agentleFS
DaRL-GenAIDaRL-GenAI/instructional_agents-skills/skills/latex-to-pptx/SKILL.md

latex-to-pptx

Skill1 starsChanged 7 months agoMITView on GitHub

Convert a Beamer LaTeX (.tex) file into a fully-editable PowerPoint (.pptx) deck. Use this when the user has a .tex slide source and wants an editable .pptx — for example "convert this LaTeX to PPT", "export my beamer slides as PowerPoint", or when they mention editing slides in PowerPoint/Keynote.

  • Installs packages

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not invoke this for:

    line 17
  2. Distinctive:

    If either is missing, tell the user and offer to install.

    line 34
  3. Very specific:

    Run the wrapper script with the input .tex path.

    line 38
  4. Distinctive:

    If used in published work, please cite the paper — see the plugin README.

    line 83

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

LaTeX → PPTX Conversion

Converts a Beamer .tex file into a native, editable PowerPoint deck using the instructional_agents parser plus pptxgenjs.

When to invoke this skill

  • User has a .tex file (Beamer or Beamer-compatible) and wants a .pptx
  • User asks to "export LaTeX slides to PowerPoint / Keynote"
  • User wants to edit generated slides in PowerPoint (vs. getting a static PDF)

Do not invoke this for:

  • Generating new slides from scratch → use course-generate
  • Compiling LaTeX to PDF → use latex-compile

Prerequisites

Before running, verify:

  1. Python 3.11+ with instructional-agents installed:
    pip show instructional-agents || pip install instructional-agents
  2. Node.js with pptxgenjs:
    node -e "require('pptxgenjs')" 2>/dev/null || npm install -g pptxgenjs

If either is missing, tell the user and offer to install.

Usage

Run the wrapper script with the input .tex path. The .pptx is written next to the source unless --output is given.

python3 "${CLAUDE_PLUGIN_ROOT}/skills/latex-to-pptx/scripts/convert.py" \
  <input.tex> [--output <output.pptx>]

Arguments

ArgRequiredDescription
<input.tex>yesPath to the Beamer .tex file
--output <path>noOutput .pptx path (default: same dir, same stem)

Example

python3 "${CLAUDE_PLUGIN_ROOT}/skills/latex-to-pptx/scripts/convert.py" \
  ~/courses/ml/chapter1.tex
# → ~/courses/ml/chapter1.pptx

Supported LaTeX constructs

itemize, enumerate, block, alertblock, code listings (lstlisting), inline & display math, columns, tikz (rendered as placeholder boxes).

Output

An editable .pptx — every text object, bullet list, and code block is a native PowerPoint shape, not an embedded image. Safe to edit in PowerPoint, Keynote, or Google Slides.

Troubleshooting

  • "pptxgenjs not found" → npm install -g pptxgenjs
  • Math doesn't render → pptxgenjs doesn't support native LaTeX math; the skill emits math as plain text. For math-heavy decks, keep the PDF.
  • \include / \input → flatten first with latexpand input.tex > flat.tex then run the skill on flat.tex.

Citation

This skill wraps code from Instructional Agents (arXiv:2508.19611). If used in published work, please cite the paper — see the plugin README.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.