LaTeX Document Skill

The capybara sat down at the typewriter. When it stood up, there was a thesis.

Turn handwritten notes, scanned textbooks, and raw data into publication-ready LaTeX -- without knowing a single LaTeX command.

27 templates · 27 automation scripts · 26 reference guides · 4 OCR profiles · 217 tests · 0 LaTeX commands required

The 10-Second Pitch

You describe a document in plain English. This skill produces a compiled PDF.

• An 80-page handwritten math PDF becomes color-coded lecture notes with proper equations and TikZ diagrams.
• A 162-page textbook becomes a 2-page cheat sheet.
• A CSV becomes nine chart types.
• A one-line prompt becomes a thesis, a resume, a conference poster, or a 37-page book with drop caps.

No LaTeX knowledge required. The capybara handles the semicolons.

What Can It Actually Do?

(Spoiler: more than most humans with a PhD in LaTeX.)

Handwritten chaos in, publication-ready PDF out. It's not magic. It's 27 shell scripts.

Template Gallery -- 27 Templates

Every template has been compiled, tested, and verified to produce zero errors. The capybara is a perfectionist.

Resumes -- 5 ATS-Optimized + 1 Legacy

All 5 modern templates designed to pass Applicant Tracking Systems (no columns, no tables for layout, no graphics in header, machine-readable text):

Classic ATS	Modern Professional	Executive (p1)	Executive (p2)
Technical	Entry-Level

Academic Documents

Thesis / Dissertation -- Full book-class, 38+ pages

Palatino fonts, microtype, mathtools, cleveref. Front matter (title, declaration, abstract, acknowledgments, TOC), multiple chapters, appendices, bibliography with biblatex/biber. \geometry{bindingoffset=1.5cm} for professional printing.

Title Page	Table of Contents	Literature Review	TikZ Diagram
Results	Charts	Chapter Content	Bibliography

Academic Paper -- 11 pages, arXiv-compatible

Times fonts, colorblind-safe Tol palette, multi-author affiliations via authblk, siunitx for consistent units, algorithm environments, theorem/proof. \pdfoutput=1 for arXiv submission.

Title & Abstract	Tables + Charts	Ablation Study	References

Lecture Notes (Beautiful Mode) -- Color-coded theorem environments

lecture-notes.tex: Palatino fonts, tcolorbox with semantic colors -- blue theorems, green definitions, orange examples, purple remarks. TikZ graph theory macros, custom math operators (\E, \Var, \Cov).

Academic CV -- Multi-page with publications, grants, teaching

Numbered publications ([J1], [C1], [W1]), grants with dollar amounts, student advising (current + graduated), professional service, invited talks. ORCID and Google Scholar links.

Homework / Assignment -- Solution toggle

Custom problem/solution environments, code listings (Python, Java, C++, Matlab), honor code section. Toggle solutions globally with \showsolutionstrue/\showsolutionsfalse.

Lab Report -- STEM lab writeups

siunitx for uncertainties and SI units, pgfplots for data with error bars, structured sections: abstract -> theory -> procedure -> data -> analysis -> discussion -> conclusion.

Scientific Posters -- tikzposter class

Interactive workflow asks: conference -> orientation -> layout -> color scheme.

Conference presets: NeurIPS, ICML, CVPR, ICLR (main + workshop sizes).

Portrait A0	Landscape A0

Book -- Full-Length Publishing Template

book class, 37+ pages. Palatino fonts, lettrine drop caps, imakeidx for indexing. Structure: half-title -> full title -> copyright page (ISBN slot) -> dedication -> preface -> acknowledgments -> TOC -> parts -> chapters with epigraphs -> appendices -> bibliography -> index -> colophon.

Half Title	Full Title	Copyright	TOC	Preface
Acknowledgments	Part I	Ch 1: Drop Caps	Definitions & Theorems	Notation & Summary

Exam / Quiz -- exam class

6 question types (multiple choice, true/false, fill-in-blank, matching, short answer, essay). Point values per question, \gradetable[h][questions] for grading grid. \printanswers / \noprintanswers toggles solution visibility.

