SkillAgentSearch skills...

research-paper-writing

Pipeline for ML/AI research papers — lit review to LaTeX submission

Install / Use

npx skills add taracodlabs/aiden --skill research-paper-writing

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

85/100

Category

Automation

Supported Platforms

Universal

Our assessment of research-paper-writing

research-paper-writing scores 85/100 on our quality scale, 1987th of 2,769 Automation skills we index.

Its SKILL.md is 4.8 KB long, well organised into 14 sections with 7 code examples: a solid amount of guidance for an agent.

It has 843 GitHub stars, a meaningful sign that others use it.

Substance
26/30
Structure
20/20
Description
12/15
Adoption
12/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated about 2 months ago, so research-paper-writing is actively maintained.
  • Our last check on 2026-11-05 found the source still online.
  • It is released under AGPL-3.0, a copyleft license: you can use it, but modified versions you distribute must carry the same license.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-10-06. Automated pattern scan on 2026-10-06. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

research-paper-writing compared with similar skills

All 4 of these similar skills score higher than research-paper-writing; compare them before choosing.

SkillScoreStarsUpdatedFormat
research-paper-writing (this skill)by taracodlabs858432mo agoSKILL.md
taste-skillby Leonxlnx100117.6k9d agoCLAUDE.md
Agent-Reachby Panniantong100112.7k9d agoCLAUDE.md
rufloby ruvnet10082.0ktodayCLAUDE.md
Claude-Code-Game-Studiosby Donchitos10039.9k8d agoCLAUDE.md

Frequently asked questions

How do I install research-paper-writing?
Run npx skills add taracodlabs/aiden --skill research-paper-writing. The install tabs above show the steps for each supported agent.
Which AI agents does research-paper-writing work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is research-paper-writing safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is AGPL-3.0-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is research-paper-writing still maintained?
The repository was last updated about 2 months ago, so research-paper-writing is actively maintained.

name: research-paper-writing description: Pipeline for ML/AI research papers — lit review to LaTeX submission category: research version: 1.0.0 origin: aiden license: Apache-2.0 tags: research, paper, writing, latex, ml, ai, academic, arxiv, publication, citation

Research Paper Writing Pipeline

A structured, step-by-step pipeline for writing ML/AI research papers: from problem framing through literature review, experiment design, writing, and LaTeX formatting for arXiv submission.

When to Use

  • User wants to write or structure an academic research paper
  • User wants help organizing experiments and results for a paper
  • User wants to format a paper in LaTeX for arXiv or a conference
  • User wants to do a literature review on a topic
  • User wants to write an abstract, introduction, or related work section

How to Use

Phase 1: Frame the contribution

Define the paper's core claim before writing anything else.

1. One-sentence contribution: "We show that X outperforms Y on Z by doing W"
2. Key insight: what is non-obvious about your approach?
3. Research question: what question does the paper answer?
4. Limitations scope: what is explicitly out of scope?

Phase 2: Literature review

Use the arXiv skill to find related work, then organize findings:

Search strategy:
- Start with 2-3 "seed" papers you know are relevant
- Find papers that cite them (via Semantic Scholar API)
- Search arXiv for your core keywords + recent date filter
- Organize into: direct predecessors, concurrent work, tangential work

For each related paper, note:
- Core method
- Dataset/benchmark used
- Key result number
- How your work differs
# Semantic Scholar API — find papers citing a known paper
import requests
paper_id = "arXiv:2305.17333"
resp = requests.get(f"https://api.semanticscholar.org/graph/v1/paper/{paper_id}/citations?fields=title,year,authors,externalIds&limit=20")
for c in resp.json()["data"]:
  print(c["citingPaper"]["title"])

Phase 3: Structure the paper

Standard ML/AI paper structure:

Abstract   (150-250 words) — problem, method, key result, significance
1. Introduction — motivation, gap, contribution, paper overview
2. Related Work — organize by theme, not chronologically
3. Method — notation, architecture/algorithm, key design choices
4. Experiments — datasets, baselines, metrics, implementation details
5. Results — main table, ablation study, qualitative examples
6. Discussion — limitations, failure modes, future work
7. Conclusion — restate contribution, broader impact
References
Appendix (optional) — proofs, additional experiments, hyperparameters

Phase 4: Write in LaTeX

Basic arXiv-ready template:

\documentclass[10pt,twocolumn]{article}
\usepackage{arxiv}       % from https://github.com/kourgeorge/arxiv-style
\usepackage{amsmath,amssymb,graphicx,booktabs,hyperref}

\title{Your Paper Title}
\author{Author One \and Author Two}
\date{\today}

\begin{document}
\maketitle

\begin{abstract}
Your abstract here. State the problem, method, key result, and significance in 150--250 words.
\end{abstract}

\section{Introduction}
...

\bibliography{refs}
\bibliographystyle{plain}
\end{document}

Phase 5: Tables and figures

% Results table with booktabs
\begin{table}[t]
\centering
\caption{Comparison on benchmark dataset.}
\begin{tabular}{lcc}
\toprule
Method & Accuracy & F1 \\
\midrule
Baseline   & 72.3 & 71.1 \\
Prior SOTA & 78.6 & 77.9 \\
\textbf{Ours} & \textbf{83.2} & \textbf{82.7} \\
\bottomrule
\end{tabular}
\label{tab:results}
\end{table}

Phase 6: Compile and check

# Compile LaTeX (requires MiKTeX or TeX Live)
pdflatex paper.tex
bibtex paper
pdflatex paper.tex
pdflatex paper.tex   # run twice to resolve references

# Check word count
texcount paper.tex

Examples

"Help me write the abstract for my paper on efficient transformers" → Use Phase 1 to extract the core claim, then write 4 sentences: problem → gap → method → key result.

"I need to find related papers on sparse attention before writing the related work section" → Use Phase 2: search arXiv (cs.LG + sparse attention), use Semantic Scholar to find citing papers.

"Format my experiment results as a LaTeX table" → Use Phase 5 with the booktabs template.

Cautions

  • Write the related work section after the method section — you need to know your contribution to characterize prior work accurately
  • Ablation studies are required at top venues (NeurIPS, ICML, ICLR) — plan them during experiment design, not after
  • arXiv LaTeX compilation is strict — avoid non-standard packages; test with pdflatex before submitting
  • Never include fabricated citations — use only papers you have actually read
  • Check target venue formatting guidelines — ICML, NeurIPS, and ICLR each have distinct style files

Related Skills

View on GitHub
GitHub Stars843
CategoryAutomation
Updated2mo ago
Forks147

Languages

TypeScript

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions