Overview
auto-paper-improvement-loop is an open-source data skill for Claude Code and compatible agents, published by wanshuiyin. Its author describes it as: “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 ge…”. The project has 15k stars on GitHub and is available under the MIT license. Add it to your setup with `git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/auto-paper-improvement-loop`.
What auto-paper-improvement-loop does
> 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It > already loops internally (review → fix → recompile) with its own round > structure and a deliberate fresh-reviewer bias guard each round (no > `codex-reply`). Re-asking it to "improve the paper" on a > wall-clock timer produces no new signal — quality changes when the *review* > changes, not when the clock ticks — and a timed re-run that also accepts its > own output to decide when to stop crosses into self-acquittal > (`acceptance-gate.md`). Schedule the *external wait that precedes it*, not the > improvement loop.…
What’s inside
The SKILL.md for auto-paper-improvement-loop is organised into these sections:
- Context
- Constants
- Optional: Style reference (— style-ref: <source>, opt-in)
- Optional: Edit Whitelist (— edit-whitelist <path>, opt-in)
- Schema
- Resolution rules
- Glob semantics
- Forbidden-operation detectors
- Behavior at loop start (before Round 1 fix-implementation)
- Behavior during fix-implementation (Steps 3 and 6)
- End-of-round surfacing
- Example invocations
Installation
Add auto-paper-improvement-loop to your agent with:
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/auto-paper-improvement-loopReview a skill’s source before installing it — skills can instruct your agent to run commands. This command comes from the skill’s public repository, which is the source of truth for setup steps. New to skills? Read how to install Claude Code skills.
Supported agents
- Claude Code — declared in the repository topics
- Codex — declared in the repository topics
License
auto-paper-improvement-loop is published under the MIT license.
Strengths
- Clear MIT license — safe to read and adapt within its terms
- Ships in wanshuiyin/Auto-claude-code-research-in-sleep, an established project with 14,858 GitHub stars
- Works with Claude Code, Codex
- Actively maintained — repository updated in the last 90 days
Author
Topics
Frequently asked questions
- What does auto-paper-improvement-loop do?
- 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.
- How do I install auto-paper-improvement-loop?
- Run git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep ~/.claude/skills/auto-paper-improvement-loop in your agent, then reload your skills. Review the source at https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep before installing.
- Is auto-paper-improvement-loop free to use?
- Yes. auto-paper-improvement-loop is free and open source under the MIT license, so you can read, run, and adapt it within that license's terms.
- Which agents does auto-paper-improvement-loop work with?
- auto-paper-improvement-loop lists Claude Code and Codex — named in its SKILL.md, its plugin marketplace or its repository topics. Skills use the portable SKILL.md format, so other agents that read that format may load it too.
- Where does auto-paper-improvement-loop come from?
- auto-paper-improvement-loop ships inside wanshuiyin/Auto-claude-code-research-in-sleep, a repository that contains 41 catalogued skills in total. The repository's 14,858 GitHub stars apply to that whole collection, not to this skill on its own.