latex-document-skill

What this skill does

# LaTeX Document Skill

Create any LaTeX document, compile to PDF, and generate PNG previews. Convert PDFs of any type to LaTeX.

## Workflow: Create Documents

1. Determine document type (resume, report, letter, invoice, article, thesis, academic CV, presentation, poster, exam, book, cheat sheet)
2. **If the target is an IEEE journal / Transactions / IEEE two-column paper:** Read [references/ieee-journal-twocolumn-guide.md](references/ieee-journal-twocolumn-guide.md) before choosing a template. Start from `examples/ieee-twocolumn-sample.tex` for a working IEEEtran baseline and use `examples/ieee-twocolumn.png` / `examples/ieee-twocolumn-p1.png` / `examples/ieee-twocolumn-p2.png` as visual references.
3. **If poster:** Run the poster sub-workflow (see [Poster Sub-Workflow](#poster-sub-workflow) below), then skip to step 5.
4. **If cheat sheet / reference card:** Run the cheat sheet sub-workflow (see [Cheat Sheet / Reference Card Sub-Workflow](#cheat-sheet--reference-card-sub-workflow) below), then skip to step 5.
5. **Ask the user which enrichment elements they want** (use AskUserQuestion tool with multiSelect). Offer relevant options based on document type:
   - **AI-generated images** -- custom illustrations, diagrams, photos (uses generate-image skill)
   - **Charts/graphs** -- bar, line, pie, scatter, heatmap (pgfplots or matplotlib)
   - **Flowcharts/diagrams** -- process flows, architecture, decision trees (TikZ or Mermaid)
   - **Citations/bibliography** -- academic references, footnotes, works cited (BibTeX/biblatex)
   - **Tables with data** -- comparison matrices, financial data, statistics (booktabs)
   - **Watermarks** -- DRAFT, CONFIDENTIAL, or company logo background
   - Skip this step for simple documents (cover letters, invoices) or when the user has already specified exactly what they want.
6. Copy the appropriate template from `assets/templates/` or write from scratch
7. Customize content based on user requirements
8. Generate external assets based on user's element choices:
   - AI images: `python3 <skill_path>/../generate-image/scripts/generate_image.py "prompt" --output ./outputs/figure.png`
   - matplotlib charts: `python3 <skill_path>/scripts/generate_chart.py <type> --data '<json>' --output chart.png`
   - Mermaid diagrams: `bash <skill_path>/scripts/mermaid_to_image.sh diagram.mmd output.png`
9. **For documents 5+ pages:** Review the [Long-Form Document Anti-Patterns](#long-form-document-anti-patterns-must-read-for-reports-theses-books) section and run the Content Generation Checklist before compiling. Key rules: prefer prose over bullets, include global list compaction, escape `<`/`>` in text mode, vary section formats, limit `\newpage`, size images at 0.75-0.85 textwidth.
10. Compile with `scripts/compile_latex.sh` (auto-detects XeLaTeX for CJK/RTL, glossaries, bibliography)
11. Show PNG preview to user, deliver PDF

### Poster Sub-Workflow

When the user requests a poster: read [references/poster-design-guide.md](references/poster-design-guide.md) for the complete workflow including conference size presets (NeurIPS/ICML/CVPR/ICLR dimensions), layout archetypes (Traditional/BetterPoster/Visual-Heavy), color schemes, and typography standards. Use `poster.tex` (portrait) or `poster-landscape.tex` (landscape). Ask the user for conference/orientation, layout style, and color scheme using AskUserQuestion, then proceed to step 5.

### Cheat Sheet / Reference Card Sub-Workflow

When the user requests a cheat sheet, reference card, or formula sheet:

1. Read [references/cheatsheet-guide.md](references/cheatsheet-guide.md) for the complete workflow including template selection, content budgets, typography rules, and the PDF-to-cheatsheet pipeline.
2. Select template: `cheatsheet.tex` (general, 3-col landscape), `cheatsheet-exam.tex` (exam formula, 2-col portrait), or `cheatsheet-code.tex` (programming, 4-col landscape).
3. Follow the guide's workflow steps, then return to main workflow step 5.

