Video To Landing Page

Community

hoodini

video-to-landing-page

Turn any video into a cinematic scroll-driven landing page — Apple-style hero where scrolling progresses the visible frame through the video. Use when the user provides a video file and asks for "a landing page from this video", "scroll-frame website", "Apple-style scroll site", "hero that scrubs the video", "like the GitHub Copilot landing", or any equivalent. Extracts N evenly-spaced frames via ffmpeg, builds a self-contained HTML page with a sticky hero + JS scroll listener that swaps the visible frame as you scroll, plus headline, sections and CTA below. For YUV.AI projects, applies the yuv-design-system skill in Neon mode (pink/cyan/white, default for YUV.AI web) — Decks (purple/yellow) is reserved for slides only. For generic / non-YUV.AI projects, picks an appropriate palette per the source video. Output is one folder with `index.html` and a `frames/` directory — drop on any static host.

Overview

Publisher	hoodini
Repository	`ai-agents-skills`
Skill name	`video-to-landing-page`
Stars	280
Forks	62
Bundled files	4
Links	Skill source Repository

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 hoodini on GitHub. Read the source before you install it.

Installation

Install the Video To Landing Page AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
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.

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/hoodini/ai-agents-skills.git /tmp/ai-agents-skills
mkdir -p .claude/skills
cp -r /tmp/ai-agents-skills/skills/video-to-landing-page .claude/skills/video-to-landing-page

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Video To Landing Page 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 Video To Landing Page 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 Video To Landing Page 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.

Video → Scroll-Driven Landing Page

Build a cinematic landing page where the hero is a video playing on scroll instead of time — like Apple product pages or the GitHub Copilot landing. Frames are extracted from the source video and swapped as the user scrolls; below the sticky hero, normal-scroll sections carry copy and CTA.

When to invoke

User drops a video and asks for a landing page, scrolling site, scroll-frame hero, or website from a video
Mentions of "Apple-style scroll", "GitHub Copilot landing", "scrub-on-scroll", "frame on scroll"
Hebrew equivalents: "דף נחיתה מסרטון", "אתר עם גלילה", "סרטון בגלילה"

Save location

Default: ~/Documents/yuv-projects/landings/<slug>/ — always save landing pages here so you can find them again. Create the parent directory if missing.

bash
mkdir -p ~/Documents/yuv-projects/landings
cd ~/Documents/yuv-projects/landings
# Build <slug>/ here.

Final path: ~/Documents/yuv-projects/landings/<slug>/. Tell the user where the landing lives at the end of every build.

Workflow (8 steps)

Probe the source — ffprobe for duration, fps, dimensions, audio.
Pick frame count — default 80. Floor 40 (choppy if lower), ceiling 160 (heavy page). Choose by duration: ≤10s → 50, 10–30s → 80, 30–60s → 120, >60s → 160.
Decide output directory — default ~/Documents/yuv-projects/landings/<slug>/. The <slug> is short, derived from the video name or the topic. Override only on explicit request.
Extract frames — run references/extract-frames.py <source-video> <output-dir> [count]. Outputs output-dir/frames/f_0001.jpg… with consistent JPG quality 82 and a max-width of 1920 (downscaled if source is larger).
Copy and customise references/landing-template.html into output-dir/index.html:
- Replace the __FRAMES__ placeholder with <img> tags for each frame (the build script does this for you when you pass --build-html).
- Fill in __HEADLINE__, __TAGLINE__, __CTA_TEXT__, __CTA_HREF__, sections.
- For Hebrew content: set <html lang="he" dir="rtl"> and swap fonts to Rubik/Assistant (see references/design-notes.md).
Optimise frames — the build script already scales to 1920px max-width. If the page total weight is > 12 MB, drop quality to 75 or reduce frame count.
Preview — python -m http.server inside the output directory and open http://localhost:8000. Scroll feels buttery on a decent machine.
Deploy — drop the folder on Vercel/Netlify/Cloudflare Pages. No build step needed.

The scroll mechanic

Outer scroller .scroll-stage height set in viewport units (default 600vh = scroll 5 screens to traverse all frames).
Sticky hero position: sticky; top: 0; height: 100vh containing all frames absolutely positioned and hidden except the active one.
Scroll listener computes progress = scrolledIntoStage / scrollableHeight clamped 0–1.
idx = floor(progress * (N - 1)) — swap the .active class to that frame.
Wrap the listener in requestAnimationFrame to keep 60fps.

Design rules

If the project is YUV.AI-branded (Yuval personally, his portfolio, his brand): call yuv-design-system and lock it to a mode by medium —
- Neon mode (DEFAULT for YUV.AI web): hot pink (#FF1464) + neon cyan (#00E5FF) + white or rich black canvas. Anton + Inter (English) / Rubik + Assistant (Hebrew). 0px or 999px radii.
- Warm Editorial mode: only for Hope, Marcus, bigcats.ai, practical.yuv.ai — pink + yellow + bone, off-white never pure #fff.
- Never use Decks mode (Fly High purple/yellow) for a landing page — that palette is reserved for slide decks only.
If the project is not YUV.AI-branded: do not apply yuv-design-system. Pick a palette that fits the source video's mood. Anton + Inter remain reasonable defaults but aren't mandatory.
Hero overlays should be subtle — a vignette and a single big headline; don't drown the frame.
Below-hero sections: light canvas (white in Neon mode, off-white in Warm Editorial, bone if going generic-warm), large Anton heading, body copy in Inter at 18–22px, CTA as a sharp pill (border-radius: 999px) — pink fill in Neon mode, brand-appropriate color otherwise.
For Hebrew: respect RTL, use Rubik 900 for headlines, Assistant 400/500 for body.

File references

File	Purpose
`references/extract-frames.py`	ffmpeg-based frame extractor; optionally builds the full HTML in one go
`references/landing-template.html`	Self-contained landing-page skeleton with the scroll mechanic
`references/design-notes.md`	Typography, palette, and motion defaults

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 Video To Landing Page AI skill do?

Why use Video To Landing Page on TypingMind?

Because you install it once and use it with any model. Video To Landing Page 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 Video To Landing Page in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/hoodini/ai-agents-skills/tree/master/skills/video-to-landing-page. 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 Video To Landing Page?

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 Video To Landing Page?

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

Is the Video To Landing Page AI skill free?

It is published on GitHub by hoodini. Check the repository for licensing terms. 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

Agent Development

anthropics

OrganizationPopular

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors",…

Skill Development

This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improve skill description", "organize skill content", or needs guidance on skill…

Ponytail

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the…

Autoplan

Auto-review pipeline — reads the full CEO, design, eng, and DX review skills from disk and runs them sequentially with auto-decisions using 6 decision principles. (gstack)

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Video → Scroll-Driven Landing Page

When to invoke

Save location

Workflow (8 steps)

The scroll mechanic

Design rules

File references

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now