auto-paper-improvement-loop

Orchestrate two-round Claude review, fix LaTeX sources, and recompile papers.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/nxZhai/Nicy-Extension-Skills --skill auto-paper-improvement-loop-nxzhai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: auto-paper-improvement-loop
Source: https://github.com/nxZhai/Nicy-Extension-Skills/tree/main/skills-codex-claude-review/auto-paper-improvement-loop
Command: npx skills add https://github.com/nxZhai/Nicy-Extension-Skills --skill auto-paper-improvement-loop-nxzhai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Autonomously improve a compiled paper by orchestrating Claude review through the claude-review MCP bridge, applying fixes, and recompiling for two rounds, reducing manual editing workload.

Core Features & Use Cases

  • Two-round, autonomous review and rewrite loop that updates LaTeX sources and main.pdf.
  • Maintains a persistent state to recover from interruptions using JSON state files.
  • Integrates with the claude-review MCP bridge for structured expert feedback and automated patch application.
  • Generates a detailed paper-improvement log documenting reviews and fixes.

Quick Start

Run the skill against a paper directory containing paper/main.tex and paper/main.pdf to start the two-round improvement loop.

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 automate paper improvement and LaTeX recompiling using Claude reviews?

You can automate paper improvement by running a two-round loop that uses Claude reviews to apply fixes to LaTeX sources and recompiles the PDF. This autonomously polishes writing and argumentation while maintaining a persistent JSON state for recovery.

What is autonomous paper polishing with state persistence for research writing?

Autonomous paper polishing is an automated workflow applying Claude expert feedback to research papers across two rounds. State persistence via JSON ensures the improvement loop recovers from interruptions and transparently versions document artifacts.

Can I use a workflow automation loop to fix LaTeX sources and update main.pdf?

Yes, workflow automation can orchestrate Claude review feedback to patch LaTeX source files and deterministically recompile main.pdf. This targets generated research papers requiring rigorous argumentation and presentation enhancements.

How do I start an automated Claude review loop for a LaTeX paper directory?

Run the workflow against a paper directory containing paper/main.tex and paper/main.pdf to start the automated Claude review loop. The system then executes two rounds of review, patching, and recompiling while logging progress.

Does the automated paper improvement loop support recovering from interruptions?

Yes, the automated loop supports recovering from interruptions by maintaining persistent state using JSON files. This ensures progress is logged and the workflow resumes without losing completed review and rewrite steps.