Compiles LaTeX papers to PDF with automatic error fixing and submission checks. It runs latexmk, parses compilation logs, and fixes common issues like missing packages, undefined references, and BibTeX errors across up to three attempts. The post-compilation verification is thorough: checks page counts against conference limits (correctly handling ML venues where references don't count versus IEEE where they do), scans for undefined citations, verifies font embedding, and even detects orphaned section files not referenced in main.tex. If you're submitting to NeurIPS or ICLR and need to know if your paper fits the 9-page limit or has stray author names breaking anonymity, this handles it. The workflow is opinionated but covers the real pre-submission checklist.

skills.sh installs
539
GitHub stars
18.9K
last updated
Aug 21, 2026

Install

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

Installs into .claude/skills of the current project.

Files

Paper Compile: LaTeX to Submission-Ready PDF

Compile the LaTeX paper and fix any issues: $ARGUMENTS

Constants

  • COMPILER = latexmk — LaTeX build tool. Handles multi-pass compilation automatically.
  • ENGINE = pdflatex — LaTeX engine. Options: pdflatex (default), xelatex (for CJK/custom fonts), lualatex.
  • MAX_COMPILE_ATTEMPTS = 3 — Maximum attempts to fix errors and recompile.
  • PAPER_DIR = paper/ — Directory containing LaTeX source files.
  • MAX_PAGES — Page limit. ML conferences: main body to Conclusion end (excluding references & appendix). ICLR=9, NeurIPS=9, ICML=8. IEEE venues: references ARE included in page count. IEEE journal ≈ 12-14 pages, IEEE conference ≈ 5-8 pages (all inclusive).

Workflow

Step 1: Verify Prerequisites

Check that the compilation environment is ready:

# Check LaTeX installation
which pdflatex && which latexmk && which bibtex

# If not installed, provide instructions:
# macOS: brew install --cask mactex-no-gui
# Ubuntu: sudo apt-get install texlive-full
# Server: conda install -c conda-forge texlive-core

Verify all required files exist:

# Must exist
ls $PAPER_DIR/main.tex

Sponsors

Details

Repository
github.com/wanshuiyin/auto-claude-code-research-in-sleep
Categories
DevOps & CI/CD, Data Science & ML, Debugging, Office & Documents
First seen
Jun 3, 2026

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

All 41
1wshaddix avatarproject-structurewshaddix/dotnet-skillsGuidelines for organizing .NET projects, including solution structure, project references, folder conventions, .slnx format, centralized build properties, and c539skills.sh installs
2longbridge avatarlongbridge-sector-rotationlongbridge/skillsSector-rotation snapshot across A-share, HK, and US markets — point-in-time multi-factor scoring of momentum, capital flow, and valuation to rank sectors by cur535skills.sh installs
3tuist avatardebug-generated-projecttuist/agent-skillsDebugs issues users encounter with Tuist-generated projects by reproducing the scenario locally, building Tuist from source when needed, and triaging whether it533skills.sh installs
4wanshuiyin avatarrebuttalwanshuiyin/auto-claude-code-research-in-sleepWorkflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and man532skills.sh installs
5plugin87 avatarmigrate-design-systemplugin87/ux-ui-agent-skillsMap this token system to or from any external design system (Material Design 3, Apple HIG, Fluent, Carbon, Ant, shadcn/ui, Radix, Chakra, Mantine, Bootstrap…) —531skills.sh installs
6wanshuiyin avatarexperiment-bridgewanshuiyin/auto-claude-code-research-in-sleepWorkflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use531skills.sh installs