Presentation Making logo

Presentation Making

Community
msimchowitz
presentation-making

Plan, create, revise, and review presentation decks with a clear narrative, accurate content, coherent visual system, editable source, and rendered-slide verification. Use for PowerPoint, Keynote, Google Slides, Beamer, lecture decks, talks, pitches, speaker notes, slide outlines, or slide-level visual and writing review.

Overview

Publishermsimchowitz
Repositorywriting-skills
Skill namepresentation-making
Stars
67
Forks
4
Bundled files
3
LicenseMIT
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.

  • 3 bundled files

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

  • Open source

    Published by msimchowitz on GitHub. Read the source before you install it.

Installation

Install the Presentation Making 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.
    https://github.com/msimchowitz/writing-skills/tree/main/for-agents/presentation-making
  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/msimchowitz/writing-skills.git /tmp/writing-skills
mkdir -p .claude/skills
cp -r /tmp/writing-skills/for-agents/presentation-making .claude/skills/presentation-making
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Presentation Making 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 Presentation Making 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 Presentation Making 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.

Presentation Making

Turn source material into a presentation built for an audience and a live explanation. Preserve technical accuracy while making the argument easier to follow than the source alone.

Load detailed guidance selectively

  • Read deck-workflow.md before creating a new deck or substantially restructuring an existing deck.
  • Read visual-design-review.md when selecting a visual system, designing layouts, or reviewing rendered slides.
  • For a narrow text edit to a few existing slides, use the core rules below without loading both references.

Core rules

  • Establish the audience, purpose, venue, allotted time, source material, and required output format before building.
  • Read the full source relevant to the talk. Do not invent claims, examples, results, equations, references, or quotations.
  • Plan the narrative and the job of each slide before editing the deck.
  • Give each slide one primary point or teaching move.
  • Use an existing approved deck or template as the visual source when one is available. Preserve its typography, margins, colors, and page furniture.
  • Keep one visual system. Do not mix themes or recreate a supplied style from memory.
  • Prefer diagrams, equations, figures, plots, and concrete evidence over dense prose. Do not add decorative images.
  • Keep visible text short enough to read at presentation distance. Put details needed for delivery, but not simultaneous reading, in speaker notes.
  • Preserve notation exactly. Render mathematics with true superscripts, subscripts, primes, limits, and conditioning notation.
  • Use progressive builds only when each step helps the spoken explanation.
  • Keep the source editable. Retain PowerPoint objects or compilable Beamer source rather than flattening the deck into images.
  • Render and inspect every slide before delivery. Fix clipping, overflow, accidental overlap, tiny text, inconsistent spacing, distorted images, placeholder residue, and unreadable citations.

Workflow

  1. Resolve the source and constraints.
  2. Write a slide plan with the point, evidence, layout, and build behavior for every slide.
  3. Select a visual source and map planned slides to suitable layout families.
  4. Build the editable deck with the appropriate presentation tools.
  5. Render the complete deck and inspect every physical slide or overlay.
  6. Correct defects, rerender, and repeat until the review passes.
  7. Report the final deck path and any unresolved content questions.

When the user provides feedback, preserve the exact concern and convert repeated feedback into a short reusable rule for later decks.

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 Presentation Making AI skill do?

Plan, create, revise, and review presentation decks with a clear narrative, accurate content, coherent visual system, editable source, and rendered-slide verification. Use for PowerPoint, Keynote, Google Slides, Beamer, lecture decks, talks, pitches, speaker notes, slide outlines, or slide-level visual and writing review.

Why use Presentation Making on TypingMind?

Because you install it once and use it with any model. Presentation Making 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 Presentation Making in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/msimchowitz/writing-skills/tree/main/for-agents/presentation-making. 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 Presentation Making?

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 Presentation Making?

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

Is the Presentation Making AI skill free?

Yes. It is published on GitHub by msimchowitz under the MIT license. 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 👇