agentsclimarketplace

Scientific article pdf

Skill dongzhigang13305312738-art/paper-skills/scientific-article-pdf

📝 124 个 SCI/SSCI 论文写作 AI 技能合集:选题→文献综述→实验→图表→写作→润色→去AI痕迹→投稿,一个 paper-studio 总入口全流程调度。支持 Claude Code / WorkBuddy。

Install
npx -y skills add dongzhigang13305312738-art/paper-skills --skill scientific-article-pdf

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

3 things to look at

  • 17 days oldThe repository was created 17 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Generate publication-ready scientific article PDFs from templates

SKILL.md

7.8 KB, ~2.0k tokens by cl100k_base, as published. Nobody here has run it

Scientific Article PDF

Overview

Producing a publication-ready PDF that meets the exact formatting requirements of a target journal or conference is one of the final and most frustrating steps of the research publication process. Each venue has its own LaTeX class file, formatting rules, margin specifications, font requirements, and reference style. Getting these details wrong can lead to desk rejection before your paper even reaches a reviewer.

This skill provides a systematic approach to generating correctly formatted scientific article PDFs. It covers obtaining and using official LaTeX templates, configuring common elements (title blocks, author affiliations, abstracts, section numbering, bibliography), and troubleshooting formatting issues that arise during compilation. The goal is to produce a PDF that compiles cleanly and passes the publisher's automated format checks on the first try.

The skill focuses on LaTeX-based workflows, as LaTeX remains the standard for most scientific venues, particularly in STEM fields. It includes guidance for major publishers and conference families.

Obtaining Official Templates

Major Publisher Templates

Always start from the official template provided by your target venue. Using a custom or outdated template is a common cause of formatting problems.

IEEE:

# IEEE conference and journal templates
# Download from: https://www.ieee.org/conferences/publishing/templates.html
# Key files: IEEEtran.cls, IEEEtran.bst
wget https://www.ieee.org/content/dam/ieee-org/ieee/web/org/pubs/conference-latex-template_10-17-19.zip

ACM (Association for Computing Machinery):

# ACM Primary Article Template
# Download from: https://www.acm.org/publications/proceedings-template
# Key file: acmart.cls (supports all ACM formats)
# Use: \documentclass[sigconf]{acmart}  % for conference
#      \documentclass[acmlarge]{acmart}  % for journal

Springer (LNCS - Lecture Notes in Computer Science):

# Download from: https://www.springer.com/gp/computer-science/lncs/conference-proceedings-guidelines
# Key file: llncs.cls
# Typical usage: \documentclass[runningheads]{llncs}

Elsevier:

# Elsevier article template
# Download from: https://www.elsevier.com/authors/policies-and-guidelines/latex-instructions
# Key file: elsarticle.cls
# Usage: \documentclass[preprint,12pt]{elsarticle}  % for submission
#        \documentclass[final,3p,times]{elsarticle}  % for camera-ready

NeurIPS / ICML / ICLR:

# NeurIPS: https://neurips.cc/Conferences/2026/PaperInformation/StyleFiles
# ICML: https://icml.cc/Conferences/2026/StyleAuthorInstructions
# ICLR: Uses OpenReview; template available from submission portal

Template Verification

After downloading a template, verify it compiles correctly before writing:

# Compile the sample document
pdflatex sample.tex
bibtex sample       # or biber sample
pdflatex sample.tex
pdflatex sample.tex  # Two passes to resolve references

# Check for warnings
grep -i "warning" sample.log | head -20

Document Structure Template

Here is a general-purpose structure that works across most scientific article templates:

\documentclass[options]{template-class}

% ========== Packages ==========
\usepackage[utf8]{inputenc}     % UTF-8 encoding
\usepackage{amsmath,amssymb}    % Math symbols
\usepackage{graphicx}           % Figures
\usepackage{booktabs}           % Professional tables
\usepackage{hyperref}           % Clickable links
\usepackage{algorithm2e}        % Algorithm pseudocode
\usepackage{microtype}          % Typographic refinement

% ========== Metadata ==========
\title{Your Paper Title}
\author{%
  Author One\thanks{Corresponding author: [email protected]} \\
  University of Example \\
  \and
  Author Two \\
  Institute of Research
}
\date{}

\begin{document}
\maketitle

\begin{abstract}
Your abstract text here (typically 150-300 words).
\end{abstract}

\section{Introduction}
\label{sec:intro}

\section{Related Work}
\label{sec:related}

\section{Method}
\label{sec:method}

\section{Experiments}
\label{sec:experiments}

\section{Conclusion}
\label{sec:conclusion}

\section*{Acknowledgments}
This work was supported by...

