Takes a compiled LaTeX paper and runs two rounds of GPT-5.5 review, fix implementation, and recompilation without human intervention. Each round uses a fresh reviewer thread to avoid score inflation from context carryover, a real problem the author documented when trying reply-based reviews. You can optionally pass a style reference to guide structural fixes or an edit whitelist to lock down which files and operations are allowed, useful for resubmissions where you can't touch the bibliography or add new theorems. Set human checkpoint mode if you want to approve changes between rounds. The two round limit reflects diminishing returns: round one catches structural issues, round two catches presentation problems, and round three rarely improves the actual quality score.

skills.sh installs
572
GitHub stars
18.9K
last updated
Aug 21, 2026

Install

$ npx -y skills add wanshuiyin/auto-claude-code-research-in-sleep --skill auto-paper-improvement-loop --agent claude-code

Installs into .claude/skills of the current project.

Files

Auto Paper Improvement Loop: Review → Fix → Recompile

Before each reviewer slot, follow Selectable Reviewers: resolve invocation → .aris/reviewer.json → Claude Code default (Codex MCP) with reviewer_route.py through the canonical helper resolver, preserving this slot's tier, fresh contexts, source/image inputs and deterministic gates. Codex examples/pins below apply only to backend=codex; other routes use their own first-call/reply contract. Save the route and actual returned identity; unavailable selections are REVIEW_UNAVAILABLE. Classify acceptance from actual families/completion/scope. Forward invocation reviewer/model/effort overrides to reviewer-bearing children. Writer selection is separate; follow the writing-worker guidance below when drafting or revising prose.

Sponsors

Details

Repository
github.com/wanshuiyin/auto-claude-code-research-in-sleep
Categories
Git & Pull Requests, Code Review & Quality, Data Science & ML
First seen
Jun 3, 2026

More from wanshuiyin/auto-claude-code-research-in-sleep

All 41
1plugin87 avatarux-writingplugin87/ux-ui-agent-skillsWrite or review UI copy — buttons, errors, empty states, microcopy, notifications, labels — using the voice & tone system (clear, concise, useful, human, honest564skills.sh installs
2alirezarezvani avatarcode-touralirezarezvani/claude-skillsUse when the user asks to create a CodeTour .tour file — persona-targeted, step-by-step walkthroughs that link to real files and line numbers. Trigger for: crea562skills.sh installs
3wanshuiyin avatarresearch-refinewanshuiyin/auto-claude-code-research-in-sleepTurn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.6-Sol review. Use when560skills.sh installs
4wanshuiyin avatarpaper-planwanshuiyin/auto-claude-code-research-in-sleepGenerate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or want558skills.sh installs
5adobe avatarprototypeadobe/skillsRender a proposed redesign of a page on the current website as a self-contained static HTML file, then iterate via the impeccable craft loop. Per-page, idempote555skills.sh installs
6aliyun avataralibabacloud-ram-permission-diagnosealiyun/alibabacloud-aiops-skillsAlibaba Cloud RAM permission diagnosis and repair assistant. When an agent encounters any permission-related error while operating Alibaba Cloud resources (403,555skills.sh installs