review

Evaluate research hypotheses through multiple review modes with automated scoring.

Updated Jul 3, 2026
One-click install
npx skills add https://github.com/GiorgioRicciardiello/LabBrain --skill review-giorgioricciardiello
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/GiorgioRicciardiello/LabBrain/tree/main/core/.claude/skills/review
Command: npx skills add https://github.com/GiorgioRicciardiello/LabBrain --skill review-giorgioricciardiello

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill addresses the need for a structured, efficient review process for evaluating hypotheses, offering multiple analytical modes to ensure comprehensive evaluation.

Core Features & Use Cases

  • Multi-Mode Review: Provides six distinct review modes to assess hypotheses from various perspectives.
  • Automated Scoring: Computes an aggregate score based on predefined criteria, including correctness, testability, novelty, and impact.
  • Review History Tracking: Maintains a detailed record of each review for traceability and historical analysis.
  • Use Case: Imagine you have a set of research hypotheses that need to be evaluated. Use this Skill to review each hypothesis using the literature review mode, and then use the tournament-informed review mode to compare them against previous meta-reviews.

Quick Start

Review all unreviewed hypotheses for the active research goal using the tournament-informed review mode.

Frequently Asked Questions about review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
What is the best way to review research hypotheses against existing meta-reviews?

Reviewing research hypotheses against existing meta-reviews is best handled using a tournament-informed review mode, which evaluates new hypotheses against previous meta-reviews to ensure comprehensive historical analysis and traceability.

How does multi-mode review work for structured hypothesis analysis?

Multi-mode review for structured hypothesis analysis works by providing six distinct analytical perspectives, such as a literature review mode, to assess hypotheses comprehensively from various angles.

Can I track the history of automated hypothesis evaluations?

You can track the history of automated hypothesis evaluations because the review process maintains a detailed record of each review for traceability and historical analysis.

What are the limitations of using automated scoring for research analysis?

A limitation of automated scoring for research analysis is that it relies entirely on predefined criteria for correctness, testability, novelty, and impact, which may require manual validation for edge cases outside established literature.