Cheat Sheets -- 3 Variants

Example: Algebraic Geometry (162 pages -> 2 pages)

Page 1 -- Affine/Projective Space, Varieties, Morphisms	Page 2 -- Sheaves, Schemes, Cohomology, Key Examples

Interactive / Dynamic Templates

Business Documents

letter.tex -- Business letter	cover-letter.tex -- Job application	invoice.tex -- Professional invoice

Presentation (presentation.tex) -- Beamer 16:9

Custom theme, widescreen aspect ratio, title/section/content/two-column/code/image/thank-you frame types.

Report (report.tex)

Executive summary, findings, recommendations with TOC, pgfplots bar charts, TikZ flowcharts, colored data tables.

Killer Features

(The things that make this more than "just another template repo.")

1. Smart Compilation Engine (compile_latex.sh -- 525 lines)

Not a wrapper around pdflatex. It is an intelligent build system that reads your document and makes decisions. Think of it as a capybara that learned to read .tex files.

Auto-detection logic:

Document contains \usepackage{fontspec} or \usepackage{xeCJK}  ->  xelatex
Document contains \usepackage{luacode} or \directlua            ->  lualatex
Otherwise                                                        ->  pdflatex

Document contains \bibliography{}                                ->  bibtex
Document contains \addbibresource{}                              ->  biber

Document contains \makeindex                                     ->  runs makeindex
Document contains \makeglossaries                                ->  runs makeglossaries

Multi-pass compilation: Runs the engine up to 3 times, checking for "Rerun to get cross-references right" each pass. Bibtex/biber runs between passes 1 and 2.

Auto-fix mode (--auto-fix):

Error translation -- parses .log and translates into actionable English:

Preview generation: After compilation, runs pdftoppm -png -r 200 on the output PDF and resizes to <=2000px.

bash scripts/compile_latex.sh document.tex --preview --auto-fix

2. PDF-to-LaTeX Reconstruction (Vision OCR Pipeline)

Convert any PDF -- scanned textbook, handwritten notes, printed report -- into compilable LaTeX. The capybara reads your handwriting better than your professor does.

Pipeline:

1. pdf_to_images.sh renders pages at 200 DPI using pdftoppm, zero-pads filenames, resizes to <=2000px for API limits
2. Vision model reads each page image
3. Generates .tex with profile-appropriate formatting

Scaling strategy (empirically validated on 115-page handwritten math notes):

4 conversion profiles (in references/profiles/):

3. PDF-to-Cheat Sheet Pipeline

Condense entire textbooks into 2-page reference cards. Because the night before the exam, you need density, not decoration.

Density techniques:

• Symbol substitution (for all -> "for all", there exists -> "there exists")
• Horizontal formula stacking with \quad separators
• Telegram-style text (articles and filler words stripped)
• Content prioritization: formulas 60-70% -> procedures 15-20% -> constants 10-15% -> definitions 5-10%
• Compile-and-verify loop to fit exact page budget

4. Mail Merge (mail_merge.py -- 574 lines)

Generate N personalized documents from one template + one data source. HR departments have hired worse interns.

python3 scripts/mail_merge.py template.tex contacts.csv \
    --output-dir ./letters --workers 4 --merge --merge-name all_letters.pdf

Two templating modes:

Technical details:

• Data sources: CSV, JSON, JSONL
• Uses concurrent.futures.ProcessPoolExecutor for parallel compilation
• Each document compiled independently (crash isolation)
• Final merge via qpdf --pages or pdfunite
• Custom naming: --name-field last_name --prefix "offer_letter" -> offer_letter_Smith.pdf

5. Version Diffing (latex_diff.sh -- 409 lines)

A full-featured latexdiff wrapper with git integration. Track every comma your advisor changed at 2 AM.

