Self Review

This does a multi-reviewer simulation of your academic paper before you submit it. It extracts text from PDFs or LaTeX, then runs three independent reviews using different personas (harsh but fair, harsh and critical, open-minded) following the NeurIPS review format. Each reviewer goes through up to three reflection rounds to refine their scores, then all reviews get aggregated with weighted scoring borrowed from AgentLaboratory. You get a structured report with consensus strengths and weaknesses, actionable suggestions tagged to specific sections, and a score breakdown table. The workflow is thorough but the quality depends entirely on the paper text extraction working cleanly. Most useful when you want to stress test a draft before real submission and need specific feedback beyond what a single LLM pass would give you.

Install to Claude Code

npx -y skills add lingzhi227/agent-research-skills --skill self-review --agent claude-code