paper-review-helper

# Paper Review Helper

Guide user through structured paper review, logging issues and generating formal review response.

## Phase 1: Setup

1. **Locate paper** from `$ARGUMENTS`:
   - If PDF file: create `<paper-name>-review/` folder, copy PDF into it
   - If folder: search for `.tex` first (prioritize over PDF)
   - No paper found → `AskUserQuestion`: "No paper detected. Please provide path to paper."

2. **Convert PDF → LaTeX** (if no .tex exists):

   ```bash
   # Check credentials
   [ -n "$MATHPIX_APP_ID" ] && [ -n "$MATHPIX_API_KEY" ] && echo "OK" || echo "MISSING"
   ```

   - If MISSING → notify user: "Set MATHPIX_APP_ID and MATHPIX_API_KEY for PDF→LaTeX. Proceeding with direct PDF (figures not extractable)."
   - If OK → run conversion:

   ```bash
   python ~/.claude/plugins/science-skill/skills/paper-review-helper/scripts/pdf2tex.py "<pdf_path>" "<paper-folder>"
   ```

   Output structure: `<paper-folder>/<pdf_id>/<pdf_id>.tex` with `images/` subfolder for figures.

3. **Initialize workspace**:

```text
<paper-folder>/
├── <pdf_id>/                 # Mathpix output (if converted)
│   ├── <pdf_id>.tex          # Converted LaTeX
│   └── images/               # Extracted figures
├── artifact/
│   ├── review-log.md         # Conversation log
│   ├── issues-major.md       # Major issues
│   ├── issues-minor.md       # Minor issues
│   └── programs/             # Math verification scripts
└── original.pdf              # Source PDF (if applicable)
```

## Phase 2: Section-by-Section Review

Parse LaTeX structure: `\section`, `\subsection`, `\begin{abstract}`. For each section:

1. **Chunk appropriately**:
   - Section ≤5 paragraphs: review whole
   - Section >5 paragraphs: split by `\subsection` or paragraph groups

2. **Present section** with:
   1. Section text - save the partial tex to markdown format.   
   2. Inline markers for issues (see Grammar Check Markers) in the markdown file.
   3. and provide the user with a path link to the file in the workspace