Slides logo

Slides

Organization
Rune-kit
slides

Generate Marp-compatible slide decks from structured JSON schema. Converts context into presentations for tech talks, sprint demos, and tutorials.

Overview

PublisherRune-kit
Repositoryrune
Skill nameslides
Stars
88
Forks
26
Bundled files
1
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.

  • 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 Rune-kit on GitHub. Read the source before you install it.

Installation

Install the Slides 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/Rune-kit/rune/tree/master/skills/slides
  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/Rune-kit/rune.git /tmp/rune
mkdir -p .claude/skills
cp -r /tmp/rune/skills/slides .claude/skills/slides
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Slides 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 Slides 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 Slides 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.

slides

Purpose

Generates structured slide decks as Marp-compatible markdown. The agent analyzes context (feature, sprint, tutorial) and produces a JSON slide schema, then calls build-deck.js to convert it to presentation-ready markdown. The script standardizes output format — preventing agent freestyle errors when context runs low.

Triggers

  • User says "create slides", "make presentation", "demo deck", "sprint review slides", "tech talk"
  • /rune slides — manual invocation
  • Called by other skills needing presentation output

Called By (inbound)

  • marketing (L2): launch presentations, product demos
  • video-creator (L3): slide-based video storyboards
  • User: direct invocation

Calls (outbound)

None — pure L3 utility.

Executable Instructions

Step 1: Analyze Context

Determine the presentation type from the user's request:

ContextTemplateTypical Slides
Feature demoDemo walkthroughProblem → Solution → Architecture → Live demo → Next steps
Sprint reviewSprint summaryGoals → Completed → Metrics → Blockers → Next sprint
Tech talkTeaching formatHook → Concept → Deep dive → Code examples → Takeaways
TutorialStep-by-stepIntro → Prerequisites → Step 1-N → Summary → Resources
PitchPersuasionProblem → Market → Solution → Traction → Ask

Step 2: Generate JSON Schema

Create a JSON file following this schema:

json
{
  "title": "Presentation Title",
  "author": "Author Name (optional)",
  "theme": "default|gaia|uncover",
  "slides": [
    {
      "type": "title|content|code|diagram|image|quote|section",
      "heading": "Slide Heading",
      "body": "Markdown body text",
      "notes": "Speaker notes (optional)",
      "code": { "lang": "javascript", "source": "console.log('hi')" },
      "diagram": "graph LR; A-->B"
    }
  ]
}

Slide types:

  • title — opening slide with # heading
  • content — standard slide with ## heading + body
  • code — slide with syntax-highlighted code block
  • diagram — slide with Mermaid diagram (stays a Mermaid fence for Marp; do NOT replace with a diagram-generated HTML here)
  • image — slide with image reference in body
  • quote — slide with blockquote formatting
  • section — section divider with # heading

Save the JSON to a temporary file (e.g., slides.json).

Step 3: Build Deck

Execute the build script:

bash
node {scripts_dir}/build-deck.js --input slides.json --output deck.md

The script outputs Marp-compatible markdown with:

  • Marp frontmatter (marp: true, theme)
  • Slide separators (---)
  • Speaker notes as HTML comments
  • Code blocks with language hints
  • Mermaid diagram blocks

Step 4: Present Result

Show the user:

  1. The generated deck.md file path
  2. How to preview: npx @marp-team/marp-cli deck.md --preview (or any Marp viewer)
  3. How to export PDF: npx @marp-team/marp-cli deck.md --pdf

Fallback: If {scripts_dir}/build-deck.js is unavailable, generate the Marp markdown directly — the script is an optimization, not a hard dependency.

Output Format

markdown
---
marp: true
theme: default
---

# Presentation Title

Author Name

---

## Slide Heading

Slide body content

<!-- notes: Speaker notes here -->

Sharp Edges

Failure ModeSeverityMitigation
build-deck.js not foundLOWAgent generates Marp markdown directly (fallback)
Invalid JSON inputMEDIUMScript exits 1 with parse error — agent fixes JSON and retries
Marp not installedLOWScript outputs plain .md — user installs Marp CLI separately
Too many slides (>30)MEDIUMAgent should split into multiple decks or summarize
System/architecture/flow/sequence/state/ER/swimlane diagramsMEDIUMEditorial HTML/SVG diagrams → diagram. For an editorial slide graphic: diagram with size=slide-16x9, then embed the HTML or a screenshot — do NOT replace the Marp type: diagram fence (that stays Mermaid for build-deck.js)

Constraints

  1. Output MUST be valid Marp markdown (parseable by @marp-team/marp-cli)
  2. DO NOT embed build-deck.js source in this skill — call it via {scripts_dir}
  3. DO NOT require Marp installation — output is standard markdown that Marp can consume
  4. Keep slide count reasonable (5-15 for demos, 10-25 for talks)
  5. Always include speaker notes for non-trivial slides

Returns

ArtifactFormatLocation
Slide schemaJSONslides.json (temporary)
Presentation deckMarp Markdowndeck.md or user-specified path

Done When

  • Presentation type identified (demo/sprint/talk/tutorial/pitch)
  • JSON schema generated with correct slide types
  • build-deck.js executed (or fallback markdown generated)
  • Output file path presented to user
  • Preview/export commands provided

Cost Profile

~500-1500 tokens input, ~300-800 tokens output. Sonnet for quality copy and structure.

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 Slides AI skill do?

Generate Marp-compatible slide decks from structured JSON schema. Converts context into presentations for tech talks, sprint demos, and tutorials.

Why use Slides on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Rune-kit/rune/tree/master/skills/slides. 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 Slides?

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 Slides?

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

Is the Slides AI skill free?

Yes. It is published on GitHub by Rune-kit 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 👇