skills/43-wentorai-research-plugins/skills/writing/templates/thuthesis-guide/SKILL.md
Write Tsinghua University theses using the ThuThesis LaTeX template
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research thuthesis-guideInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
ThuThesis is the official LaTeX thesis template for Tsinghua University, one of China's most prestigious research institutions. Maintained by TUNA (Tsinghua University Network Administrators), the template provides comprehensive formatting for bachelor's, master's, and doctoral theses, as well as postdoctoral reports, ensuring full compliance with Tsinghua University's stringent formatting requirements.
Writing a thesis involves balancing content creation with precise typographic standards. ThuThesis eliminates the formatting burden by encoding all institutional requirements into LaTeX class files: page margins, font selections, heading hierarchy, bibliography formatting, front matter structure, and appendix layout are all handled automatically. Researchers can focus entirely on writing while the template ensures every page, caption, and citation meets the graduation office requirements.
With over 5,000 GitHub stars, ThuThesis has become the de facto standard for thesis typesetting at Tsinghua. Its codebase also serves as a reference implementation for other university thesis templates in China, influencing templates at dozens of institutions.
TeX Live Installation (recommended):
ThuThesis requires a complete TeX distribution. Install TeX Live (full scheme recommended to avoid missing packages):
# On macOS via Homebrew
brew install --cask mactex
# On Ubuntu/Debian
sudo apt-get install texlive-full
# On Windows, download TeX Live from tug.org/texlive
Download ThuThesis:
git clone https://github.com/tuna/thuthesis.git
cd thuthesis
Alternatively, download the latest release from the GitHub releases page or install via CTAN:
tlmgr install thuthesis
Compile the template:
# Using latexmk (recommended)
latexmk -xelatex main.tex
# Or manually
xelatex main.tex
bibtex main
xelatex main.tex
xelatex main.tex
XeLaTeX is required rather than pdfLaTeX because the template uses system fonts for Chinese typesetting. Ensure you have the required fonts installed (SimSun, SimHei, KaiTi, FangSong for Windows; or their equivalents on macOS and Linux).
Degree Type Configuration: A single configuration option switches between thesis formats:
\documentclass[
degree=doctor, % bachelor, master, doctor, or postdoc
degree-type=academic % academic or professional
]{thuthesis}
Each degree type automatically adjusts title page layout, committee signature pages, abstract formatting, and chapter numbering conventions.
Bilingual Support: Tsinghua requires both Chinese and English abstracts, title pages, and keywords. ThuThesis provides dedicated environments for each:
\begin{abstract}
This thesis investigates the application of deep learning methods
to protein structure prediction, focusing on attention mechanisms
that capture long-range amino acid interactions.
\end{abstract}
\begin{abstract*}
% Chinese abstract here
\end{abstract*}
Bibliography Management: The template integrates with BibTeX and supports the GB/T 7714 citation standard required by Chinese academic institutions:
\usepackage[backend=bibtex, style=gb7714-2015]{biblatex}
\addbibresource{references.bib}
% In text
\cite{einstein1905}
\parencite{dirac1928}
Mathematical Typesetting: Full support for equations, theorems, and proofs with consistent numbering tied to chapter structure:
\begin{theorem}\label{thm:convergence}
Under assumptions A1--A3, the proposed estimator converges
at rate $O(n^{-1/2})$ uniformly over the parameter space.
\end{theorem}
\begin{proof}
By the triangle inequality and Lemma~\ref{lem:concentration}...
\end{proof}
Figure and Table Formatting: Captions, numbering, and cross-referencing follow institutional standards automatically. The template supports subfigures and multi-page tables.
ThuThesis provides a standard project structure:
thuthesis/
main.tex # Master document
thuthesis.cls # Class file (do not modify)
thuthesis-setup.tex # Personal info and thesis metadata
data/
abstract.tex # Abstracts (CN + EN)
chap01.tex # Chapter 1
chap02.tex # Chapter 2
...
appendix01.tex # Appendices
acknowledgements.tex
resume.tex # Publication list
figures/ # All figures
ref/
refs.bib # Bibliography database
Edit thuthesis-setup.tex to fill in your personal information:
\thusetup{
title = {Deep Learning for Protein Structure Prediction},
title* = {Your Chinese title here},
author = {Zhang San},
supervisor = {Prof. Li Si},
degree-name = {Doctor of Engineering},
department = {Department of Computer Science},
date = {2026-06-01},
}
Version Control: The plain-text LaTeX source works seamlessly with Git. Track changes across drafts, collaborate with advisors via pull requests, and maintain a complete revision history:
git init
git add main.tex data/ figures/ ref/
git commit -m "Initial thesis structure"
Continuous Compilation: Use latexmk in watch mode during writing for immediate feedback:
latexmk -xelatex -pvc main.tex
Overleaf Compatibility: Upload the ThuThesis files to Overleaf for cloud-based editing. Set the compiler to XeLaTeX in project settings. Note that some system fonts may not be available on Overleaf; the template includes fallback font configurations.
Advisor Collaboration: Generate PDF versions for advisor review while maintaining the LaTeX source as the canonical version. Use PDF annotation tools for feedback and incorporate changes back into the source files.
tools
Show mcp-stata identity, connected tools, and status. Use when the user asks if mcp-stata is available, asks about access to the toolkit, or asks what Stata tools are connected.
tools
Activate when users mention Stata commands, .do files, regressions, econometrics, stored results, graphs, dataset inspection, replication, or Stata errors. Route the task through mcp-stata tools and the specialized research skills instead of treating it as plain text coding.
development
Build and review paper-ready regression, balance, and summary tables from Stata outputs. Use when the user needs a clean table for a draft, appendix, or coauthor share-out.
tools
Install, configure, update, or verify mcp-stata across Claude Code, Codex, Gemini CLI, Cursor, Windsurf, and VS Code. Activate when users ask to set up the Stata toolkit or troubleshoot the installation.