General-purpose cross-model review — Review LLM independently reviews any research artifact, outputs structured scores, wiki entity mapping, and improvement suggestions

What problem does it solve?

This Skill helps you objectively evaluate research artifacts by producing structured scores, prioritized weaknesses with fixes, and a mapping of findings to wiki entities—without directly modifying your wiki.

Core Features & Use Cases

• Cross-model independent review: Uses a dedicated Review LLM with a reviewer-independence principle to avoid leaking pre-judgments.
• Difficulty + focus controls: Supports standard, hard (multi-round rebuttal), and adversarial (fatal-flaw search) modes, with focuses on method, evidence, writing, or completeness.
• Wiki entity mapping output: Identifies which ideas/methods need strengthening and which knowledge gaps were discovered, enabling downstream refinement.

Quick Start

Run the review on an experiment plan using standard difficulty and comprehensive focus by giving the command: review /your-artifact-slug --difficulty standard --focus comprehensive.