Agent skill

auto-paper-improvement-loop

Autonomously improve a generated paper via GPT-5.6-Sol xhigh review → implement fixes → recompile, for 2 rounds. Use when user says \"改论文\", \"improve paper\", \"论文润色循环\", \"auto improve\", or wants to iteratively polish a generated paper.

★ 15,640 stars MIT wanshuiyin/Auto-claude-code-research-in-sleep

Install this skill

This command installs the skill into the portable ~/.agents/skills directory. The homepage installer can generate the native path for your specific agent.

mkdir -p $HOME/.agents/skills/'auto-paper-improvement-loop' && curl -fsSL 'https://raw.githubusercontent.com/wanshuiyin/Auto-claude-code-research-in-sleep/HEAD/skills/skills-codex/auto-paper-improvement-loop/SKILL.md' -o $HOME/.agents/skills/'auto-paper-improvement-loop'/SKILL.md

View raw SKILL.md View repository

Skill details

Repository: wanshuiyin/Auto-claude-code-research-in-sleep
SKILL.md path: skills/skills-codex/auto-paper-improvement-loop/SKILL.md
Author: wanshuiyin
Tags: research, research-automation, paper-writing, agent-skill