mcpbeat Sign in

Beamer Check Skill for Claude

by aspi6246

> Audit and fix Beamer slide decks for compilation errors, layout problems, and visual issues. Use this skill whenever the user says "check my slides", "fix my slides", "the slides don't compile", "text is running off the page", "slides look wrong", or after generating a Beamer deck to verify it before delivering. Also use when the user mentions overfull boxes, overlapping content, broken images, or any Beamer formatting issue.

4k tokens
context cost
the whole folder, loaded on every use
2
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
146
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/aspi6246/Claude-Code-Skills-for-Academics --skill beamer-check

The instruction itself

13 sections, as written by the author

Beamer Slide Deck Audit and Fix

Overview

This skill implements a compile → inspect → fix → verify loop for Beamer

slide decks. The goal is to catch and fix all issues before the user has to

open the PDF themselves.

Run the full audit protocol below. Do not skip the visual inspection phase —

compilation warnings alone do not catch all layout problems.

Phase 1: Automated Compilation Check

Run the diagnostic script:

python {baseDir}/scripts/beamer_check.py <path-to-tex-file> --output-dir <work-dir>/beamer-check-output

This will:

  • Compile the .tex file twice with pdfLaTeX
  • Parse the log for errors, warnings, overfull/underfull boxes, and missing files
  • Render every slide to a PNG image for visual inspection
  • Write a diagnostics.json summary

Read the script output and the diagnostics.json file. Categorise every

issue found:

  • Compilation errors — the PDF was not produced or is incomplete
  • Missing files — images, packages, or fonts that could not be found
  • Overfull hbox — content wider than the text area (text running off the right edge)
  • Overfull vbox — content taller than the slide area (text running off the bottom)
  • Warnings — package conflicts, deprecated commands, missing references

Phase 2: Visual Inspection

This is the most important phase. Many layout problems produce no warnings

at all.

Open and examine EVERY rendered slide image in

beamer-check-output/slides/. For each slide, check for:

Text issues

  • Text running off the right edge of the slide
  • Text running off the bottom of the slide
  • Text overlapping with other elements (headers, footers, images)
  • Font size too small to read (below \footnotesize on a 16:9 slide)
  • Orphaned words or lines that look awkward
  • Verbatim/code blocks that exceed the text width

Layout issues

  • Itemize/enumerate lists that overflow the frame
  • Tables wider than the slide
  • Columns that are misaligned or overlapping
  • Excessive white space on one side, crowded on the other
  • Content obscured by the Beamer theme elements (navigation bar, footer)

Image issues

  • Missing images (blank spaces or error markers)
  • Images that are distorted (wrong aspect ratio)
  • Images that are too small to be useful
  • Images that overflow the frame boundary

Structure issues

  • Empty slides (no content rendered)
  • Duplicate slide titles
  • Table of contents that doesn't match actual section structure
  • Frame titles that are cut off

Phase 3: Fix

For every issue identified in Phases 1 and 2, apply the appropriate fix.

Ask the user before editing their file.

Common fixes reference

Text running off the right edge (overfull hbox):

% Option 1: Allow slightly loose spacing
\begin{frame}[fragile]{Title}
\sloppy
Content here...
\end{frame}

% Option 2: Reduce font size for that frame
\begin{frame}{Title}
\small  % or \footnotesize for more reduction
Content here...
\end{frame}

% Option 3: Break long lines manually
Very long text that needs to be broken\\
across multiple lines.

% Option 4: For URLs
\url{https://very-long-url.com/that/overflows}
% Replace with:
{\small\url{https://very-long-url.com/that/overflows}}

Content overflowing the bottom (overfull vbox):

% Option 1: Reduce font size
\begin{frame}{Title}
\small
Too much content...
\end{frame}

% Option 2: Use allowframebreaks to auto-split
\begin{frame}[allowframebreaks]{Title}
Lots of content that will auto-split across slides...
\end{frame}

% Option 3: Shrink the whole frame (use sparingly)
\begin{frame}[shrink=10]{Title}
Content...
\end{frame}

% Option 4 (best): Split into two slides manually
% This is usually the right answer for teaching slides

Verbatim/code blocks overflowing:

% Use fragile option on the frame
\begin{frame}[fragile]{Title}
\begin{verbatim}
code here
\end{verbatim}
\end{frame}

% For long code, reduce font size
\begin{frame}[fragile]{Title}
\begin{verbatim}
\small
code here
\end{verbatim}
\end{frame}

Tables too wide:

% Option 1: Use \resizebox
\resizebox{\textwidth}{!}{%
\begin{tabular}{lccccc}
...
\end{tabular}
}

% Option 2: Use \small or \footnotesize
{\footnotesize
\begin{tabular}{lccccc}
...
\end{tabular}
}

% Option 3: Use tabularx for automatic column width
\usepackage{tabularx}
\begin{tabularx}{\textwidth}{lXXX}
...
\end{tabularx}

Missing images:

% Add a fallback so compilation doesn't fail
\IfFileExists{image.png}{%
  \includegraphics[width=0.8\textwidth]{image.png}
}{%
  \textit{[Image not found: image.png]}
}

Column alignment issues:

