skills/43-wentorai-research-plugins/skills/writing/templates/thesis-writing-guide/SKILL.md
Templates, formatting rules, and strategies for thesis and dissertation writing
npx skillsauth add brycewang-stanford/Awesome-Agent-Skills-for-Empirical-Research thesis-writing-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.
Writing a thesis or dissertation is the culminating challenge of graduate education. Unlike journal papers, a thesis demands sustained coherence across hundreds of pages, covering background, methodology, multiple studies, and synthesis. The formatting requirements are often institution-specific and unforgiving -- a misplaced margin or incorrect heading style can delay your defense.
This guide draws from the awesome-thesis repository (626+ stars), which curates practical tips and tricks for computer science theses, and extends the advice to cover all disciplines. It covers thesis structure, LaTeX and Word templates, formatting checklists, writing strategies for long documents, and common pitfalls that delay graduation.
Whether you are writing a master's thesis (50-100 pages) or a PhD dissertation (150-300 pages), the planning and execution patterns here will help you finish on time and produce a document you are proud of.
| Chapter | Content | Typical Pages | |---------|---------|---------------| | 1. Introduction | Problem, motivation, contributions, outline | 10-20 | | 2. Background | Core concepts, definitions, prerequisites | 15-25 | | 3. Related Work | Comprehensive literature review | 15-30 | | 4. Methodology | Your approach, design, algorithms | 20-40 | | 5. Experiments | Setup, results, analysis | 20-40 | | 6. Discussion | Interpretation, limitations, broader impact | 10-20 | | 7. Conclusion | Summary, contributions, future work | 5-10 |
Many institutions now accept theses composed of published papers:
Chapter 1: Introduction and Overview (new content, 15-20 pages)
Chapter 2: Paper A (published, reformatted)
Chapter 3: Paper B (published, reformatted)
Chapter 4: Paper C (under review, reformatted)
Chapter 5: Synthesis and Conclusion (new content, 10-15 pages)
Appendix: Supplementary materials for each paper
The key challenge with compilation theses is the "red thread" -- the narrative that connects your papers into a coherent whole. The introduction and conclusion chapters carry this responsibility.
Most universities provide official LaTeX templates. Here is a generic setup:
\documentclass[12pt, a4paper, twoside]{report}
% Essential packages
\usepackage[margin=1in, bindingoffset=0.5in]{geometry}
\usepackage{setspace}
\doublespacing
\usepackage[hidelinks]{hyperref}
\usepackage{cleveref}
\usepackage[backend=biber, style=numeric]{biblatex}
\addbibresource{thesis.bib}
% Front matter
\begin{document}
\frontmatter
\include{chapters/titlepage}
\include{chapters/abstract}
\include{chapters/acknowledgments}
\tableofcontents
\listoffigures
\listoftables
% Main content
\mainmatter
\include{chapters/introduction}
\include{chapters/background}
\include{chapters/related_work}
\include{chapters/methodology}
\include{chapters/experiments}
\include{chapters/discussion}
\include{chapters/conclusion}
% Back matter
\backmatter
\printbibliography
\appendix
\include{chapters/appendix_a}
\end{document}
| Template | Institution/Style | Link |
|----------|-------------------|------|
| thuthesis | Tsinghua University | github.com/tuna/thuthesis |
| SJTUThesis | Shanghai Jiao Tong | github.com/sjtug/SJTUThesis |
| Dissertate | Harvard (multi-school) | github.com/suchow/Dissertate |
| novathesis | Universidade Nova de Lisboa | github.com/joaomlourenco/novathesis |
| cleanthesis | Generic clean style | github.com/derric/cleanthesis |
thesis/
main.tex # Master file
thesis.bib # Bibliography
chapters/
titlepage.tex
abstract.tex
introduction.tex
...
figures/
ch1/
ch2/
...
tables/
code/ # Code listings
Makefile # Build automation
.gitignore
For a 6-month writing period:
| Month | Task | Deliverable | |-------|------|------------| | 1 | Outline all chapters; write Methods | Methods draft | | 2 | Write Experiments chapter | Experiments draft | | 3 | Write Background and Related Work | Literature review draft | | 4 | Write Discussion and Conclusion | Full rough draft | | 5 | Write Introduction; revise all chapters | Complete first draft | | 6 | Advisor review; final revisions; formatting | Submission-ready thesis |
latexdiff or track changes in Word.# Generate a visual diff between thesis versions
latexdiff old_version.tex new_version.tex > diff.tex
pdflatex diff.tex
Before submission, verify every item:
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.