Cinematic Motion logo

Cinematic Motion

Community
madebymustafa
cinematic-motion

Genre pack: the site-of-the-day aesthetic — the page as a film projected on studio print. Warm paper canvas, near-black ink type, one vivid electric-blue accent, grotesk display, alternating scene canvases, a scrubbed index counter, text-dissolve pins, and a drag-driven card carousel. For portfolios, product launches, agencies, and any brief that wants premium scroll-driven storytelling. Requires taste-gsap for the implementation. Stack on the design-taste core skill.

Overview

Publishermadebymustafa
Repositorydesign-taste
Skill namecinematic-motion
Stars
198
Forks
10
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Cinematic Motion 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/madebymustafa/design-taste/tree/main/skills/cinematic-motion
  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/madebymustafa/design-taste.git /tmp/design-taste
mkdir -p .claude/skills
cp -r /tmp/design-taste/skills/cinematic-motion .claude/skills/cinematic-motion
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cinematic Motion 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 Cinematic Motion 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 Cinematic Motion 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.

cinematic-motion

One identity: opening credits, projected on studio print — the scroll is the projector, the paper is the screen, and one electric blue is the light.

1. PALETTE (Fixed)

  • Canvas: #F7F5E7 (warm studio paper — never white, never grey). Cards: #FCFBF4. Hairline rules: rgba(18,18,18,0.14).
  • Ink: #121212 (all primary type). Muted: rgba(18,18,18,0.55) (labels, secondary). On dark scenes invert: ink canvas, paper type, rgba(247,245,231,0.16) hairlines.
  • Accent — exactly one: #0F4BFD (electric blue). Used for: the accent word, one hairline, stats, one fill. That's the budget.
  • The canvas flips are the rhythm: paper scenes alternate with ink scenes and one full blue scene. Scene-hops are the signature; max two ink scenes (the index and the roadmap own them) and one blue section per page.
  • NO gradients (the paper is the texture — clean, flat, no grain, no blends), NO second accent, NO pure black (#000), NO white sections.

2. TYPOGRAPHY (Fixed)

  • Display: a tight grotesk (Inter Tight), weights 500–700, sentence case. NO serifs, no italics — the accent word earns attention by color alone.
  • Headlines: clamp(3rem, 9vw, 8rem), weight 600, leading 0.94, tracking −0.04em. One blue accent word per headline, never two.
  • Scene h2s: same family, weight 600, clamp(1.6rem, 3.4vw, 2.6rem), tracking −0.02em, with mono kickers.
  • Labels/metadata: mono caps (ui-monospace/IBM Plex Mono), letter-spacing: 0.14em, 10–11px, muted. Numbered kickers: 01 — THE LEAK, 02 — THE INDEX.
  • No body text below 14.5px; body in the grotesk at 400, line-height 1.65–1.7, muted for secondary.
  • CTAs are pills (this pack allows them): ink pill, blue fill sweeps up on hover (::before + transform: translateY transition). Max one pill per viewport besides the nav.

3. COMPOSITION (Fixed)

  • The film structure: hero with a live product screen (paper) → statement brief (paper) → the pinned index (ink) → marquee (paper, outlined type) → statement brief (full blue) → drag carousel (paper) → detail accordion (paper) → the pinned roadmap (ink) → evidence (paper) → the close (blue) → footer (ink).
  • One pinned index + one pinned roadmap = two pins total — the budget (see taste-gsap: desktop-only, += ends).
  • The giant scrubbed index numeral (the 63% beat) sits pinned, counting with the scrub; the roadmap pin scrubs its four steps up a rail whose fill climbs in blue (steps build, they never crossfade-swap).
  • Hero presence without video: the live product screen — a CSS-built dashboard (live counter that ticks, funnel bars, a playing waveform, stat cells) that reads like product footage without a single video frame. All its loops are CSS keyframes, killed under reduced motion; the tick is a JS interval, gated.
  • The accordion is native <details>/<summary> — first item open by default, rotating + medallion, no JS required to work, no-JS complete by construction.
  • Hero atmosphere: a blue particle field (canvas, ~60 dots, upward drift, ≤ 0.16 alpha) and one dashed orbit ring, rotating slowly — both JS-gated, both dead under reduced motion.
  • Index numerals: giant, weight 600, sitting in scene corners where kitchen-sink kits would put pictures.

