An AI-driven academic analysis tool that employs a multi-agent system to simulate rigorous peer reviews and find logical flaws.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install peer-reviewer
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install peer-reviewer using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Peer Reviewer?
The Peer Reviewer skill is a sophisticated analytical framework designed to assist researchers and developers in stress-testing academic papers and technical claims. By leveraging a multi-agent system—including the Deconstructor, Devil's Advocate, and Judge—it performs a deep-dive analysis into the logical consistency and empirical validity of any provided text. As a prominent tool within the Openclaw Skills ecosystem, it provides a cold, objective critique that mimics the rigor of high-stakes academic publishing.
Whether you are preparing a manuscript for submission or verifying a new hypothesis, this skill helps identify hidden contradictions and logic gaps. It integrates seamlessly into professional research workflows, providing a programmatic way to ensure that your work stands up to the most demanding scrutiny found in Openclaw Skills.
Peer Reviewer Use Cases
- Reviewing an academic paper draft for internal logical contradictions before formal submission.
- Stress-testing a scientific claim to find empirical flaws or missing evidence.
- Generating a "Reviewer 2" style critique to anticipate potential objections from external reviewers.
- Analyzing technical whitepapers for consistency with established literature.
How Peer Reviewer Works
- The user inputs a file path or raw text via the Node.js CLI interface.
- The multi-agent system deconstructs the paper into its core arguments and premises.
- The Devil's Advocate agent identifies weaknesses and searches for contradictions within the text.
- The Judge agent evaluates the findings and synthesizes them into a quantitative and qualitative report.
- The tool outputs a Merit Report in JSON format, detailing scores and specific suggestions for improvement.
Peer Reviewer Setup
To get started with this Peer Reviewer tool within your Openclaw Skills setup, ensure you have the necessary environment variables and dependencies configured.
# Navigate to the installation directory
cd /Users/sschepis/Development/peer-reviewer
# Ensure Google Cloud credentials are configured
export GOOGLE_APPLICATION_CREDENTIALS="./google.json"
# Execute the review on a local file
node dist/index.js "/path/to/your/research_paper.txt"
Peer Reviewer Data Schema & Taxonomy
The skill generates a structured Merit Report in JSON format to ensure the data is easily consumable by other Openclaw Skills or automation pipelines.
| Key | Type | Description |
|---|---|---|
overallScore |
Number | A value from 0-10 representing the paper's strength. |
defenseStrategy |
String | Suggested approaches to defending the paper's claims. |
suggestions |
Array | A list of actionable improvements to enhance clarity or logic. |
dimensions |
Object | Individual scores for logic, novelty, and empirical validity. |
Peer Reviewer Advanced Features
- Multi-agent orchestration involving specialized roles (Deconstructor, Devil's Advocate, Judge).
- Support for both local file system paths and direct raw text input for flexible analysis.
- Automated contradiction detection against established scientific premises.
- Quantitative scoring across multiple academic dimensions for objective benchmarking.
SKILL.md
Loading
Related Openclaw Skills
OpenClaw Data Importer
An intelligent data ingestion engine that automates the migration of disparate file formats into structured Supabase databases using AI.
System Diagnostics
A comprehensive system diagnostics and troubleshooting toolkit designed for DevOps engineers and system administrators using Openclaw Skills.
QR Auction Bidder
Automate USDC bids on daily $QR code auctions on the Base network using the Bankr transaction layer.
AgentPulse
Track and analyze LLM API costs, token consumption, and performance metrics in real-time for your AI agent.
VAST.ai GPU Rental
A powerful automation tool for searching, renting, and managing high-performance GPU cloud instances via VAST.ai.
Arena
A specialized skill for AI agents to compete in live frontend development challenges with automated progress reporting and on-chain rewards.
Featured*
