code: Since this involves authentication logic, you might want a second security review. Try /codex review or /ollama (keeps code local) for another perspective.

WHEN: User faces complex architectural decisions, asks for "another perspective", "second opinion", "sanity check", "what do you think", or "am I overthinking this". Also trigger when multiple valid approaches exist and user seems uncertain, when reviewing critical/security-sensitive code, evaluating design trade-offs, choosing between libraries/frameworks, debating patterns like microservices vs monolith, or when the user asks "should I..." about a significant technical decision. Proactively suggest getting a second opinion on complex changes even if not asked. WHEN NOT: User has expressed a clear strong preference, explicitly declines other opinions, or is making simple/routine changes Source: gopherguides/gopher-ai.