auto-paper-improvement-loop

Run two-round automated reviews and fixes on academic paper manuscripts.

Updated Apr 10, 2026
One-click install
npx skills add https://github.com/KwongFuk/codex-skills --skill auto-paper-improvement-loop-kwongfuk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: auto-paper-improvement-loop
Source: https://github.com/KwongFuk/codex-skills/tree/main/global/auto-paper-improvement-loop
Command: npx skills add https://github.com/KwongFuk/codex-skills --skill auto-paper-improvement-loop-kwongfuk

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill autonomously improves a generated paper through two rounds of expert review, fixes, and recompile steps, reducing manual drafting time and improving presentation quality.

Core Features & Use Cases

  • Two-round automated improvement: Repeated GPT-5.4-driven review and fixes to enhance technical rigor, writing clarity, and structure.
  • End-to-end paper pipeline: From review to fix to recompile with state tracking and recovery for long documents.
  • Use Case: A researcher uses this skill to polish a conference paper after the initial draft, ensuring the final manuscript adheres to structure and quality expectations.

Quick Start

Instruct the system to run the two-round improvement loop on the target paper directory.

Frequently Asked Questions about auto-paper-improvement-loop

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically polish an academic paper draft?

To automatically polish an academic paper draft, use an autonomous two-round improvement loop that applies AI-driven reviews and fixes to enhance technical rigor, writing clarity, and structure before recompiling the manuscript.

What is a two-round AI review for LaTeX manuscripts?

A two-round AI review for LaTeX manuscripts is an automated process that repeatedly evaluates sources to identify technical and structural issues, applies fixes, and recompiles the document to ensure presentation quality.

Can I use an automated paper improvement loop for long documents with state persistence?

Yes, you can use an automated paper improvement loop for long documents because it implements end-to-end state tracking and recovery, ensuring the workflow persists across review and recompile steps without losing progress.

Does the automated paper review process support human checkpoints?

Yes, the automated paper review process supports optional human checkpoints, allowing researchers to manually verify manuscript modifications during the drafting and revision workflow before proceeding to the next round.

How to log automated paper improvement results in a markdown file?

To log automated paper improvement results, the workflow automatically records review and fix outcomes in PAPER_IMPROVEMENT_LOG.md, providing a persistent record of the two-round AI-driven manuscript enhancements.