\bibliographystyle{template-bst}
\bibliography{references}

\appendix
\section{Additional Results}
\label{app:results}

\end{document}

Common Formatting Tasks

Professional Tables with booktabs

\begin{table}[t]
\centering
\caption{Comparison of methods on the benchmark dataset.}
\label{tab:results}
\begin{tabular}{lccc}
\toprule
Method & Accuracy & F1 Score & Params (M) \\
\midrule
Baseline A & 82.3 & 79.1 & 110 \\
Baseline B & 84.7 & 81.4 & 145 \\
\textbf{Ours} & \textbf{87.6} & \textbf{84.9} & 95 \\
\bottomrule
\end{tabular}
\end{table}

Figure Placement

\begin{figure}[t]  % [t]=top, [b]=bottom, [h]=here, [p]=page of floats
\centering
\includegraphics[width=0.9\columnwidth]{figures/architecture.pdf}
\caption{Overview of the proposed architecture. The encoder (left)
processes input features while the decoder (right) generates
predictions autoregressively.}
\label{fig:architecture}
\end{figure}

Algorithm Pseudocode

\begin{algorithm}[t]
\caption{Training Procedure}
\label{alg:training}
\KwIn{Dataset $\mathcal{D}$, learning rate $\eta$, epochs $T$}
\KwOut{Trained model parameters $\theta^*$}
Initialize $\theta$ randomly\;
\For{$t = 1$ \KwTo $T$}{
    \ForEach{batch $(x, y) \in \mathcal{D}$}{
        $\hat{y} \gets f_\theta(x)$\;
        $\mathcal{L} \gets \text{Loss}(\hat{y}, y)$\;
        $\theta \gets \theta - \eta \nabla_\theta \mathcal{L}$\;
    }
}
\Return $\theta$\;
\end{algorithm}

Build Pipeline and Automation

Makefile for Clean Builds

MAIN = paper
LATEX = pdflatex
BIB = bibtex

all: $(MAIN).pdf

$(MAIN).pdf: $(MAIN).tex references.bib
	$(LATEX) $(MAIN)
	$(BIB) $(MAIN)
	$(LATEX) $(MAIN)
	$(LATEX) $(MAIN)

clean:
	rm -f *.aux *.bbl *.blg *.log *.out *.toc *.fls *.fdb_latexmk

check:
	@echo "=== Overfull boxes ==="
	@grep -c "Overfull" $(MAIN).log || echo "None"
	@echo "=== Undefined references ==="
	@grep -c "undefined" $(MAIN).log || echo "None"
	@echo "=== Missing citations ==="
	@grep -c "Citation.*undefined" $(MAIN).log || echo "None"

.PHONY: all clean check

Using latexmk for Automatic Rebuilds

# latexmk automatically determines how many passes are needed
latexmk -pdf paper.tex

# Continuous mode: recompiles on file changes
latexmk -pdf -pvc paper.tex

# Clean up auxiliary files
latexmk -c paper.tex

Troubleshooting

ProblemSolution
"Overfull hbox" warningsRephrase text, use \sloppy locally, or adjust figure widths
Missing referencesRun BibTeX/Biber and re-run LaTeX twice
Figures not foundUse paths relative to the main .tex file; check file extensions
Font not foundInstall the required font package: tlmgr install <font>
Page limit exceededMove content to appendix; tighten prose; reduce figure sizes
"Too many unprocessed floats"Add \clearpage or use the placeins package with \FloatBarrier

References

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most pdf office docs skills give in ~2.0k tokens

Counted across 636 of the 690 authors here whose files we hold, read 2026-08-07

  • extract text using pdfplumberin 89 of 636, across 23 files
  • create PDFs using reportlabin 83 of 636, across 16 files
  • read forms.md to fill out pdf formsin 80 of 636, across 13 files
  • OCR scanned PDFs using pytesseractin 77 of 636, across 10 files
  • merge or split PDFs using qpdfin 70 of 636, across 3 files
  • use excel formulas instead of hardcoded calculated valuesin 68 of 636, across 13 files
  • unpack edit xml and repack existing documentsin 63 of 636, across 8 files
  • document sources for hardcoded valuesin 61 of 636, across 9 files
  • write minimal python code without unnecessary commentsin 59 of 636, across 7 files
  • run the recalculation script after adding or modifying formulasin 59 of 636, across 7 files
  • fix all identified formula errors and recalculatein 58 of 636, across 6 files
  • format years as text stringsin 57 of 636, across 5 files

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.