# Reasoning Quality Comparison

> Compare model outputs for evidence use, assumptions, edge cases, and decision usefulness.

- Skill: `conectlens/reasoning-quality-comparison` (Agent Skill)
- Install (CLI): `npx skillmds@latest add conectlens/reasoning-quality-comparison`
- Raw SKILL.md: https://api.skillmd.com/api/skills/conectlens/reasoning-quality-comparison/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: conectlens (https://skillmd.com/u/conectlens)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/conectlens/reasoning-quality-comparison

---


# Reasoning Quality Comparison

Compare `[[outputs]]` across: factual grounding, assumption handling, edge-case coverage, actionability, calibration, and concise reasoning.

Return a score table and a short winner rationale.