Beamer Presentation logo

Beamer Presentation

CommunityPopular
brycewang-stanford
beamer-presentation

Create academic presentations in Beamer with professional themes

Overview

Publisherbrycewang-stanford
RepositoryAuto-Empirical-Research-Skills
Skill namebeamer-presentation
Stars
3.8K
Forks
479
Bundled files
1
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by brycewang-stanford on GitHub. Read the source before you install it.

Installation

Install the Beamer Presentation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills.git /tmp/Auto-Empirical-Research-Skills
mkdir -p .claude/skills
cp -r /tmp/Auto-Empirical-Research-Skills/skills/09-meleantonio-awesome-econ-ai-stuff/_skills/communication/beamer-presentation .claude/skills/beamer-presentation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Beamer Presentation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Beamer Presentation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Beamer Presentation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Beamer Presentation Creator

Purpose

This skill helps economists create professional academic presentations using LaTeX Beamer. It provides templates for conference talks, job market presentations, and seminar presentations with proper structure and clean aesthetics.

When to Use

  • Preparing conference presentations
  • Creating job market talk slides
  • Making seminar/workshop presentations
  • Converting a paper into presentation slides

Instructions

Step 1: Understand the Context

Ask the user:

  1. What type of presentation? (20-min conference, 90-min seminar, job market)
  2. What's the paper/project about?
  3. What's the target audience expertise level?
  4. Do they have specific style preferences?

Step 2: Structure by Time

DurationStructure
15-20 minMotivation (2) → Question (1) → Method (2) → Results (3-4) → Conclusion (1)
45-60 minAdd literature review, more results detail, robustness
90 minFull seminar with theoretical framework, extensive empirics

Step 3: Follow Presentation Best Practices

  • One idea per slide
  • Minimal text - use bullets of 3-6 words
  • Big fonts - minimum 20pt for content
  • Consistent colors - use a limited palette
  • Reveal incrementally using \pause or <+-> for complex slides

Example Output

latex
\documentclass[aspectratio=169, 11pt]{beamer}

% ============================================
% THEME AND APPEARANCE
% ============================================

% Clean minimal theme
\usetheme{metropolis}
\usecolortheme{default}

% Or for a more traditional look:
% \usetheme{Madrid}
% \usecolortheme{whale}

% Custom colors
\definecolor{darkblue}{RGB}{0, 51, 102}
\definecolor{lightgray}{RGB}{245, 245, 245}

\setbeamercolor{frametitle}{bg=darkblue, fg=white}
\setbeamercolor{title}{fg=darkblue}
\setbeamercolor{structure}{fg=darkblue}

% Remove navigation symbols
\setbeamertemplate{navigation symbols}{}

% Frame numbers
\setbeamertemplate{footline}[frame number]

% ============================================
% PACKAGES
% ============================================

\usepackage{graphicx}
\usepackage{booktabs}
\usepackage{tikz}
\usepackage{pgfplots}
\pgfplotsset{compat=1.17}

% ============================================
% TITLE PAGE
% ============================================

\title{The Effect of X on Y: \\Evidence from Z}
\subtitle{Short and Descriptive}
\author{Your Name}
\institute{Your University}
\date{Conference Name \\ Month Year}

\begin{document}

% Title slide
\begin{frame}[plain]
    \titlepage
\end{frame}

% ============================================
% MOTIVATION (2-3 slides)
% ============================================

\begin{frame}{Motivation: Why This Matters}
    \begin{itemize}
        \item<1-> \textbf{Big picture:} [One sentence on broad relevance]
        \item<2-> \textbf{Specific puzzle:} [What we don't know]
        \item<3-> \textbf{Stakes:} [Why should we care?]
    \end{itemize}
    
    \vspace{1em}
    
    \only<4>{
    \begin{block}{Key Statistic}
        \Large \textbf{X\%} of [outcome] can be explained by [factor]
    \end{block}
    }
\end{frame}

\begin{frame}{What We Know (and Don't Know)}
    \textbf{Previous literature:}
    \begin{itemize}
        \item Author et al. (2020): Finding 1
        \item Other Author (2019): Finding 2
    \end{itemize}
    
    \vspace{1em}
    
    \textbf{Gap we fill:}
    \begin{itemize}
        \item[\textcolor{red}{?}] [Open question our paper addresses]
    \end{itemize}
\end{frame}

% ============================================
% RESEARCH QUESTION (1 slide)
% ============================================

\begin{frame}{This Paper}
    \begin{center}
        \Large
        \textbf{Research Question:} \\[1em]
        Does [X] cause [Y]? \\[2em]
    \end{center}
    