% Make sure column widths sum to \textwidth
\begin{columns}[T]  % T = top-aligned
\begin{column}{0.48\textwidth}
Left content
\end{column}
\begin{column}{0.48\textwidth}
Right content
\end{column}
\end{columns}
% Leave ~0.04\textwidth for the gap between columns

Phase 4: Verify

After applying fixes:

  • Run the diagnostic script again on the modified file:
   python {baseDir}/scripts/beamer_check.py <path-to-tex-file> --output-dir <work-dir>/beamer-check-verify
  • Confirm that:
  • All previous compilation errors are resolved
  • No new errors or warnings were introduced
  • Overfull box count has decreased (ideally to zero)
  • Visually inspect the re-rendered slides again, focusing on the

slides that were modified. Confirm the fixes worked and didn't

introduce new layout problems.

  • If new issues are found, repeat Phases 3-4 until clean.

Phase 5: Report

Present a summary to the user:

Beamer Audit Complete
=====================
Slides checked: [N]
Issues found: [N]
Issues fixed: [N]
Remaining issues: [N] (with explanation if any)

Changes made:
- Slide 3: Reduced font size to \small (text overflow)
- Slide 7: Split into two slides (content exceeded frame)
- Slide 12: Added [fragile] option (verbatim block)
- ...

Important notes

  • Always ask the user before editing their .tex file
  • Prefer splitting content across slides over shrinking text —

readability matters more than slide count

  • The [shrink] option is a last resort — it makes everything

smaller, which is usually worse than splitting

  • [allowframebreaks] is acceptable for reference/bibliography slides

but looks bad for regular content — prefer manual splits

  • When in doubt, err on the side of more slides with less content

Other skills for the same job

different authors, same section of the catalogue
Legacy Circuit Mockups
by github
vendor ×1

Generate breadboard circuit mockups and visual diagrams using HTML5 Canvas drawing techniques. Use when asked to create circuit layouts, visualize electronic component placements, draw breadboard diagrams, mockup 6502 builds, generate retro computer schematics, or design vintage electronics projects. Supports 555 timers, W65C02S microprocessors, 28C256 EEPROMs, W65C22 VIA chips, 7400-series logic gates, LEDs, resistors, capacitors, switches, buttons, crystals, and wires.

37k tokens
Hyperframes Keyframes
by aiskillstore
×1

> Use when a HyperFrames composition needs seek-safe 2D/3D keyframes, GSAP timelines, CSS keyframes, Anime.js, WAAPI, FLIP, paths, masks, SVG morph/draw, text trails, 3D depth, or `hyperframes keyframes` diagnostics. Don't use for broad scene strategy, brand design, media sourcing, captions, or general video planning.

17k tokens
Anydesign
by uxKero
×1

Analyze images, websites, and Figma files to extract their design and generate a `design.md` with token system, component inventory, and reconstruction notes. Use this skill whenever the user wants to understand, document, replicate, or audit the design of something visual: a screenshot, a URL, a Figma link, a Pinterest reference, a mockup, a competitor's site, a component, a dashboard, a landing page. Also when they ask 'extract the design system from X', 'document the style of Y', 'analyze this visually', 'convert this image into tokens', 'help me replicate this design', 'what palette does this site use', 'how is this built'. Also for single elements: 'copy this navbar', 'recreate this illustration', 'give me a prompt to regenerate this graphic' — element mode outputs a focused element.md, with token-grounded image-model prompts when the element is visual art. If the user brings any visual source and wants to understand it at a design level — this skill should activate.

728k tokens scripts
Brandkit
by lornshrimp
×1

Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

4k tokens
Imagegen Frontend Mobile
by lornshrimp
×1

Elite mobile app image-generation skill for creating premium, app-native screen concepts and flows. Designed for iOS, Android, and cross-platform mobile products. Prioritizes clean hierarchy, comfortably readable text, strong multi-screen consistency, controlled color palettes, non-generic creative direction, textured surfaces, image-led composition, tasteful custom iconography, and clean phone mockup framing. By default, screens should be shown inside a subtle premium iPhone or similar phone mockup with a visible frame, while the main focus stays on the app content itself. This skill generates images only. It does not write code.

10k tokens
Perf Web Optimization
by christophacham
×1

Optimize web performance: bundle size, images, caching, lazy loading, and overall page speed. Use when site is slow, reducing bundle size, fixing layout shifts, improving Time to Interactive, or optimizing for Lighthouse scores. Triggers on: web performance, bundle size, page speed, slow site, lazy loading. Do NOT use for Core Web Vitals-specific fixes (use core-web-vitals), running Lighthouse audits (use perf-lighthouse), or Astro-specific optimization (use perf-astro).

4k tokens
Brandkit
by nexu-io

| Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional logo concepting, refined composition, sparse typography, strong symbolic meaning, premium mockups, art-directed imagery, and flexible grid layouts.

4k tokens
Gsap Performance
by nexu-io

| Official GSAP skill for performance — prefer transforms, avoid layout thrashing, will-change, batching. Use when optimizing GSAP animations, reducing jank, or when the user asks about animation performance, FPS, or smooth 60fps.

1k tokens

How to use it

Copy the folder

Take aspi6246/beamer-check from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.