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
Recommend AND run open-source AI tools, agents, Claude Code / Codex skills, and MCP servers for any stage of a literature review — searching, reading, extracting, synthesizing, screening, citation-checking, and paper writing. Use when the user asks "what tool should I use to..." OR "install/run/use <tool> to ..." for research/lit-review work: automating a survey or related-work section, PDF→Markdown extraction for LLMs (MinerU/marker/docling), PRISMA / systematic review (ASReview), citation-backed Q&A over PDFs (PaperQA2), wiring papers into Claude/Cursor via MCP (arxiv/paper-search/zotero servers), or chatting with a Zotero library. Ships a launcher (scripts/litrun.py) that installs each tool in an isolated venv and runs it. Curated catalog of 70+ vetted projects. 支持中英文(用于「文献综述工具选型」与「一键安装/运行」)。
development
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
documentation
Use when the project collects primary data or runs a field, lab, or survey experiment, before the intervention begins — write the pre-analysis plan, size the sample from a power calculation, and register with the AEA RCT Registry. Apply after the design is chosen in aer-identification and before any outcome data are seen.
tools
Guide economists to authoritative data sources with explicit, confirmed data specifications before retrieval; interfaces with Playwright MCP to navigate portals and extract real data, not articles about data.