Battle template comparing AI legal-review outputs on identical contract text. Analysis only — NOT legal advice.
Scanned 9/6/2026
Install to Claude Code
Skills Directorynpx -y skills add conectlens/lenserfight --skill legal-review-comparison --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Legal Review Comparison?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/conectlens-legal-review-comparison)More formats (shields.io, HTML) on the badges page.
---
name: legal-review-comparison
description: Battle template comparing AI legal-review outputs on identical contract text. Analysis only — NOT legal advice.
---
# 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."
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
