/review

Review research artifacts with cross-model critique, scores, and improvement guidance.

Updated May 23, 2026
One-click install
npx skills add https://github.com/duany049/multi-skill-orchestration --skill review-duany049
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: /review
Source: https://github.com/duany049/multi-skill-orchestration/tree/main/.claude/skills/review
Command: npx skills add https://github.com/duany049/multi-skill-orchestration --skill review-duany049

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps researchers evaluate an idea, method, experiment plan, or paper draft by producing an independent, structured review that surfaces weaknesses, missing evidence, and gaps in wiki entities.

Core Features & Use Cases

  • Cross-model independent review: Uses a dedicated Review LLM configured as an objective reviewer.
  • Structured scoring and verdict: Outputs an overall 1-10 score, prioritized strengths/weaknesses, and a clear readiness verdict.
  • Wiki entity mapping: Maps findings back to specific wiki ideas/methods/experiments and identifies which entities need strengthening.
  • Difficulty and focus controls: Supports standard, hard, and adversarial review modes plus method/evidence/writing/completeness focus.
  • Read-only operation: Does not modify the wiki directly; it only generates actionable suggestions for callers to apply.

Quick Start

Run the review on a paper-draft by providing its path, focusing on evidence, and using standard difficulty to get a ready-to-apply report.

Frequently Asked Questions about /review

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

FAQPage Schema
How do I get an independent peer review for a paper draft or experiment plan?

Independent peer review for a paper draft or experiment plan is generated by producing cross-model critique, 1-10 scoring, and structured improvement guidance without modifying the original research artifact.

How does cross-model critique identify gaps in research artifacts?

Cross-model critique identifies gaps by mapping findings to specific wiki entities like ideas and methods, highlighting missing evidence and weaknesses to produce prioritized fixes with justifications.

Can I use a specific focus mode to review the evidence in my research methods?

Yes, you can review evidence using configurable difficulty and focus modes, targeting method, evidence, writing, or completeness to generate a ready-to-apply report for your specific research artifact.

What is the best way to review a research artifact without modifying the wiki?

The best way to review without modifying the wiki is using a read-only operation that loads context and outputs actionable suggestions, ensuring your original ideas, methods, and experiments remain untouched.

Does the review tool support adversarial difficulty modes for paper drafts?

Yes, the review tool supports standard, hard, and adversarial difficulty modes for paper drafts, applying rigorous cross-model critique to surface weaknesses and output a clear readiness verdict.