An AI-driven platform that transforms academic reviewer feedback into actionable, structured revision suggestions for manuscripts.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install paper-reviser
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 paper-reviser 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 PaperReviser?
PaperReviser is a specialized tool within the Openclaw Skills ecosystem designed to assist researchers and academics in the grueling process of manuscript revision. By utilizing advanced LLMs, the platform analyzes peer-review comments—both strengths and weaknesses—and maps them directly to the content of an uploaded PDF or LaTeX file. It bridges the gap between critical feedback and the final draft by providing evidence-based suggestions for improvement.
The platform offers a professional-grade interface for managing multiple reviewers and generating structured revision logs. By integrating various AI models, PaperReviser ensures that researchers can choose the most effective logic engine for their specific field of study, making it a vital asset for navigating the 'Revise and Resubmit' phase of academic publishing.
PaperReviser Use Cases
- Processing complex peer-review feedback from multiple sources for journal submissions.
- Generating structured revision plans for 'Revise and Resubmit' decisions.
- Analyzing manuscript weaknesses after a rejection to prepare for a new submission.
- Exporting organized modification logs in Markdown to share with co-authors and research teams.
How PaperReviser Works
- The user authenticates via Google OAuth 2.0 to access a personalized workspace.
- A manuscript is uploaded in either PDF or LaTeX (.tex) format, from which the system automatically extracts the core text.
- The user inputs qualitative feedback from reviewers, categorized into dynamic lists of strengths and weaknesses.
- An LLM (such as Claude, GPT-4, or Gemini) performs a point-by-point analysis of the reviewer comments relative to the manuscript text.
- The system generates a structured revision plan that includes specific suggestions and citations from the original text.
- The final revision strategy is displayed in a structured UI and can be exported as a Markdown file for further editing.
PaperReviser Setup
To deploy this tool as part of your Openclaw Skills collection, follow these installation steps:
# Navigate to the project directory
cd paper-revision-platform
# Configure environment variables
cp .env.example .env
# Update .env with your Google OAuth credentials and LLM API keys
# Install all necessary dependencies
cd server && npm install && cd ../client && npm install && cd ..
# Start the backend and frontend services in separate terminals
# Backend (Port 3001)
cd server && npm run dev
# Frontend (Port 5173)
cd client && npm run dev
PaperReviser Data Schema & Taxonomy
PaperReviser manages data through a local SQLite database (sql.js) and structured session storage to maintain security and persistence.
| Component | Description |
|---|---|
| Authentication | Google OAuth 2.0 profile data managed via Passport.js |
| Document Store | Extracted text and metadata from uploaded PDF or LaTeX files |
| Reviewer Schema | Relational mapping of strengths, weaknesses, and reviewer IDs |
| Revision Output | Structured JSON objects containing AI suggestions, original quotes, and rationale |
| Export Format | Standard Markdown (.md) for cross-platform compatibility |
PaperReviser Advanced Features
- Multi-model support allowing seamless switching between Anthropic Claude, OpenAI GPT, Google Gemini, and Kimi.
- Automated text extraction for complex LaTeX source files and standard academic PDFs.
- Dynamic multi-reviewer management to track conflicting or complementary feedback in one view.
- Secure session encryption and Google OAuth integration for protecting sensitive research data.
- Structured Markdown export capabilities to facilitate the creation of response-to-reviewer documents.
SKILL.md
Loading
Related Openclaw Skills
Release Discipline
A governance skill that enforces release quality and prevents version spam through strict pre-deployment checklists and mandatory cooldown periods.
OpenClaw Starter Kit
A comprehensive onboarding package that guides users through the initial setup, personality definition, and security hardening of their AI agent via an interactive dialogue.
Gandalf Breaker
A systematic prompt injection toolkit designed to solve Lakera's Gandalf challenge through layered attack methodologies.
Prompt Enhancer
An intelligent wrapper that automatically refines and expands simple user instructions into professional-grade AI prompts.
AI-NEWS
An automated intelligence gathering skill that synthesizes critical AI industry updates by sector and timeframe.
Weather Assistant
A high-performance utility that fetches and summarizes real-time meteorological data for any specified city.
Featured*
