skills/full/academic-paper-helper/SKILL.md
学术论文写作助手,专门用于 LaTeX 论文编写、BibTeX 管理、格式化、学术写作规范检查。适用于 AI/ML 研究论文、会议投稿(NeurIPS、ICML、ICLR 等)
npx skillsauth add cnfjlhj/ai-collab-playbook academic-paper-helperInstall 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.
专为 AI/ML 博士生设计的学术写作助手,提供端到端的论文写作支持。
使用场景:创建新论文时
模板类型:
生成内容:
\documentclass{article}
% 会议特定包
\usepackage[final]{neurips_2024} % 或其他会议
% 标准学术包
\usepackage{amsmath,amssymb,amsfonts}
\usepackage{algorithm,algorithmic}
\usepackage{graphicx}
\usepackage{booktabs}
\usepackage{hyperref}
\title{Your Paper Title}
\author{
Your Name \\
Department \\
University \\
\texttt{[email protected]}
}
\begin{document}
\maketitle
\begin{abstract}
Your abstract here.
\end{abstract}
\section{Introduction}
% Your content
\section{Related Work}
% Your content
\section{Method}
% Your content
\section{Experiments}
% Your content
\section{Conclusion}
% Your content
\bibliographystyle{plain}
\bibliography{references}
\end{document}
使用场景:管理论文引用
功能:
示例:
输入混乱的论文信息:
attention is all you need
vaswani et al
2017
neurips
输出规范的 BibTeX:
@inproceedings{vaswani2017attention,
title={Attention Is All You Need},
author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N. and Kaiser, {\L}ukasz and Polosukhin, Illia},
booktitle={Advances in Neural Information Processing Systems},
volume={30},
year={2017},
doi={10.5555/3295222.3295349}
}
检查项目:
常见错误及解决:
% 错误 1:Undefined control sequence
% 原因:包未导入或命令拼写错误
% 解决:检查 \usepackage{} 和命令名
% 错误 2:Missing $ inserted
% 原因:数学符号在文本模式中使用
% 解决:使用 $...$ 或 \( ... \) 包围数学内容
% 错误 3:File not found
% 原因:图片或 .bib 文件路径错误
% 解决:检查文件路径,使用相对路径
% 错误 4:Citation undefined
% 原因:.bib 文件未编译或引用键错误
% 解决:运行 bibtex,检查引用键
\section{Introduction}
% 段落 1:研究背景和动机
Recent advances in [field] have led to...
However, existing approaches suffer from...
% 段落 2:具体问题
Consider the problem of [specific problem]...
Current methods [limitation 1], [limitation 2]...
% 段落 3:本文方法概述
To address these challenges, we propose [method name]...
Our approach [key innovation 1], [key innovation 2]...
% 段落 4:主要贡献
The main contributions of this work are:
\begin{itemize}
\item We propose [contribution 1]...
\item We demonstrate [contribution 2]...
\item We achieve [contribution 3]...
\end{itemize}
\section{Method}
\subsection{Problem Formulation}
Let $\mathcal{X}$ denote... We aim to learn...
\subsection{Architecture}
Our model consists of... Figure~\ref{fig:architecture} illustrates...
\subsection{Training Procedure}
We optimize the following objective:
\begin{equation}
\mathcal{L} = \mathbb{E}_{(x,y)\sim\mathcal{D}}[\ell(f_\theta(x), y)]
\end{equation}
\subsection{Implementation Details}
We implement our method in PyTorch...
\section{Experiments}
\subsection{Experimental Setup}
\textbf{Datasets:} We evaluate on...
\textbf{Baselines:} We compare against...
\textbf{Metrics:} We report...
\textbf{Implementation:} We use...
\subsection{Main Results}
Table~\ref{tab:main_results} shows...
\subsection{Ablation Study}
To understand the contribution of each component...
\subsection{Analysis}
Figure~\ref{fig:analysis} visualizes...
\begin{algorithm}
\caption{Your Algorithm}
\label{alg:youralgorithm}
\begin{algorithmic}[1]
\REQUIRE Input $x$
\ENSURE Output $y$
\STATE Initialize $\theta$
\FOR{$t = 1$ to $T$}
\STATE Compute $\nabla_\theta \mathcal{L}$
\STATE Update $\theta \leftarrow \theta - \alpha \nabla_\theta \mathcal{L}$
\ENDFOR
\RETURN $\theta$
\end{algorithmic}
\end{algorithm}
\begin{table}[t]
\centering
\caption{Comparison with baselines}
\label{tab:results}
\begin{tabular}{lcc}
\toprule
Method & Accuracy & F1-Score \\
\midrule
Baseline 1 & 85.3 & 82.1 \\
Baseline 2 & 87.6 & 84.5 \\
\textbf{Ours} & \textbf{91.2} & \textbf{89.3} \\
\bottomrule
\end{tabular}
\end{table}
\begin{figure}[t]
\centering
\includegraphics[width=0.8\linewidth]{figures/architecture.pdf}
\caption{Overall architecture of our model.}
\label{fig:architecture}
\end{figure}
% 行内公式
The loss function $\mathcal{L}(\theta)$ is defined as...
% 单行公式
\begin{equation}
\mathcal{L}(\theta) = \sum_{i=1}^{n} \ell(f_\theta(x_i), y_i)
\end{equation}
% 多行公式
\begin{align}
\mathcal{L}(\theta) &= \mathbb{E}_{x\sim p_{\text{data}}}[\log p_\theta(x)] \\
&= \sum_{i=1}^{n} \log p_\theta(x_i)
\end{align}
正确引用方式:
% 作为名词
\citet{vaswani2017attention} proposed the Transformer architecture.
% 输出:Vaswani et al. (2017) proposed...
% 括号中
The Transformer architecture~\citep{vaswani2017attention} has...
% 输出:... architecture (Vaswani et al., 2017) has...
% 多个引用
Recent work~\citep{vaswani2017attention,devlin2018bert} has shown...
% 输出:... work (Vaswani et al., 2017; Devlin et al., 2018) has...
版本: v1.0 创建日期: 2025-10-21 适用对象: AI/ML 博士生、研究人员 核心价值: 提高学术写作效率,确保论文质量和规范性
tools
小红书笔记素材创作技能。当用户需要创建小红书笔记素材时使用这个技能。技能包含:根据用户的需求和提供的资料,撰写小红书笔记内容(标题+正文),生成图片卡片(封面+正文卡片),以及发布小红书笔记。
tools
This skill should be used when the user wants to publish an existing Markdown article to Xiaohongshu as a private longform post, keep the original wording and structure, insert inline images in order, use one-click layout, and verify the result in note manager.
testing
This skill should be used when the user asks to "remove AI writing patterns", "humanize this text", "make this sound more natural", "remove AI-generated traces", "fix robotic writing", or needs to eliminate AI writing patterns from prose. Supports both English and Chinese text. Based on Wikipedia's "Signs of AI writing" guide, detects and fixes inflated symbolism, promotional language, superficial -ing analyses, vague attributions, AI vocabulary, negative parallelisms, and excessive conjunctive phrases.
development
Generate a detailed, professional video content summary from timestamped subtitles/transcripts (e.g., lines starting with 00:00 / 1:23:45). Enforce strict per-segment structure (timestamp range + bold segment title + 2-paragraph body: first-person creator summary + expert 【导师评注】 critique with uncertainty handling). Use when the user provides time-coded subtitles and asks for a规范化纪要/内容纪要/逐段总结, and optionally wants a clean PDF export (do NOT include the full raw transcript in the PDF unless explicitly requested).