HN Showcase
Back to browse
GitHub Repository
0 stars

Second opinion – A skill to query different models

by a_c·Jun 30, 2026·4 points·2 comments
Visit ProjectView on HN

AI Analysis

●●SolidNiche GemBig Brain

Cross-examine AI suggestions mid-session by querying different models without leaving your workflow.

Strengths
  • •Session persistence across harnesses enables meaningful follow-ups with the second model
  • •Gell-Mann Amnesia framing identifies a real AI verification problem developers face
  • •Works with both Claude Code and opencode without requiring new infrastructure
Weaknesses
  • •Only supports two harnesses; opencode-to-opencode cross-checking remains untested
  • •Fundamentally wraps existing CLI tools rather than introducing novel architecture
Target Audience

Developers using Claude Code or opencode CLI tools

Post Description

Make this skill to help me cross examine suggestions made by claude to other Claude or opencode supported models mid session. It compiles relevant context, consult a second opinion for me and support following up with the second opinion. A pattern that I find quite useful.

Currently it supports claude to claude, claude to opencode and opencode to claude invocation. These are the two harnesses I use.

Similar Projects

AI/ML●●Solid

Open-geo – Skill for Claude Code which shows your AI Visibility

Browser-based GEO tracking beats API scraping for real AI answer visibility.

Niche GemBig Brain
pupok46
108d ago