paper-compile
Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says "编译论文", "compile paper", "build PDF", "生成PDF", or wants to compile LaTeX into a submission-ready PDF.
Best use case
paper-compile is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says "编译论文", "compile paper", "build PDF", "生成PDF", or wants to compile LaTeX into a submission-ready PDF.
Teams using paper-compile should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/paper-compile/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How paper-compile Compares
| Feature / Agent | paper-compile | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says "编译论文", "compile paper", "build PDF", "生成PDF", or wants to compile LaTeX into a submission-ready PDF.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# 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:
```bash
# 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:
```bash
# Must exist
ls $PAPER_DIR/main.tex
# Should exist
ls $PAPER_DIR/references.bib
ls $PAPER_DIR/sections/*.tex
ls $PAPER_DIR/figures/*.pdf 2>/dev/null || ls $PAPER_DIR/figures/*.png 2>/dev/null
```
### Step 2: First Compilation Attempt
```bash
cd $PAPER_DIR
# Clean previous build artifacts
latexmk -C
# Full compilation (pdflatex + bibtex + pdflatex × 2)
latexmk -pdf -interaction=nonstopmode -halt-on-error main.tex 2>&1 | tee compile.log
```
### Step 3: Error Diagnosis and Auto-Fix
If compilation fails, read `compile.log` and fix common errors:
**Missing packages:**
```
! LaTeX Error: File `somepackage.sty' not found.
```
→ Install via `tlmgr install somepackage` or remove the `\usepackage` if unused.
**Undefined references:**
```
LaTeX Warning: Reference `fig:xyz' on page 3 undefined
```
→ Check `\label{fig:xyz}` exists in the correct figure environment.
**Missing figures:**
```
! LaTeX Error: File `figures/fig1.pdf' not found.
```
→ Check if the file exists with a different extension (.png vs .pdf). Update the `\includegraphics` path.
**Citation undefined:**
```
LaTeX Warning: Citation `smith2024' undefined
```
→ Add the missing entry to `references.bib` or fix the citation key.
**`[VERIFY]` markers in text:**
→ Search for `[VERIFY]` markers left by `/paper-write`. These indicate unverified citations or facts. Search for the correct information or flag to the user.
**Overfull hbox:**
```
Overfull \hbox (12.5pt too wide) in paragraph at lines 42--45
```
→ Minor: usually ignorable. If severe (>20pt), rephrase the text or adjust figure width.
**BibTeX errors:**
```
I was expecting a `,' or a `}'---line 15 of references.bib
```
→ Fix BibTeX syntax (missing comma, unmatched braces, special characters in title).
**`\crefname` undefined for custom theorem types:**
→ Ensure `\crefname{assumption}{Assumption}{Assumptions}` and similar are in the preamble after `\newtheorem{assumption}`.
### Step 4: Iterative Fix Loop
```
for attempt in 1..MAX_COMPILE_ATTEMPTS:
compile()
if success:
break
parse_errors()
auto_fix()
```
For each error:
1. Read the error message from `compile.log`
2. Locate the source file and line number
3. Apply the fix
4. Recompile
**Stuck after 2 attempts?** If Codex plugin is installed, invoke `/codex:rescue` — Codex can independently read the LaTeX source and `compile.log` to spot issues Claude missed (e.g., conflicting packages, encoding problems, subtle macro errors). If not installed, continue with Claude's own diagnosis.
### Step 5: Post-Compilation Checks
After successful compilation, verify the output:
```bash
# Check PDF exists and has content
ls -la main.pdf
# Check page count
pdfinfo main.pdf | grep Pages
# macOS: open for visual inspection
# open main.pdf
```
**Automated checks:**
- [ ] PDF file exists and is > 100KB (not empty/corrupt)
- [ ] Total page count is reasonable (MAX_PAGES + appendix + references)
- [ ] No "??" in the PDF (undefined references — grep the log)
- [ ] No "[?]" in the PDF (undefined citations — grep the log)
- [ ] Figures are rendered (not missing image placeholders)
```bash
# Check for undefined references
grep -c "LaTeX Warning.*undefined" compile.log
# Check for missing citations
grep -c "Citation.*undefined" compile.log
```
### Step 6: Page Count Verification
**CRITICAL**: Verify paper fits within MAX_PAGES.
**For ML conferences (ICLR/NeurIPS/ICML/CVPR/ACL/AAAI):** Main body = first page through end of Conclusion section (not necessarily §5 — could be §6, §7, or §8 depending on structure). References and appendix are NOT counted.
**For IEEE venues:** The TOTAL page count (including references) must fit within the limit. There is no separate "main body" counting — everything up to and including the references counts.
**Precise check using `pdftotext`:**
```bash
# Extract text and find where Conclusion ends vs References begin
pdftotext main.pdf - | python3 -c "
import sys
text = sys.stdin.read()
pages = text.split('\f')
for i, page in enumerate(pages):
if 'Ethics Statement' in page or 'Reproducibility' in page:
print(f'Conclusion ends on page {i+1}')
if any(w in page for w in ['References', 'Bibliography']):
lines = [l for l in page.split('\n') if l.strip()]
for l in lines[:3]:
if 'References' in l or 'Bibliography' in l:
print(f'References start on page {i+1}')
break
"
```
If Conclusion ends mid-page and References start on the same page, the main body is that page number (e.g., if both are on page 9, main body = ~8.5 pages, which is fine for a 9-page limit since it leaves room for the References header).
