AI-powered academic paper reviewer. Uses a multi-agent system (Deconstructor, Devil's Advocate, Judge) to analyze papers for logical flaws, contradictions, and empirical validity.
A rigorous academic review system that uses multiple AI agents to deconstruct, attack, and judge scientific papers.
Use this skill when:
Run the tool via the Node.js CLI in the installation directory.
Directory: /Users/sschepis/Development/peer-reviewer
node dist/index.js "<path_to_paper_or_raw_text>"
path_to_paper_or_raw_text: either a file path (absolute or relative to the package root) OR the raw text of the paper/claim.The tool outputs a "Merit Report" in JSON format, containing:
overallScore (0-10)defenseStrategysuggestions (list of improvements)dimensions (scores for logic, novelty, etc.)Review a local file:
cd /Users/sschepis/Development/peer-reviewer
node dist/index.js "/Users/sschepis/Desktop/research/draft_v1.txt"
Review a raw claim:
cd /Users/sschepis/Development/peer-reviewer
node dist/index.js "Claim: P=NP because I can solve Traveling Salesman in O(1) by guessing."
Ensure google.json is present in the root directory or GOOGLE_APPLICATION_CREDENTIALS is set if running in a new environment.