## Workflow: Mail Merge (Batch Personalized Documents)

Generate N personalized documents from a LaTeX template + CSV/JSON data source using `scripts/mail_merge.py`. Template syntax: `{{variable}}` for simple substitution, Jinja2 (`<< >>`, `<% %>`) for conditionals/loops. See `assets/templates/mail-merge-letter.tex` for an example. Full guide: [references/interactive-features.md](references/interactive-features.md).

## Workflow: Version Diffing (latexdiff)

Generate highlighted change-tracked PDFs using `scripts/latex_diff.sh`. Supports file-to-file diff, git revision diff, multi-file flatten, and custom markup styles. Full guide: [references/interactive-features.md](references/interactive-features.md).

## Workflow: Convert Document Formats

Convert between Markdown, DOCX, HTML, and LaTeX using `scripts/convert_document.sh`. Full guide: [references/format-conversion.md](references/format-conversion.md).

## Workflow: Convert PDF to LaTeX

Convert existing PDFs (handwritten notes, printed reports, legal docs) to LaTeX. Full pipeline: [references/pdf-conversion.md](references/pdf-conversion.md).

**Quick steps**: Split PDF into page images (`scripts/pdf_to_images.sh`), select a conversion profile, create shared preamble, apply scaling strategy, validate with `scripts/validate_latex.py`, concatenate, compile.

**Scaling strategy**: 1-10 pages = single agent; 11-20 pages = split in half (2 agents); 21+ pages = batch-7 pipeline (ceil(N/7) agents with `run_in_background: true`).

**Conversion profiles** (in `references/profiles/`): `math-notes.md` (equations, theorems -- has beautiful mode), `business-document.md` (reports, memos), `legal-document.md` (contracts, statutes), `general-notes.md` (handwritten, mixed content).

## Workflow: Fill PDF Forms

Fill existing PDF forms -- both fillable (with form fields) and non-fillable (image-based). Full guide: [references/pdf-operations.md](references/pdf-operations.md).

**Step 1: Check form type:**
```bash
python3 <skill_path>/scripts/pdf_check_form.py form.pdf
```

**If fillable** (has form fields):
```bash
# Extract field metadata
python3 <skill_path>/scripts/pdf_extract_fields.py form.pdf field_info.json
# Create field_values.json with values for each field, then fill
python3 <skill_path>/scripts/pdf_fill_form.py form.pdf field_values.json output.pdf
```

**If non-fillable** (no form fields):
```bash
# Convert to images for visual analysis
bash <skill_path>/scripts/pdf_to_images.sh form.pdf ./tmp/pages
# Visually identify fields, create fields.json with bounding boxes
# Validate bounding boxes (+ optional validation image)
python3 <skill_path>/scripts/pdf_validate_boxes.py fields.json --image page_1.png --output validation.png --page 1
# Fill with text annotations
python3 <skill_path>/scripts/pdf_fill_annotations.py form.pdf fields.json output.pdf
```

## Workflow: Advanced PDF Operations

For text/table extraction (pdfplumber), OCR (pytesseract), programmatic PDF creation (reportlab), watermarking, page rotation/cropping, metadata extraction, JavaScript libraries (pdf-lib, pdfjs-dist), and batch processing, see [references/pdf-operations.md](references/pdf-operations.md).

## Compile Script

```bash
# Basic compile (auto-detects engine)
bash <skill_path>/scripts/compile_latex.sh document.tex

# Compile + generate PNG previews
bash <skill_path>/scripts/compile_latex.sh document.tex --preview

# Compile + PNG in specific directory
bash <skill_path>/scripts/compile_latex.sh document.tex --preview --preview-dir ./outputs

# Force a specific engine
bash <skill_path>/scripts/compile_latex.sh document.tex --engine xelatex
bash <skill_path>/scripts/compile_latex.sh document.tex --engine lualatex

# Use latexmk for automatic multi-pass (recommended for complex documents)
bash <skill_path>/scripts/compile_latex.sh document.tex --use-latexmk --preview

# PDF/A output for thesis submissions and archival compliance
bash <skill_path>/scripts/compile_latex.sh document.tex --pdfa

# Verbose output for debuggi