If over limit:
- Identify which sections are longest
- Suggest specific cuts (move proofs to appendix, compress tables, tighten writing)
- Report: "Main body is X pages (limit: MAX_PAGES). Suggestion: move [specific content] to appendix."
### Step 6.5: Stale File Detection
Check for orphaned section files not referenced by `main.tex`:
```bash
# Find all .tex files in sections/ and check which are \input'ed by main.tex
for f in paper/sections/*.tex; do
base=$(basename "$f")
if ! grep -q "$base" paper/main.tex; then
echo "WARNING: $f is not referenced by main.tex — consider removing"
fi
done
```
This prevents confusion from leftover files when section structure changes (e.g., old `5_conclusion.tex` left behind after restructuring to 7 sections).
### Step 7: Submission Readiness
For conference submission, additional checks:
- [ ] **Anonymous**: no author names, affiliations, or self-citations that reveal identity
- [ ] **Page limit**: main body within MAX_PAGES (to end of Conclusion)
- [ ] **Font embedding**: all fonts embedded in PDF
```bash
pdffonts main.pdf | grep -v "yes" # should return nothing (or only header)
```
- [ ] **No supplementary mixed in**: appendix clearly after `\newpage\appendix`
- [ ] **File size**: reasonable (< 50MB for most venues, < 10MB preferred)
- [ ] **No `[VERIFY]` markers**: search the PDF text for leftover markers
### Step 8: Output Summary
```markdown
## Compilation Report
- **Status**: SUCCESS / FAILED
- **PDF**: paper/main.pdf
- **Pages**: X (main body to Conclusion) + Y (references) + Z (appendix)
- **Within page limit**: YES/NO (MAX_PAGES = N)
- **Errors fixed**: [list of auto-fixed issues]
- **Warnings remaining**: [list of non-critical warnings]
- **Undefined references**: 0
- **Undefined citations**: 0
### Next Steps
- [ ] Visual inspection of PDF
- [ ] Run `/paper-write` to fix any content issues
- [ ] Submit to [venue] via OpenReview / CMT / HotCRP
```
## Key Rules
- **Never delete the user's source files** — only modify to fix errors
- **Keep compile.log** — useful for debugging
- **Don't suppress warnings** — report them, let the user decide
- **If LaTeX is not installed**, provide clear installation instructions rather than failing silently
- **Font embedding is critical** — some venues reject PDFs with non-embedded fonts
- **Page count rules differ by venue** — ML conferences: main body to Conclusion (refs excluded). **IEEE venues: total pages including references.**
## Common Venue Requirements
| Venue | Style File | Citation | Page Limit | Refs in limit? | Submission |
|-------|-----------|----------|------------|----------------|------------|
| ICLR 2026 | `iclr2026_conference.sty` | `natbib` (`\citep`/`\citet`) | 9 pages (to Conclusion end) | No | OpenReview |
| NeurIPS 2025 | `neurips_2025.sty` | `natbib` (`\citep`/`\citet`) | 9 pages (to Conclusion end) | No | OpenReview |
| ICML 2025 | `icml2025.sty` | `natbib` (`\citep`/`\citet`) | 8 pages (to Conclusion end) | No | OpenReview |
| IEEE Journal | `IEEEtran.cls` [journal] | `cite` (`\cite{}`, numeric) | ~12-14 pages (Transactions) / ~4-5 (Letters) | **Yes** | IEEE Author Portal / ScholarOne |
| IEEE Conference | `IEEEtran.cls` [conference] | `cite` (`\cite{}`, numeric) | 5-8 pages (varies by conf) | **Yes** | EDAS / IEEE Author Portal |Related Skills
paper-writing
Workflow 3: Full paper writing pipeline. Orchestrates paper-plan → paper-figure → paper-write → paper-compile → auto-paper-improvement-loop to go from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.
paper-write
Draft LaTeX paper section by section from an outline. Use when user says "写论文", "write paper", "draft LaTeX", "开始写", or wants to generate LaTeX content from a paper plan.
paper-slides
Generate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", or wants beamer slides for a conference talk.
paper-poster
Generate a conference poster (article + tcbposter LaTeX → A0/A1 PDF + editable PPTX + SVG) from a compiled paper. Use when user says "做海报", "制作海报", "conference poster", "make poster", "生成poster", "poster session", or wants to create a poster for a conference presentation.
paper-plan
Generate 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 wants to create a paper plan before writing.
paper-illustration
Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.
paper-figure
Generate publication-quality figures and tables from experiment results. Use when user says "画图", "作图", "generate figures", "paper figures", or needs plots for a paper.
auto-paper-improvement-loop
Autonomously improve a generated paper via GPT-5.4 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.
vast-gpu
Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.
system-profile
Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation. Produces structured performance reports with actionable recommendations. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.
training-check
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.
serverless-modal
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.