# Compare two files directly
bash scripts/latex_diff.sh paper_v1.tex paper_v2.tex --compile --preview

# Compare against a git commit
bash scripts/latex_diff.sh paper.tex --git-rev HEAD~3 --compile

# Compare between two git tags
bash scripts/latex_diff.sh paper.tex --git-rev v1.0 --compile --type CULINECHBAR

# Multi-file document with \input/\include
bash scripts/latex_diff.sh old/main.tex new/main.tex --flatten --compile

8 markup types:

Git integration: Extracts old version via git show <rev>:<path>, diffs against current working copy. Supports HEAD~1, v1.0, branch names.

Custom colors: --color-add "green!70!black" --color-del "red!80!black" injects override commands.

6. BibTeX Auto-Fetch (fetch_bibtex.sh -- 251 lines)

Download BibTeX entries from DOIs or arXiv IDs with zero manual work. No more copy-pasting from Google Scholar like an animal.

# From DOI
bash scripts/fetch_bibtex.sh 10.1038/nature12373

# From arXiv
bash scripts/fetch_bibtex.sh 2301.07041

# Multiple at once, append to existing .bib
bash scripts/fetch_bibtex.sh 10.1145/3290605.3300608 1906.08237 \
    --append --output references.bib

Auto-detects identifier type: 10.xxxx/... -> DOI, YYMM.NNNNN -> arXiv. Strips arXiv: prefix if present.

Visual Elements

Charts & Graphs (generate_chart.py -- 459 lines)

9 chart types from JSON or CSV data, output as PNG or PDF:

python3 scripts/generate_chart.py bar \
    --data '{"x":["Q1","Q2","Q3","Q4"],"y":[120,150,180,210]}' \
    --output chart.png --title "Revenue" --style ggplot --figsize 10 6

Inline charts can also be created directly in LaTeX using pgfplots.

Tables (csv_to_latex.py -- 364 lines)

python3 scripts/csv_to_latex.py data.csv --style booktabs --alternating-rows \
    --caption "Experimental Results" --label tab:results --max-rows 50

Auto-detects column alignment (right-aligns numeric columns). Handles LaTeX special character escaping.

Diagrams -- 4 Rendering Pipelines

Graphviz supports 6 layout engines: dot (hierarchical), neato (spring model), circo (circular), fdp (force-directed), twopi (radial), sfdp (scalable force-directed).

Mermaid uses npx @mermaid-js/mermaid-cli with Puppeteer. Themes: default, dark, forest, neutral.

PlantUML auto-downloads plantuml.jar if not installed. Requires Java.

Format Conversion (convert_document.sh -- 316 lines)

Pandoc wrapper with auto-detection of input/output formats from file extensions:

Markdown <-> LaTeX <-> DOCX <-> HTML <-> PDF

# Markdown to LaTeX
bash scripts/convert_document.sh notes.md notes.tex --standalone --toc

# DOCX to LaTeX with bibliography
bash scripts/convert_document.sh manuscript.docx manuscript.tex --bibliography refs.bib --csl ieee.csl

# LaTeX to PDF (uses lualatex if available for Unicode)
bash scripts/convert_document.sh paper.tex paper.pdf

PDF Utilities

All 4 scripts use qpdf (auto-installed if missing):

# Encrypt with restrictions
bash scripts/pdf_encrypt.sh report.pdf --user-password secret --restrict-print --restrict-modify

# Merge chapters into book
bash scripts/pdf_merge.sh ch1.pdf ch2.pdf ch3.pdf --output book.pdf

# Compress for email (shows % reduction)
bash scripts/pdf_optimize.sh large.pdf --output small.pdf

# Extract appendix
bash scripts/pdf_extract_pages.sh thesis.pdf --pages last:3 --output appendix.pdf

LaTeX Quality & Analysis Tools

Multi-Language Support

Behind every great PDF is a capybara who figured out the correct number of pdflatex passes.

