Paper Writing Section

Paper Section Writer

Write a publication-quality section for an academic paper.

Input

• $0 — Section name: abstract, introduction, background, related-work, methods, experimental-setup, results, discussion, conclusion
• $1 — (Optional) Path to context file (research plan, results, prior sections)

Workflow

Step 1: Gather Context

Read the paper's existing .tex files, experiment logs, result files, and any provided context. Understand: title, contributions, methodology, key results, figures, tables.

Step 2: Write the Section

Load section-specific tips from references/section-tips.md. Before every paragraph, include a brief plan as a LaTeX comment (% Plan: ...).

Step 3: Two-Pass Refinement

Apply both refinement passes from references/refinement-prompts.md:

• Pass 1: Fix errors (unenclosed math, broken refs, hallucinated numbers, duplicate labels)
• Pass 2: Remove redundancies, compress, ensure smooth transitions

References

• Section writing tips: ~/.claude/skills/paper-writing-section/references/section-tips.md
• Refinement prompts and error checklist: ~/.claude/skills/paper-writing-section/references/refinement-prompts.md

Output

LaTeX fragment (no \documentclass, no preamble). All math enclosed in $...$ or \begin{equation}, all figures referenced with \ref{}, all cited works use \cite{}, no placeholder text.

Quality Checklist

• All math enclosed properly
• All \ref{} and \cite{} valid
• No TODO/TBD/FIXME markers
• Numbers match experimental logs exactly
• Writing style is objective — no hype words
• Section length appropriate for venue

Related Skills

• Upstream: data-analysis, figure-generation, table-generation, related-work-writing
• Downstream: latex-formatting, citation-management
• See also: paper-assembly

Two-Pass Refinement Prompts

Extracted verbatim from AI-Scientist perform_writeup.py.

Error Checklist

When refining any section, check for these specific errors:

• Unenclosed math symbols
• Only reference figures that exist in our directory
• LaTeX syntax errors
• Numerical results that do not come from explicit experiments and logs
• Repeatedly defined figure labels
• References to papers that are not in the .bib file, DO NOT ADD ANY NEW CITATIONS!
• Unnecessary verbosity or repetition, unclear text
• Results or insights in the notes.txt that have not yet been included
• Any relevant figures that have not yet been included in the text
• Closing any \begin{figure} with a \end{figure} and \begin{table} with a \end{table}, etc.
• Duplicate headers, e.g. duplicated \section{Introduction} or \end{document}
• Unescaped symbols, e.g. shakespeare_char should be shakespeare\_char in text
• Incorrect closing of environments, e.g. </end{figure}> instead of \end{figure}

Pass 1: Error Correction

Great job! Now criticize and refine only the {section} that you just wrote.
Make this complete in this pass, do not leave any placeholders.

Pay particular attention to fixing any errors such as:
[error checklist above]

Pass 2: Compression and Polish

Criticize and refine the {section} only. Recall the advice:
{tips for this section}
Make this complete in this pass, do not leave any placeholders.

Pay attention to how it fits in with the rest of the paper.
Identify any redundancies (e.g. repeated figures or repeated text), if there are any, decide where in the paper things should be cut.
Identify where we can save space, and be more concise without weakening the message of the text.
Fix any remaining errors as before:
[error checklist above]

Section Generation Prompt Template

For each section, use this pattern:

Please fill in the {section} of the writeup. Some tips are provided below:
{per_section_tips[section]}

Be sure to use \cite or \citet where relevant, referring to the works provided in the file.
Do not cite anything that is not already in references.bib. Do not add any new entries to this.

Keep the experimental results (figures and tables) only in the Results section, and make sure that any captions are filled in.
In this pass, do not reference anything in later sections of the paper.

Before every paragraph, please include a brief description of what you plan to write in that paragraph in a comment.

Related Work Sketch (before citation harvesting)

Please fill in the Related Work of the writeup. Some tips are provided below:

{per_section_tips["Related Work"]}

For this section, very briefly sketch out the structure of the section, and clearly indicate what papers you intend to include.
Do this all in LaTeX comments using %.
The related work should be concise, only plan to discuss the most relevant work.
Do not modify references.bib to add any new citations, this will be filled in at a later stage.

Per-Section Writing Tips

Extracted verbatim from AI-Scientist (perform_writeup.py) and AgentLaboratory (papersolver.py).

Abstract

• TL;DR of the paper
• What are we trying to do and why is it relevant?
• Why is this hard?
• How do we solve it (i.e. our contribution!)
• How do we verify that we solved it (e.g. Experiments and results)
• This must only be a single paragraph, not more.
• Please make sure the abstract reads smoothly and is well-motivated. This should be one continuous paragraph with no breaks between the lines.

Introduction

• Longer version of the Abstract, i.e. of the entire paper
• What are we trying to do and why is it relevant?
• Why is this hard?
• How do we solve it (i.e. our contribution!)
• How do we verify that we solved it (e.g. Experiments and results)
• New trend: specifically list your contributions as bullet points
• Extra space? Future work!

Related Work

• Academic siblings of our work, i.e. alternative attempts in literature at trying to solve the same problem.
• Goal is to "Compare and contrast" - how does their approach differ in either assumptions or method? If their method is applicable to our Problem Setting I expect a comparison in the experimental section. If not, there needs to be a clear statement why a given method is not applicable.
• Note: Just describing what another paper is doing is not enough. We need to compare and contrast.

Background

• Academic Ancestors of our work, i.e. all concepts and prior work that are required for understanding our method.
• Usually includes a subsection, Problem Setting, which formally introduces the problem setting and notation (Formalism) for our method. Highlights any specific assumptions that are made that are unusual.
• Make sure to use mathematical notation when necessary.
• Note: If our paper introduces a novel problem setting as part of its contributions, it's best to have a separate Section.

Methods

• What we do. Why we do it. All described using the general Formalism introduced in the Problem Setting and building on top of the concepts / foundations introduced in Background.
• Make sure you clearly report precise mathematical equations in the methods section and the precise methodology.

Experimental Setup

• How do we test that our stuff works? Introduces a specific instantiation of the Problem Setting and specific implementation details of our Method for this Problem Setting.
• Do not imagine unknown hardware details.
• Includes a description of the dataset, evaluation metrics, important hyperparameters, and implementation details.

Results

• Shows the results of running Method on our problem described in Experimental Setup.
• Includes statements on hyperparameters and other potential issues of fairness.
• Only includes results that have actually been run and saved in the logs. Do not hallucinate results that don't exist.
• Make sure you clearly and numerically report experimental results in the results section.
• If results exist: compares to baselines and includes statistics and confidence intervals.
• If results exist: includes ablation studies to show that specific parts of the method are relevant.
• Discusses limitations of the method.
• Make sure to include all the results from the experiments, and include all relevant figures.

Discussion / Conclusion

• Brief recap of the entire paper.
• To keep going with the analogy, you can think of future work as (potential) academic offspring.