LaTeX Document Skill

Poster Sub-Workflow

When the user requests a poster: read 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 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.

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.

Workflow: Convert Document Formats

Convert between Markdown, DOCX, HTML, and LaTeX using scripts/convert_document.sh. Full guide: 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.

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.

Step 1: Check form type:

python3 <skill_path>/scripts/pdf_check_form.py form.pdf

If fillable (has form fields):

# 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):

# 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.

Compile Script

# 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 debugging compilation issues
bash <skill_path>/scripts/compile_latex.sh document.tex --verbose

# Quiet mode for batch/CI jobs (only errors shown)
bash <skill_path>/scripts/compile_latex.sh document.tex --quiet

# Clean auxiliary files only (no compilation)
bash <skill_path>/scripts/compile_latex.sh document.tex --clean

Compilation Flags

Compilation Backends

Manual multi-pass (default): Runs the engine multiple times with bibliography/index/glossary passes as needed. This is the traditional approach and works without latexmk installed.

latexmk (--use-latexmk): Uses latexmk for automatic dependency-driven compilation. Recommended for complex documents with bibliographies, indexes, glossaries, or cross-references -- latexmk determines the correct number of passes automatically. Requires latexmk (included with TeX Live).

Log Filtering (texfot)

When texfot is installed (included with TeX Live), compilation output is automatically filtered to show only relevant warnings and errors, suppressing noisy package loading messages. This applies in the default verbosity mode. Use --verbose to see unfiltered output, or --quiet to suppress all non-error output.

Engine auto-detection: If the .tex file uses fontspec, xeCJK, or polyglossia, the script automatically uses xelatex. If it uses luacode or luatextra, it uses lualatex. Otherwise defaults to pdflatex. Override with --engine.

The script auto-installs texlive (including texlive-science, texlive-xetex, texlive-luatex, biber) and poppler-utils if missing. It auto-detects \bibliography{} (runs bibtex), \addbibresource{} (runs biber), \makeindex (runs makeindex), \makeglossaries (runs makeglossaries), runs the correct number of passes, generates PNG previews with pdftoppm, and cleans auxiliary files.

Script & Tool Reference

For PDF utilities (encrypt, merge, optimize, extract pages, pdf-to-images), LaTeX quality tools (lint, word count, analysis, package check, citations), compilation auto-fix, bibliography fetching, and diagram scripts (Mermaid, Graphviz, PlantUML), see references/script-tools.md.

Templates

Copy from assets/templates/ and customize.

Resume Templates (5 ATS-Compatible Options)

Select based on experience level, industry, and ATS requirements. See references/resume-ats-guide.md for full ATS guidance.

All 5 templates follow ATS rules: single-column, no graphics/images, no tables for layout, standard section headings, contact info in body (not header/footer).

STEM Student Templates

• homework.tex -- Homework/assignment submission template (article class, 11pt) with toggle-able solutions (\showsolutionstrue/\showsolutionsfalse), custom problem/solution environments, honor code section, fancyhdr headers, amsmath+amssymb+amsthm math, listings code highlighting (Python, Java, C++, Matlab styles), enumitem for (a), (b), (c) sub-parts, hyperref. Customization via \coursename, \assignmentnumber, \studentname, \studentid, \duedate. Example problems: calculus, proof by induction, Python coding, matrix algebra, kinematics, Java OOP.
• lab-report.tex -- STEM lab report template (article class, 11pt) with siunitx for uncertainties and SI units, pgfplots for data visualization, booktabs for professional tables, amsmath for equations, fancyhdr headers, caption+subcaption for figures. Structured sections: abstract, theory, procedure, data/results (with uncertainty tables), analysis (pgfplots graphs), discussion (error analysis), conclusion, references, appendix. Example: pendulum period measurement with error propagation.