Installation

# Install as a Claude Code skill
cp -r latex-document ~/.claude/skills/

# Or run full dependency setup
bash setup.sh            # Installs: TeX Live, Poppler, ImageMagick, Pandoc, Python deps
bash setup.sh --check    # Verify everything is installed

System dependencies (auto-installed by setup.sh on Debian/macOS/Fedora/Alpine/Arch):

• TeX Live -- pdflatex, xelatex, lualatex, biber, makeindex, makeglossaries
• Poppler -- pdftoppm for PNG previews, pdfinfo for page counts
• ImageMagick -- mogrify for image resizing, identify for dimensions
• Pandoc -- format conversion engine
• Python 3 + matplotlib, numpy, pandas
• qpdf -- PDF encryption, merging, optimization, page extraction

Optional:

• Node.js 18+ -- for Mermaid diagram conversion
• Java -- for PlantUML rendering
• Graphviz -- for .dot diagram rendering
• chktex -- for LaTeX linting
• latexdiff -- for version diffing

Reference Documentation

25 reference guides in references/:

Testing

217 tests covering all 27 scripts, 0 failures:

# Run all tests
bash tests/run_all_tests.sh

# Run individual suites
python -m pytest tests/test_python_scripts.py -v    # 83 tests
python -m pytest tests/test_pdf_forms.py -v          # 18 tests
bash tests/test_compile_latex.sh                     # 36 tests
bash tests/test_pdf_utils.sh                         # 33 tests
bash tests/test_analysis_tools.sh                    # 47 tests
bash tests/test_templates.sh                         # All 27 templates compiled

Tests found and fixed 2 real bugs in compile_latex.sh:

1. Engine detection matched %\usepackage{fontspec} in comments -- now filters commented lines
2. Float auto-fix regex failed when \begin{figure} was at end of line -- now uses two-pass approach

Project Structure

latex-document/
├── SKILL.md                              # Skill definition (329 lines)
├── README.md                             # You are here
├── setup.sh                              # One-click installer
├── requirements.txt                      # Python: matplotlib, numpy, pandas
│
├── assets/
│   ├── capy-professor.png                # The professor capybara (you saw him up top)
│   ├── capy-wizard.png                   # The wizard capybara (OCR sorcery)
│   ├── capy-printer.png                  # The printer capybara (steampunk vibes)
│   └── templates/                        # 27 production-tested .tex templates
│       ├── resume-*.tex (x6)
│       ├── thesis.tex, academic-paper.tex, academic-cv.tex
│       ├── lecture-notes.tex, homework.tex, lab-report.tex
│       ├── book.tex, poster.tex, poster-landscape.tex
│       ├── exam.tex, cheatsheet*.tex (x3)
│       ├── fillable-form.tex, conditional-document.tex, mail-merge-letter.tex
│       ├── letter.tex, cover-letter.tex, invoice.tex
│       ├── report.tex, presentation.tex
│       └── references.bib
│
├── scripts/                              # 27 automation scripts (8,700+ lines)
│   ├── compile_latex.sh          (525)   # .tex -> PDF + PNG
│   ├── mail_merge.py             (574)   # Template + data -> N PDFs
│   ├── generate_chart.py         (459)   # 9 chart types (matplotlib)
│   ├── validate_latex.py         (426)   # 6-check syntax validator
│   ├── latex_diff.sh             (409)   # latexdiff + git integration
│   ├── csv_to_latex.py           (364)   # CSV -> LaTeX tables
│   ├── plantuml_to_pdf.sh        (362)   # .puml -> PDF/PNG/SVG
│   ├── latex_citation_extract.sh (342)   # Citation analysis
│   ├── convert_document.sh       (316)   # Pandoc format conversion
│   ├── latex_package_check.sh    (265)   # Pre-flight package checker
│   ├── fetch_bibtex.sh           (251)   # DOI/arXiv -> BibTeX
│   ├── graphviz_to_pdf.sh        (250)   # .dot -> PDF/PNG
│   ├── pdf_extract_pages.sh      (247)   # Page extraction
│   ├── install_deps.sh           (237)   # Cross-platform deps
│   ├── pdf_validate_boxes.py     (235)   # Bounding box validation
│   ├── pdf_extract_fields.py     (228)   # Form field metadata
│   ├── pdf_fill_form.py          (223)   # Fill fillable forms
│   ├── latex_analyze.sh          (216)   # Document statistics
│   ├── pdf_encrypt.sh            (215)   # AES-256 encryption
│   ├── pdf_fill_annotations.py   (214)   # Fill non-fillable forms
│   ├── mermaid_to_image.sh       (178)   # .mmd -> PNG/PDF
│   ├── latex_lint.sh             (173)   # chktex wrapper
│   ├── pdf_optimize.sh           (157)   # Compress + linearize
│   ├── latex_wordcount.sh        (149)   # Word count
│   ├── pdf_to_images.sh          (144)   # PDF -> page images
│   ├── pdf_merge.sh              (136)   # Merge PDFs
│   └── pdf_check_form.py         (106)   # Detect form fields
│
├── references/                           # 26 deep-dive guides
│   ├── *.md (x26)
│   └── profiles/ (x4)                   # OCR profiles
│
├── tests/                                # 217 tests, 0 failures
│   ├── test_python_scripts.py   (1224)
│   ├── test_compile_latex.sh     (844)
│   ├── test_analysis_tools.sh   (1093)
│   ├── test_pdf_utils.sh         (834)
│   ├── test_pdf_forms.py         (300)
│   ├── test_templates.sh         (276)
│   ├── run_all_tests.sh          (191)
│   └── fixtures/
│
└── examples/                             # 78 PNG previews

