Narrative Scrollytelling logo

Narrative Scrollytelling

Community
glebis
narrative-scrollytelling

Turn an ordered sequence of ideas into a readable scroll-based story with canonical document order, deliberate step or progress transitions, native scrolling, and static, reduced-motion, keyboard, touch, and no-JavaScript fallbacks. Use when a method, argument, timeline, process, or visual explanation should unfold as the reader scrolls rather than behave like a slide deck. Triggers on scrollytelling, scroll story, narrative scroll, sticky story, scroll-driven narrative, scroll animation, step story, chapter reveal, pinned visual, interactive article.

Overview

Publisherglebis
Repositoryhumane-agentic-design
Skill namenarrative-scrollytelling
Stars
38
Forks
3
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

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

Installation

Install the Narrative Scrollytelling 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/glebis/humane-agentic-design/tree/main/humane/skills/narrative-scrollytelling
  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/glebis/humane-agentic-design.git /tmp/humane-agentic-design
mkdir -p .claude/skills
cp -r /tmp/humane-agentic-design/humane/skills/narrative-scrollytelling .claude/skills/narrative-scrollytelling
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Narrative Scrollytelling 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 Narrative Scrollytelling 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 Narrative Scrollytelling 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.

Narrative Scrollytelling

Announce at start: "I'm using the humane:narrative-scrollytelling skill to turn this sequence into a scroll story that remains a readable document."

Scrollytelling is a document before it is choreography. The ordered ideas, headings, prose and media alternatives form a complete canonical reading order; scroll position may change their presentation, never their existence or meaning.

Quick reference

NeedRead
Story shapes, drivers, sticky stages and pacingreferences/patterns.md
The story-map fields and fallback invariantsreferences/contract.md

Build the story map

  1. Establish the ordered beats outside the visual treatment. Each beat carries one claim or change in understanding and a stable id.
  2. Choose the least demanding driver that expresses the relationship: discrete-intersection for prose steps, view-progress for a visual whose change follows its visibility, and scroll-progress only when intermediate states themselves communicate meaning.
  3. Decide what remains in normal document flow and what may be sticky. A sticky visual stage is normally non-focusable; interactive content stays in logical source order.
  4. Specify navigation and fallbacks before transition polish: anchors, previous/next where useful, skip-story, no-JavaScript, reduced-motion, no-motion and unsupported-driver behavior.
  5. Only then name transition intents and token references.

Write the result using references/contract.md. When the user wants a saved artifact, resolve artifact_path(name, "narrative-scrollytelling", "json"); never assemble a .design path at the call site. Validate a saved map with python3 scripts/validate_map.py <map.json>.

Hard boundaries

  • steps[] order is canonical DOM and reading order. Every essential fact is present as semantic content outside canvas frames, keyframes and transition labels.
  • Native page scrolling remains in control. Do not hijack wheel/touch input, lock the reader into a scene, require scroll speed/direction, or turn the document into an inaccessible slide deck.
  • Scrolling does not move focus or announce every step. Sticky authored content cannot obscure focused controls; reserve safe offsets and scroll padding.
  • Default snap is none; proximity is optional. mandatory requires an explicit audited exception proving all content remains reachable at zoom, reflow, large text and short viewports.
  • Reduced motion removes parallax, scrubbed spatial travel, smooth scrolling and long pinning. The fallback uses discrete static states or the linear document; meaning never depends on an exact progress fraction.
  • No-JavaScript and unsupported-feature modes expose the whole story. Native CSS scroll timelines are progressive enhancement, not a prerequisite.
  • Continuous automatically started movement is absent by default. If an essential presentation exceeds five seconds alongside other content, provide pause, stop or hide controls and name the reason.

Embedded interactions and sound

This skill owns chapter activation and presentation, not feedback for buttons, toggles, maps or other controls inside a chapter. Hand those bounded transitions to humane:semantic-micro-interactions.

Passive scroll crossings do not play sound. If the experience has opted into audio, explicit chapter navigation or a genuinely committed milestone may emit a semantic soundEvent through its micro-interaction map; sound-effects then owns the audio asset and playback layer. Narrative ambience, scoring and narration are outside this skill.

Verification and handoff

Read the complete story with CSS and JavaScript disabled, then with reduced and no motion. Test forward and reverse keyboard traversal, anchors, previous/next, skip-story, zoom/reflow, short and narrow viewports, touch scrolling, back/forward navigation, refresh at a deep anchor, and fast bidirectional scrolling. Confirm that every visual state resolves and that no focused control is hidden.

Record observed coverage and mark the rest Not verified. Hand the operable story to humane:walkthrough; this skill owns the narrative mechanism, while walkthrough determines whether a reader can actually understand and complete the intended path.

What this skill does not own

ConcernOwner
The source wording of headings and proseux-writing
Duration, dimension, color and typography valuesdesign-tokens
Bounded component feedback inside a chaptersemantic-micro-interactions
Sound generation, assets and playbacksound-effects, reached through the micro-interaction hook
Task success and contextual verificationwalkthrough
Framework-specific scroll-animation craft and accessibility engineering depthinterfaces when installed; otherwise mark the implementation depth Not reviewed

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 Narrative Scrollytelling AI skill do?

Turn an ordered sequence of ideas into a readable scroll-based story with canonical document order, deliberate step or progress transitions, native scrolling, and static, reduced-motion, keyboard, touch, and no-JavaScript fallbacks. Use when a method, argument, timeline, process, or visual explanation should unfold as the reader scrolls rather than behave like a slide deck. Triggers on scrollytelling, scroll story, narrative scroll, sticky story, scroll-driven narrative, scroll animation, step story, chapter reveal, pinned visual, interactive article.

Why use Narrative Scrollytelling on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/glebis/humane-agentic-design/tree/main/humane/skills/narrative-scrollytelling. 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 Narrative Scrollytelling?

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 Narrative Scrollytelling?

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

Is the Narrative Scrollytelling AI skill free?

Yes. It is published on GitHub by glebis 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 👇