4. CONTENT TREATMENT

  • Numbered kickers keep the filmic beat structure: 01 — THE LEAK → 05 — THE CLOSE. The footer is the colophon: A SKITTIE FILM — PRODUCED IN 60 FPS.
  • Copy is quiet, confident, filmic: short lines, no exclamation marks, no superlatives. One blue accent word per headline carries the emotion.
  • No emoji. No icons — typographic marks (✳) and CSS-drawn mini-data-visuals only (funnel bars, wave bars, cohort grids — ink shapes with one blue cell).
  • One primary CTA per viewport; the secondary action is a mono text link with a blue underline.

5. MOTION (The Soul — See taste-gsap)

  • The page runs on a gsap.context + matchMedia shell: everything animated lives inside (prefers-reduced-motion: no-preference) and heavy effects inside (min-width: 768px).
  • The signature moments, in order: preloader (percentage counter ≤ 2s, slides away, only when JS + motion are active — hidden by default in CSS) → hero intro timeline (expo.out, masked line rises, the product screen slides in from the right, ≤ 1.4s) → the index pin: giant numeral counts 0 → 63 scrubbed with snapping, lines dissolve in stagger, progress hairline fills → marquee (CSS, outlined) → the drag carousel (Draggable + inertia, bounds from scrollWidth − offsetWidth, force-snapped native scroll as no-JS fallback, cursor swaps to a blue "DRAG" medallion) → the roadmap pin: four steps rise along a rail as its blue fill climbs, scrubbed → metric count-ups on entry.
  • The atmosphere layer: Lenis smooth scroll (see taste-gsap §1), difference-blended custom cursor (lerped with quickTo, grows on interactive hover, DRAG label over the carousel, hidden on coarse pointers), magnetic primary CTA (≤ 5px pull), scroll-progress hairline in the nav. The hero's live counter ticks on an interval — a cheap "it's alive" beat that dies with the rest under reduced motion.
  • Durations 0.9–1.6s; easing power3.out / expo.out; scrub smoothing 0.6–1. All motion on transform/opacity (see taste-gsap §3). The close headline's accent word renders hollow-outlined (stroke, transparent fill) — a still-frame moment that doesn't move at all.
  • The page must be complete and beautiful with JS off and with reduced motion on — pins collapse to stacked sections, the carousel becomes a native scroll-snap strip, the index shows its final value. If the still frame is boring, it fails.

6. CHECKLIST (Fail the Page If…)

  • Any gradient, any second accent, any pure black, any white section.
  • The accent blue used for a full section and the close — only one full-blue scene allowed.
  • More than two ink (dark) scenes — the index and the roadmap own them.
  • A headline with no blue accent word, or two of them.
  • Any serif or italic type — this identity is grotesk-only.
  • More than one marquee, or a marquee that runs under reduced motion.
  • No numbered kickers / no film metaphor in the copy.
  • More than two pins total, any pin below 768px, or animation without matchMedia gating.
  • A drag carousel with no native scroll-snap fallback (JS off), or one that can't be reached with a keyboard.
  • An accordion built with anything but native <details>/<summary> — it must work with JS off.
  • Hero "video" (or a live screen) that keeps animating under reduced motion.
  • A preloader that could ever show without JS, or that runs under reduced motion.
  • A custom cursor visible on touch devices, or content that depends on cursor feedback.
  • Animated layout properties or a reveal that hides content permanently if JS fails.
  • The page's wow depends on the animation — the still frame must carry it.

Frequently asked questions

What does the Cinematic Motion AI skill do?

Genre pack: the site-of-the-day aesthetic — the page as a film projected on studio print. Warm paper canvas, near-black ink type, one vivid electric-blue accent, grotesk display, alternating scene canvases, a scrubbed index counter, text-dissolve pins, and a drag-driven card carousel. For portfolios, product launches, agencies, and any brief that wants premium scroll-driven storytelling. Requires taste-gsap for the implementation. Stack on the design-taste core skill.

Why use Cinematic Motion on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/madebymustafa/design-taste/tree/main/skills/cinematic-motion. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Cinematic Motion?

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 Cinematic Motion?

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

Is the Cinematic Motion AI skill free?

Yes. It is published on GitHub by madebymustafa 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 👇