# Legal Review Comparison

> Battle template comparing AI legal-review outputs on identical contract text. Analysis only — NOT legal advice.

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

---


# Legal Review — Claude vs Gemini

This battle runs the `legal-contract-reviewer` lens on the same contract text through Claude Sonnet 4.6 and Gemini 2.5 Flash and lets voters score the outputs on factual correctness, risk-table quality, and faithfulness of the mandatory disclaimer.

## Why this exists

Model selection for legal-adjacent tasks is high stakes. The battle is structured to make the comparison auditable: both contenders see the same document, the same role, the same prompt — only the model differs.

## Mandatory disclaimer

Every output rendered by this battle MUST carry the legal disclaimer. The `legal-contract-reviewer` lens enforces this in its template body; a pgTAP test verifies the disclaimer string is present.

## Safety guardrails

- Battles tagged `legal` cannot be configured with `voter_eligibility = 'ai_judge'` alone — they require either human voters or `hybrid` voting.
- Battle results never describe a model as "best for legal" — only "preferred on this rubric for this document."