Star History

Sponsor

This project is proudly sponsored by HappyCapy

HappyCapy provided free access to their platform, full Claude Code API credits, and Anthropic Claude Opus 4.6 -- the model that built every template, wrote every script, and generated every capybara image in this repository.

Without HappyCapy, this skill would still be a half-baked idea on a sticky note. Instead, it's 27 templates, 27 scripts, 217 passing tests, and three capybara mascots with better fashion sense than most academics.

What is HappyCapy? The agent-native computer for developers. No local setup, no security risks, no "works on my machine" excuses. Launch Claude Code in your browser and start building. It's the platform where capybaras and code live in harmony.

Try HappyCapy for free

License

MIT

Keywords

For the search engines, the LLMs, and the curious humans who find things by typing random words into the void

LaTeX template, LaTeX automation, AI document generation, Claude Code skill, PDF creation tool, LaTeX PDF generator, academic document template, professional document automation, resume LaTeX template ATS, thesis template LaTeX, invoice generator LaTeX, report generator LaTeX, OCR to LaTeX, handwritten notes to PDF, PDF to LaTeX converter, cheat sheet generator, mail merge LaTeX, BibTeX auto fetch, LaTeX diff tool, version control LaTeX, arXiv paper template, NeurIPS poster template, conference poster LaTeX, exam template LaTeX, lecture notes LaTeX, book template LaTeX, Beamer presentation template, LaTeX compilation script, LaTeX error fixer, smart LaTeX compiler, chart generator matplotlib, CSV to LaTeX table, Mermaid diagram LaTeX, Graphviz LaTeX, PlantUML LaTeX, PDF encryption tool, PDF merge tool, PDF compression, fillable PDF form, LaTeX linting, LaTeX word count, document format conversion, Pandoc LaTeX, multi-language LaTeX, CJK LaTeX, RTL LaTeX, capybara LaTeX, AI typesetting, automated document creation, universal document skill, Claude Code plugin, AI coding assistant skill, LLM document generation, generative AI documents, GPT LaTeX alternative, AI-powered typesetting, best LaTeX skill, free LaTeX templates, open source LaTeX automation