    \textbf{Preview of findings:}
    \begin{itemize}
        \item Main result in plain language
        \item Key magnitude: [Quantitative summary]
    \end{itemize}
\end{frame}

% ============================================
% EMPIRICAL STRATEGY (2-3 slides)
% ============================================

\begin{frame}{Data}
    \textbf{Sources:}
    \begin{itemize}
        \item Dataset 1: [Description, years, N]
        \item Dataset 2: [Description, matching method]
    \end{itemize}
    
    \vspace{1em}
    
    \textbf{Sample:}
    \begin{itemize}
        \item Unit of observation: [What is an observation?]
        \item Final sample: [N] observations, [Time period]
    \end{itemize}
\end{frame}

\begin{frame}{Identification Strategy}
    \textbf{Challenge:} [Endogeneity concern in one sentence]
    
    \vspace{1em}
    
    \textbf{Solution:} We exploit [natural experiment / instrument / RDD]
    
    \vspace{1em}
    
    \textbf{Key assumption:} [Identification assumption in plain language]
    
    \begin{equation*}
        Y_{it} = \alpha + \beta \cdot \text{Treatment}_{it} + \gamma X_{it} + \mu_i + \delta_t + \varepsilon_{it}
    \end{equation*}
\end{frame}

% ============================================
% RESULTS (3-5 slides)
% ============================================

\begin{frame}{Main Result}
    \begin{center}
        \includegraphics[width=0.8\textwidth]{figures/main_result.pdf}
    \end{center}
    
    \vspace{0.5em}
    
    \textbf{Takeaway:} [One sentence interpretation]
\end{frame}

\begin{frame}{Main Result: Regression Table}
    \begin{table}
        \centering
        \small
        \begin{tabular}{lccc}
            \toprule
            & (1) & (2) & (3) \\
            & OLS & + Controls & + FE \\
            \midrule
            Treatment & 0.052*** & 0.048*** & 0.041** \\
                      & (0.012)  & (0.011)  & (0.015) \\
            \midrule
            Controls & No & Yes & Yes \\
            Fixed Effects & No & No & Yes \\
            N & 10,000 & 9,850 & 9,850 \\
            \bottomrule
        \end{tabular}
    \end{table}
    
    \textbf{Economic magnitude:} 1 SD increase in X $\rightarrow$ Y\% increase in outcome
\end{frame}

\begin{frame}{Robustness Checks}
    \begin{itemize}
        \item[\checkmark] Alternative specifications
        \item[\checkmark] Placebo tests
        \item[\checkmark] Different sample cuts
        \item[\checkmark] [Other relevant checks]
    \end{itemize}
    
    \vspace{1em}
    
    $\rightarrow$ Results robust across specifications
\end{frame}

% ============================================
% CONCLUSION (1 slide)
% ============================================

\begin{frame}{Takeaways}
    \begin{enumerate}
        \item \textbf{Finding 1:} [Main result]
        \item \textbf{Finding 2:} [Secondary result]
        \item \textbf{Implication:} [Policy/theory takeaway]
    \end{enumerate}
    
    \vspace{2em}
    
    \begin{center}
        \Large Thank you! \\[0.5em]
        \normalsize your.email@university.edu
    \end{center}
\end{frame}

% ============================================
% APPENDIX
% ============================================

\appendix

\begin{frame}[noframenumbering]{Appendix: Additional Results}
    [Backup slides for Q\&A]
\end{frame}

\end{document}

Theme Recommendations

AudienceThemeNotes
AcademicmetropolisClean, modern, minimal
ConferenceMadridTraditional, professional
Job marketdefault with custom colorsSafe, customizable
PolicyCambridgeUSAuthoritative look

Best Practices

  1. One message per slide - if you need more, split it
  2. Use figures over tables when possible
  3. Highlight key numbers in results tables
  4. Build complex slides incrementally with \pause
  5. Prepare backup slides for anticipated questions
  6. Practice timing - 1-2 minutes per slide max

Common Pitfalls

  • ❌ Too much text on slides
  • ❌ Reading slides word-for-word
  • ❌ Tables with too many columns
  • ❌ Skipping the roadmap/preview
  • ❌ Ending with "Questions?" instead of takeaways

References

Changelog

v1.0.0

  • Initial release with conference talk template

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Beamer Presentation AI skill do?

Create academic presentations in Beamer with professional themes

Why use Beamer Presentation on TypingMind?

Because you install it once and use it with any model. Beamer Presentation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Beamer Presentation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/main/skills/09-meleantonio-awesome-econ-ai-stuff/_skills/communication/beamer-presentation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Beamer Presentation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Beamer Presentation?

As many as you like. As long as a model supports skills, you can use Beamer Presentation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Beamer Presentation AI skill free?

It is published on GitHub by brycewang-stanford. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