review-training

Community

Generate LLM training data from reviews.

Authornicsuzor
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the creation of high-quality training data for LLMs by extracting structured feedback-evidence pairs from academic reviews and their source documents.

Core Features & Use Cases

  • Automated Pair Extraction: Processes matched review/source document pairs to identify specific feedback, locate supporting evidence, and categorize the feedback.
  • Structured Data Generation: Outputs training data in JSONL format, suitable for fine-tuning LLMs to perform academic peer review.
  • Use Case: A research lab needs to train an AI assistant to provide constructive feedback on grant proposals. This Skill can process hundreds of past reviews and proposals to build a dataset that teaches the AI to identify common issues, suggest improvements, and cite relevant sections of the proposal.

Quick Start

Run the slash command /review-training to process the next matched pair of review and source documents.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: review-training
Download link: https://github.com/nicsuzor/academicOps/archive/main.zip#review-training

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.