Html Presentation logo

Html Presentation

Community
Mathews-Tom
html-presentation

Converts documents, outlines, or notes into self-contained HTML slide decks with horizontal (Reveal.js) or vertical scroll navigation and multiple themes. Triggers on: "create a presentation", "slide deck", "pitch deck", "HTML presentation", "web-based slides", "reveal.js deck", "convert document into slides".

Overview

PublisherMathews-Tom
Repositoryarmory
Skill namehtml-presentation
Stars
318
Forks
47
Bundled files
4
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.

  • 4 bundled files

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

  • Open source

    Published by Mathews-Tom on GitHub. Read the source before you install it.

Installation

Install the Html 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/Mathews-Tom/armory.git /tmp/armory
mkdir -p .claude/skills
cp -r /tmp/armory/skills/html-presentation .claude/skills/html-presentation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Html 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 Html 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 Html 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.

HTML Presentation Skill

Convert documents, outlines, or freeform content into polished, self-contained HTML slide presentations with keyboard and scroll navigation.

When This Skill Triggers

  • User provides a document and asks for a "presentation", "slides", or "deck" as HTML
  • User asks to convert notes/outline/content into browser-presentable slides
  • User wants a Reveal.js or scroll-based HTML presentation
  • User references wanting to present from a browser rather than PowerPoint

Step 0: Gather Requirements

Before generating anything, check whether the user has specified the following. If any are missing, ask for clarification in a single concise message. Do NOT ask more than once — use sensible defaults for anything the user declines to specify.

Required context (ask if missing):

ParameterWhat to askDefault if not specified
Navigation mode"Should slides go left-to-right (horizontal) or top-to-bottom (vertical scroll)?"horizontal
Theme"Which visual style? Options: dark-editorial (dark bg, serif headlines, editorial feel), light-minimal (clean white, sans-serif), corporate (navy/white, professional), hacker (terminal green-on-black, monospace)"dark-editorial
Audience & tone"Who is this for? (e.g., investors, engineers, conference talk, internal team)"Infer from content
Slide count preference"Roughly how many slides?"Auto-determine from content density
Branding"Any logo text, tagline, or accent color to use in the header?"None
CTA / closing"Any call-to-action, links, or contact info for the final slide?"None

If the user provides a document and says something like "make this a presentation", ask all missing parameters in one shot. If they say "just make it look good", use defaults and proceed.

Step 1: Analyze the Source Document

Read the uploaded document or provided content. Identify:

  1. Logical sections — these become slides or slide groups
  2. Key data points — numbers, metrics, percentages → use metric/stat slide layouts
  3. Lists and comparisons — feature lists, pros/cons → use card grids or comparison tables
  4. Quotes or testimonials — use quote-block layouts
  5. Sequential processes — workflows, timelines → use workflow/timeline slide layouts
  6. Title and conclusion — first and last slides get special treatment

Create a mental outline mapping content sections to slide types before writing any HTML.

Step 2: Select Slide Layouts

Each slide should use one of these layout patterns. Mix them for visual variety — never use the same layout for more than 2 consecutive slides.

LayoutWhen to UseCSS Class
TitleOpening slide, section dividersslide--section slide--center
SplitText + supporting content side-by-sidesplit or split--60-40
Grid Cards3-6 related items (features, risks, components)grid-2, grid-3, grid-4
MetricsKey numbers/stats to emphasizemetrics with metric items
QuoteExpert quotes, testimonials, key statementsquote-block
WorkflowSequential process, pipeline, architectureworkflow with arrow connectors
Comparison TableFeature comparison, before/aftercomparison-table
TimelineChronological events, roadmap phasestimeline
ListOrdered or unordered key pointslist, list--check, list--numbered
CTA / ClosingFinal slide with links and contactslide--section slide--center + contact-grid

Step 3: Generate the HTML

Read the appropriate theme and template files from this skill's references directory before writing code:

  1. Always read references/THEMES.md to get the CSS variables and styles for the selected theme
  2. Always read references/TEMPLATES.md to get the HTML patterns for each slide layout
  3. Always read references/NAVIGATION.md to get the correct JS initialization for the selected navigation mode

Then assemble the presentation as a single self-contained HTML file:

File Structure

html
<!DOCTYPE html>
<html lang="en">
  <head>
    <!-- Meta, fonts, Reveal.js CDN (horizontal) or custom CSS (vertical) -->
    <!-- All styles inline in <style> block -->
  </head>
  <body>
    <!-- Slides markup -->
    <!-- Scripts: Reveal.js init (horizontal) or custom scroll handler (vertical) -->
  </body>
</html>

