all-plan
Use when a task is ambiguous and needs deep multi-role planning with designer, inspiration, and reviewer perspectives before…
Use only when the user explicitly asks for help drafting or revising an AI/ML research paper in LaTeX, including structure, BibTeX, formatting, or academic-writing checks.
$ npx -y skills add cnfjlhj/ai-collab-playbook --skill academic-paper-helper --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/academic-paper-helperContext preview
The summary Claude sees to decide when to auto-load this skill.
Use only when the user explicitly asks for help drafting or revising an AI/ML research paper in LaTeX, including structure, BibTeX, formatting, or academic-writing checks.
name: academic-paper-helper description: Use only when the user explicitly asks for help drafting or revising an AI/ML research paper in LaTeX, including structure, BibTeX, formatting, or academic-writing checks.
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@university.edu}
}
\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...Practical AI collaboration playbook for research, writing, reading, and coding: article, prompts, agent rules, and reusable skills.
Use when a task is ambiguous and needs deep multi-role planning with designer, inspiration, and reviewer perspectives before…
Use when you want Claude Code CLI as a second opinion for coding tasks such as design tradeoffs, debugging, or diff review, while…
Use when you explicitly want a second local or SSH remote Codex CLI session to prototype, debug, or review code, while your…
Use when you want Gemini CLI as a second opinion for coding tasks such as prototyping, debugging, or diff review, while keeping…
Use when the user asks whether a skill exists, wants help finding or installing one, or asks how to extend agent capabilities…
Use when a mostly complete ML conference paper needs self-review, pre-submission QA, camera-ready checking, section-by-section…