Other Templates

• lecture-notes.tex -- Beautiful lecture notes (scrartcl KOMA-Script class) with Palatino font, microtype typography, color-coded tcolorbox theorem environments (blue theorems, green definitions, orange examples, purple remarks), TikZ graph theory diagram styles and macros (\CompleteGraph, \CycleGraph, \PathGraph), styled section headings with titlesec, fancyhdr headers, hyperref + cleveref navigation. Ideal for converting handwritten math/science notes to beautiful PDFs. Includes graph theory custom commands (\V, \E, \deg, \chr). Used by the math-notes conversion profile in beautiful mode.
• thesis.tex -- Thesis/dissertation (book class) with title page, declaration, abstract, acknowledgments, TOC, list of figures/tables, chapters, appendices, bibliography. Front matter uses roman numerals, main matter uses arabic. Includes theorem environments.
• academic-cv.tex -- Multi-page academic CV with publications (journal/conference/preprint sections), grants and funding, teaching, advising (current/graduated students), awards, professional service, invited talks. ORCID and Google Scholar links.
• book.tex -- Full book (book class) with half-title, title page, copyright page, dedication, preface, acknowledgments, TOC, list of figures/tables, parts, chapters, appendix, bibliography, index. Custom chapter headings, epigraphs, fancyhdr, microtype.
• poster.tex -- Conference poster (tikzposter class, A0 portrait) with 2-column layout, QR code, 5 color schemes, tikzfigure charts, tables, coloredbox highlights. Includes commented #BetterPoster layout variant (central billboard + sidebars). Portrait is standard for most conferences. See poster design guide for conference size presets.
• poster-landscape.tex -- Landscape conference poster (tikzposter class, A0 landscape) with 3-column (30/40/30) layout, QR code, tech purple color scheme. For CS/ML conferences (NeurIPS, ICML, CVPR, ICLR). Includes commented \geometry{} presets for CVPR/NeurIPS custom sizes.
• cheatsheet.tex -- General reference card (extarticle class, landscape A4, 7pt base font) with 3-column multicols layout, tcolorbox colored section boxes, tight spacing. For command references, concept summaries, quick-reference guides. Supports front+back printing.

Usage:

cp <skill_path>/assets/templates/resume-classic-ats.tex ./outputs/my_resume.tex
# Edit content, then compile
bash <skill_path>/scripts/compile_latex.sh ./outputs/my_resume.tex --preview --preview-dir ./outputs

Document Type Selection

Key LaTeX Patterns

Escaping Special Characters

Always escape: % → \%, $ → \$, & → \&, # → \#, _ → \_

Angle brackets in text mode: < and > are NOT valid in LaTeX text mode with T1 encoding. They render as inverted question marks (¡ or ¿). Always use math mode or text commands:

• <5% → $<$5\% or \textless 5\%
• >50 → $>$50 or \textgreater 50
• <$300 → $<$\$300
• >= → $\geq$, <= → $\leq$

This is one of the most common silent errors in generated LaTeX — the document compiles without errors but the PDF shows garbage characters.

Date ranges use en-dash: 2019--2025 (double hyphen).

Standard Preamble

\documentclass[11pt,a4paper]{article}
\usepackage[utf8]{inputenc}
\usepackage[T1]{fontenc}
\usepackage{geometry}
\usepackage{hyperref}
\usepackage{xcolor}
\usepackage{graphicx}
\usepackage{tabularx}
\usepackage{colortbl}
\usepackage{enumitem}
\usepackage{titlesec}

Code Patterns (load as needed)

For ready-to-use LaTeX code snippets (tables, charts, flowcharts, bibliography, watermarks, landscape pages, multi-language, images, Mermaid diagrams, matplotlib charts, CSV tables, AI images, fillable forms, conditional content, mail merge, version diff), read references/code-patterns.md.

Visual Elements in Reports

When creating reports, use the enrichment elements the user selected in step 4. For the quick reference table of visual element tools (charts, flowcharts, AI images, tables, timelines) and sizing guidelines, see references/advanced-features.md. Use \begin{figure}[H] (from float package) to prevent figures from floating. Size TikZ diagrams with width=0.8\textwidth or smaller.

Reference Guides (load as needed)

When uncertain about LaTeX patterns, compilation issues, or document quality, consult this table and load relevant files.

Critical Notes and Common Mistakes

Compile & Output

• Run compile script from the directory containing the .tex file, or use absolute paths
• Place output .tex files in ./outputs/ for user visibility
• After compilation, read the PNG preview files to show the user how the document looks
• PNG previews require poppler-utils (auto-installed by script)

Package Dependency Errors (MUST READ)

These cause Undefined control sequence -- always include the required package:

hyperref Package

• hyperref is fine for normal documents (most templates use it).
• Only avoid it in PDF-to-LaTeX converted documents with theorem environments, where it causes \set@color errors.

Compilation Environment

• If texlive is not installed, the compile script auto-installs it. Do NOT run multiple compile commands in parallel before texlive is installed -- they will all try to install simultaneously, causing dpkg lock contention. Install once first or run compiles sequentially.
• The compile script uses -interaction=nonstopmode (not -halt-on-error) to ensure PDFs are produced even with warnings. This is intentional -- many documents produce warnings on first pass that resolve on subsequent passes.
• latexmk and texfot are included with TeX Live. The setup script (setup.sh) verifies their availability. latexmk is used when --use-latexmk is passed; texfot is used automatically when available (default verbosity mode).
• A .chktexrc configuration file is included at the skill root to suppress common false positives when linting generated LaTeX documents. The latex_lint.sh script uses it automatically.

Long-Form Document Anti-Patterns

For documents 5+ pages (reports, theses, books), read references/long-form-best-practices.md for 9 critical anti-patterns, the report preamble best practices, and the content generation checklist. This is MUST-READ material before generating any long document.