Key Rules

  1. Single file — everything inline. No external CSS/JS files except CDN resources (Google Fonts, Reveal.js, Lucide icons).
  2. CDN dependencies (horizontal mode):
    • https://cdn.jsdelivr.net/npm/reveal.js@4.5.0/dist/reveal.css
    • https://cdn.jsdelivr.net/npm/reveal.js@4.5.0/dist/reveal.js
    • https://cdn.jsdelivr.net/npm/reveal.js@4.5.0/plugin/highlight/highlight.js (if code blocks present)
    • https://cdn.jsdelivr.net/npm/reveal.js@4.5.0/plugin/highlight/monokai.css (if code blocks present)
    • https://unpkg.com/lucide@latest (for icons)
  3. Vertical scroll mode — zero CDN dependencies for Reveal.js. Uses custom CSS scroll-snap and vanilla JS for keyboard/scroll navigation.
  4. Google Fonts — load fonts matching the theme. Always use <link rel="preconnect"> for performance.
  5. Responsive — include media queries for 1400px, 1024px, and 768px breakpoints.
  6. Fragment animations — use class="fragment" for progressive reveal in horizontal mode. For vertical mode, use intersection observer fade-in animations.
  7. Slide numbers — always show current slide number.
  8. Kicker text — each content slide gets a numbered kicker like 01 // Section Name for editorial feel.
  9. Header bar — each content slide (not title/section slides) gets a header with an icon and section label.

Horizontal Mode: Reveal.js Config

javascript
Reveal.initialize({
  hash: true,
  slideNumber: true,
  controls: true,
  controlsLayout: "bottom-right",
  progress: true,
  center: false,
  transition: "slide",
  width: "100%",
  height: "100%",
  margin: 0.04,
  navigationMode: "linear",
  autoAnimate: true,
  autoAnimateDuration: 0.7,
  plugins: [RevealHighlight], // only if code blocks present
});

Vertical Scroll Mode: Navigation Behavior

  • Each slide is a full-viewport section with scroll-snap-align: start
  • Arrow keys (Up/Down/Left/Right) all navigate between slides
  • Mouse wheel scrolls between slides (debounced)
  • Page Up/Down, Home/End supported
  • Progress bar at bottom shows position
  • Smooth scroll transitions between slides
  • Touch swipe support for mobile

Step 4: Write to Output

  1. Create the HTML file at an appropriate output path (e.g., ./presentation.html or a user-specified location)
  2. Present the file to the user

If the content is large (>15 slides), build iteratively — write the skeleton first, then append slide content in chunks.

Error Handling

ProblemCauseFix
CDN fails to load (Reveal.js, Lucide, Google Fonts)Network unavailable or CDN outageSwitch to inline styles/scripts: embed Reveal.js core inline, replace Lucide icons with inline SVG paths, use system font stack (system-ui, -apple-system, sans-serif)
Content overflows slide viewportToo much text or too many elements per slideSplit the slide into two: move supporting detail to a follow-up slide or convert prose to a bullet list
Fonts render incorrectly or fail to loadGoogle Fonts CDN blocked or slowAdd system font fallback in the font-family stack: 'Font Name', system-ui, Georgia, serif
Reveal.js fails to initializeScript load order issue or missing pluginVerify CDN script tags appear before Reveal.initialize(); check browser console for 404s

Quality Checklist

Before delivering, verify:

  • All slides render without overflow (content fits viewport)
  • Navigation works with arrow keys AND mouse scroll
  • Slide numbers are visible
  • Fragment animations work (horizontal) or fade-in works (vertical)
  • Links are clickable (pointer-events: auto in Reveal.js)
  • Code blocks have syntax highlighting (if present)
  • Responsive at all three breakpoints
  • No broken icon references (Lucide icons initialized)
  • Consistent kicker numbering across all slides
  • Title slide and closing slide have distinct visual treatment

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 Html Presentation AI skill do?

Converts documents, outlines, or notes into self-contained HTML slide decks with horizontal (Reveal.js) or vertical scroll navigation and multiple themes. Triggers on: "create a presentation", "slide deck", "pitch deck", "HTML presentation", "web-based slides", "reveal.js deck", "convert document into slides".

Why use Html Presentation on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Mathews-Tom/armory/tree/main/skills/html-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 Html 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 Html Presentation?

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

Is the Html Presentation AI skill free?

Yes. It is published on GitHub by Mathews-Tom 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 👇