brycewang-stanford
brycewang-stanford/Auto-Empirical-Research-Skills
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills --skill academic-paper-writer命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Route empirical-research requests through the Auto-Empirical Research Skills catalog when this whole repository is installed as one skill in Codex, CodeBuddy, Claude Code, or another IDE. Use to choose and load the right vendored AERS skill for causal inference, econometrics, replication, data acquisition, manuscript writing, peer review and referee responses, citation checking, de-AIGC editing, or full empirical-paper workflows without reading the entire repository at once.
中英双语学术降 AIGC / bilingual academic de-AIGC skill. Removes AI-generated writing signatures from empirical papers in economics, management, and the social sciences — in both English and Chinese. Covers Turnitin AI, GPTZero, Originality.ai on the English side and 知网 AMLC, 万方, 维普 on the Chinese side. Uses a six-step loop (intake → audit → claim-evidence check → differentiated rewrite → five-dimension self-score → cold-reader recheck) with two pattern libraries (22 English + 17 Chinese patterns), section-by-section strategies for empirical papers, and hard protections that keep every number, coefficient, and citation intact.
Use when a research task needs reproducible Kaggle discovery, metadata inspection, bounded public-data downloads, competition or kernel discovery, model discovery, or an explicitly approved Kaggle write/delete operation through the official CLI.
基于 SOC 职业分类
| name | academic-paper-writer |
| description | Draft economics papers with proper structure and academic style |
| workflow_stage | writing |
| compatibility | ["claude-code","cursor","codex","gemini-cli"] |
| author | Awesome Econ AI Community |
| version | 1.0.0 |
| tags | ["LaTeX","academic-writing","papers","economics"] |
This skill helps economists draft, structure, and polish academic papers with proper conventions for economics journals. It provides templates for different paper types and guidance on academic writing style.
Ask the user:
For empirical papers, use:
\section{Introduction}
% Hook - Why does this matter?
[TOPIC] is a fundamental question in economics, with implications for
[POLICY AREA] and [BROADER RELEVANCE]. Despite extensive research,
we still lack clear evidence on [SPECIFIC GAP].
% Research question
This paper asks: [RESEARCH QUESTION IN PLAIN LANGUAGE]?
Specifically, we examine whether [PRECISE FORMULATION OF THE QUESTION].
% Preview of answer
We find that [MAIN RESULT IN ONE SENTENCE]. This effect is
[economically significant / modest / heterogeneous], with
[QUANTITATIVE SUMMARY: e.g., "a one standard deviation increase
in X associated with a Y percent increase in Z"].
% Methodology (brief)
To identify this effect, we exploit [IDENTIFICATION STRATEGY:
natural experiment / RCT / instrumental variable / RDD].
Our data come from [DATA SOURCE], covering [TIME PERIOD]
and [SAMPLE SIZE] observations.
% Contribution / Related literature
Our paper contributes to several strands of literature.
First, we extend the work of \citet{Author2020} by [EXTENSION].
Second, we provide new evidence on [MECHANISM/CHANNEL] that
complements \citet{OtherAuthor2019}. Finally, our findings
have implications for [POLICY/FUTURE RESEARCH].
% Roadmap
The remainder of the paper is organized as follows.
Section~\ref{sec:background} provides background and reviews
related literature. Section~\ref{sec:data} describes our data
and empirical strategy. Section~\ref{sec:results} presents our
main findings. Section~\ref{sec:robustness} discusses robustness
checks. Section~\ref{sec:conclusion} concludes.
\section{Results}
\label{sec:results}
% Lead with the main finding
Table~\ref{tab:main} presents our main results. Column (1) shows
the baseline OLS specification without controls. The coefficient
on [TREATMENT VARIABLE] is [POINT ESTIMATE] (s.e. = [SE]),
statistically significant at the [1/5/10] percent level.
% Add controls incrementally
In column (2), we add [CONTROL SET 1]. The point estimate
[increases/decreases slightly/remains stable] to [ESTIMATE].
Column (3) includes [CONTROL SET 2] and adds [FIXED EFFECTS].
Our preferred specification in column (4) includes [FULL CONTROLS]
and yields [FINAL ESTIMATE].
% Interpret magnitude
To gauge economic significance, note that [INTERPRETATION].
A one standard deviation increase in [X] is associated with
a [Y] percent [increase/decrease] in [OUTCOME], or roughly
[COMPARISON TO MEAN/OTHER BENCHMARK].
% Brief mention of mechanisms/heterogeneity if relevant
Table~\ref{tab:hetero} explores heterogeneity by [DIMENSION].
We find that the effect is [larger/concentrated among]
[SUBGROUP], suggesting that [INTERPRETATION].
\begin{table}[htbp]
\centering
\caption{Main Results: Effect of X on Y}
\label{tab:main}
\begin{tabular}{lcccc}
\hline\hline
& (1) & (2) & (3) & (4) \\
& OLS & + Controls & + FE & Preferred \\
\hline
Treatment & 0.052*** & 0.048*** & 0.041** & 0.039** \\
& (0.012) & (0.011) & (0.015) & (0.016) \\
\\
Controls & No & Yes & Yes & Yes \\
Fixed Effects & No & No & Yes & Yes \\
Cluster SE & No & No & No & Yes \\
\\
Observations & 10,000 & 9,850 & 9,850 & 9,850 \\
R-squared & 0.05 & 0.12 & 0.35 & 0.35 \\
\hline\hline
\multicolumn{5}{l}{\footnotesize Notes: * p<0.10, ** p<0.05, *** p<0.01.} \\
\multicolumn{5}{l}{\footnotesize Standard errors in parentheses.} \\
\end{tabular}
\end{table}
\section{Conclusion}
\label{sec:conclusion}
% Restate question and answer
This paper examined [RESEARCH QUESTION]. Using [METHOD/DATA],
we found that [MAIN FINDING]. This result is robust to
[ROBUSTNESS CHECKS].
% Implications
Our findings have several implications. For policy, they suggest
that [POLICY IMPLICATION]. For theory, they provide support for
[THEORETICAL MECHANISM] and challenge [ALTERNATIVE VIEW].
% Limitations (brief, honest)
Several limitations warrant mention. First, [LIMITATION 1:
e.g., external validity]. Second, [LIMITATION 2: e.g.,
data constraints]. Future research could address these by
[SUGGESTION].
% Future directions
This paper opens several avenues for future work.
[DIRECTION 1]. [DIRECTION 2]. We hope our findings
stimulate further research on [BROADER TOPIC].