scrollcraft-layout

scrollcraft-layout is a skill for Claude Code from anton-abyzov/vskill. It costs 137 tokens per session (1,193 once invoked), scanned A, original, MIT.

A design skill for turning a static website into a layered page whose visuals and content change as the visitor scrolls. It covers planning the mood, scroll journey, assets, and page composition before coding.

In plain words
What is it for?
Use it when designing premium or interactive scrolling layouts, especially for no-package static websites and pages with layered backgrounds, images, video, or generated filler assets.
Why use it?
It gives a structured way to make scrolling communicate a story instead of leaving a flat page unchanged as the visitor moves through it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the frontend plugin — 4 skills shipped together

Good fit Use it when designing premium or interactive scrolling layouts, especially for no-package static websites and pages with layered backgrounds, images, video, or generated filler assets.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/anton-abyzov/vskill/scrollcraft-layout
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add anton-abyzov/vskill --skill scrollcraft-layout
Clone the repo
git clone --depth 1 https://github.com/anton-abyzov/vskill

Made for: Claude Code.

Or install frontend, the plugin that ships this one along with the rest of its 4 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for scrollcraft-layout

README.md
[![agentmods](https://agentmods.dev/badge/skills/anton-abyzov/vskill/scrollcraft-layout/github.svg)](https://agentmods.dev/skills/anton-abyzov/vskill/scrollcraft-layout)
Your own site
<a href="https://agentmods.dev/skills/anton-abyzov/vskill/scrollcraft-layout"><img src="https://agentmods.dev/badge/skills/anton-abyzov/vskill/scrollcraft-layout/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for scrollcraft-layout

Your own site · 80×15
<a href="https://agentmods.dev/skills/anton-abyzov/vskill/scrollcraft-layout"><img src="https://agentmods.dev/badge/skills/anton-abyzov/vskill/scrollcraft-layout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 137 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,193 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00137 $0.01193
Opus 5.5 $0.00055 $0.00477
Sonnet 5.5 $0.00027 $0.00239
Haiku 4.5 $0.00014 $0.00119

Measured 20d ago against content hash 5850743ea9f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

scrollcraft-layout scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 20d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/frontend/skills/scrollcraft-layout/SKILL.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

scrollcraft-layout

Source: transcript of youtube.com/watch?v=QUI6Ug4cHnE (Nate Herk, "I Built The Ultimate Claude Website Design Skill", Aug 2026). Core idea: the scroll is the story. Every scroll gesture should correlate with something happening on the page, so the visitor is hooked like short-form content and keeps going. Keep the copy and the brand; change how it unfolds.

1. Interview first (2 minutes, not 20)

Answer these before touching code (from the brief or by asking):

  • Vibe on two axes: premium/trusted/editorial ↔ energetic/hype, and real assets ↔ generated world. Anton's sites default to premium editorial with real photos/videos.
  • The scroll journey: what should the visitor feel at second 0, 5, 20, 60? Which single thing must they remember?
  • Real assets available (photos, clips, logos). Generate only fillers that match the palette (Kie/GPT Image via the kie-gemini-omni skill), never photoreal people.
  • "One thing this site does that no site you have seen does."

2. Composition rules that read as premium

  • Hero must not be bland: depth (layered background planes, grain, a light source), a magazine-cover lockup (name as object, one line of role, one CTA), a subtle scroll-linked zoom or parallax, real photo/video cut-out on its own layer.
  • One thing at a time: long sections become pinned sequences where content swaps as you scroll (a "stage" with 3–6 beats), or horizontal scroll rails for series (career eras, products, goals).
  • Numbers count up on scroll, images reveal with scroll (mask/clip), lines draw, text arrives staggered. Slow it down: a scroll-linked animation should take ~60–100 vh of scroll to complete, not 20. Fast = invisible.
  • Layers: at least three planes moving at different rates (background field, mid content, foreground accents). Use translate3d only.
  • Typography and spacing carry taste: display + body pairing (no Inter/Roboto/Arial/system-ui/Space Grotesk), generous whitespace, editorial hierarchy, a data voice for metrics.
  • Cards get dynamic hover (tilt/glow following the pointer) but never depend on hover for meaning.
  • Cut what is bland or redundant rather than animating it.

Read the full file on GitHub · 42 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 20d ago First seen · 42 lines · 137 tokens per session scan A 5850743ea9f6

Subscribe to this mod's changes

scrollcraft-layout is a skill published in the GitHub repository anton-abyzov/vskill (47 stars, last pushed today), licensed MIT. It adds 137 tokens to every session and 1,193 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-26.

Related

Other skills, from other repositories

tailwind-design-system

Build scalable design systems with Tailwind CSS v4, design tokens, component libraries, and responsive patterns. Use when creating component libraries, implementing design systems, or standardizing UI patterns.

calesthio/OpenMontage · 42 tokens

ui

Generation d'interfaces SaaS — basic, premium dark-mode, ou landing page complete. Choisir le mode selon le besoin.

GlamgarOnDiscord/claude-saas-blueprint · 28 tokens

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI).…

ErikaAX08/erikas-skills · 77 tokens

gpt-taste

Use when generating elite GSAP-heavy frontend pages with strict AIDA structure, wide hero typography, and gapless bento grids.

aboalrejal-ai/skills · 31 tokens

gsap-scrolltrigger

Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building or recommending scroll-based animation, parallax, pinned sections, or when the user asks about ScrollTrigger, scroll animations, or pinning. Recommend GSAP for scroll-driven animation when no library is…

calesthio/OpenMontage · 68 tokens

gsap-timeline

Official GSAP skill for timelines — gsap.timeline(), position parameter, nesting, playback. Use when sequencing animations, choreographing keyframes, or when the user asks about animation sequencing, timelines, or animation order (in GSAP or when recommending a library that supports timelines).

calesthio/OpenMontage · 61 tokens