Cinematic Landing Kit

Community

alwkala

cinematic-landing-kit

Universal AI Agent Skill — Builds single-file, scroll-driven luxury landing pages (Apple x Cartier aesthetic) as one index.html with CDN-only libraries (GSAP, Lenis, Tailwind), zero build step, no framework. Fully compatible out-of-the-box with Google Antigravity, Claude Code, Cursor, Windsurf, Roo Code, Cline, Codex, and all AGENTS.md compliant AI coding agents. Scrubbed canvas frame sequence product film. Reads brand.json as single source of truth for identity, colors, typography, voice, and localization. Supports 8 luxury layouts (film, story, space, app, creator, product, store, auto) and curated luxury Arabic typography. Trigger on commands "init", "brand", "clone-brand", "media", "film", "hero", "theme", "typeface", "transitions", "i18n", "perf", "a11y", "convert", "audit", "variant", "deploy", "polish", or requests like "build a cinematic landing page", "scroll-driven product page", "luxury Apple-style landing page", "صفحة هبوط سينمائية".

Overview

Publisher	alwkala
Repository	`Cinematic-Landing-Kit`
Skill name	`cinematic-landing-kit`
Stars	9
Forks	1
Bundled files	20
License	MIT
Links	Skill source Repository Homepage

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.
20 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by alwkala on GitHub. Read the source before you install it.

Installation

Install the Cinematic Landing Kit 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.
https://github.com/alwkala/Cinematic-Landing-Kit/tree/main/.agents/skills/cinematic-landing-kit
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/alwkala/Cinematic-Landing-Kit/tree/main/.agents/skills/cinematic-landing-kit

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

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/alwkala/Cinematic-Landing-Kit.git /tmp/Cinematic-Landing-Kit
mkdir -p .claude/skills
cp -r /tmp/Cinematic-Landing-Kit/.agents/skills/cinematic-landing-kit .claude/skills/cinematic-landing-kit

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

Use it in TypingMind

Enable Cinematic Landing Kit 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 Landing Kit 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 Landing Kit 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.

Universal AI Agent Skill — Cinematic Landing Kit

Build a single-file, scroll-driven luxury landing page (Apple × Cartier aesthetic) for any product using any AI coding agent or agentic IDE.

Output is one index.html with CDN libraries (GSAP 3.12, Lenis 1.0, Tailwind CSS), zero build step, zero framework, zero bundler.

🤖 Agentic Tool Integration & Native Capabilities

This skill leverages native Agentic IDE capabilities:

Image Generation (generate_image): Used for Nano Banana keyframes, hero product stills, cutouts, and visual assets.
Browser Subagent / Visual Verification (browser_subagent): Used to drive programmatic scrolling (window.lenis.scrollTo), evaluate DOM timelines, test responsive breakpoints, and record preview video demos.
Local Shell Execution (run_command): Used to execute background removal (scripts/remove_backgrounds.py), image optimization (scripts/optimize_assets.py), transition keyframe generation (scripts/generate_transitions.py), and launch preview HTTP servers.

🏛️ Critical Architecture (The Locked Engine)

Film Engine: JPG frame-sequence (assets/seq/f000.jpg … fNNN.jpg) drawn on <canvas>, scrubbed smoothly by scroll progress. NEVER scrub video.currentTime — H.264 keyframe-seeking causes stutter.
Brand Source of Truth: brand.json at project root overrides template defaults (colors, fonts, voice, identity, localization) per memory/11-brand-json.md.
Layout Selection (via memory/10-use-cases.md):
- film (fullbleed.html) — Long scroll film, aura + motes hero (Perfume, watches, luxury automotive)
- story (editorial.html) — Split-screen hero, specs film (Specs-heavy products, brand stories, founder pages)
- space (spatial.html) — Establishing shot hero, walkthrough film (Real estate, architecture, hospitality)
- app (interface.html) — Device mockup frame hero, UI flow film (SaaS, mobile apps, digital platforms)
- creator (minimal.html) — Centered hero cutout, no canvas film (Digital products, books, creators)
- product (product.html) — Single product high-conversion e-commerce with price above fold & WhatsApp CTA
- store (store.html) — Multi-product catalog grid with category filter & per-card WhatsApp links
- auto (auto.html) — High-octane automotive & performance magazine with 3D car slider & HUD tooltips
Media Providers: nanobanana (default, built-in generate_image tool), qwen (Qwen Image + Wan via DashScope API), higgsfield (Higgsfield CLI).

🧭 Operational Modes

"What are we doing?

Init — build a brand-new cinematic landing page for a product

Convert — bring an existing static/standard landing page onto the cinematic engine

Improve — audit and harden a page already built on this kit"

⚡ Command Index & Reference Architecture

All detailed command specs reside in references/commands/:

Command	Purpose	Reference File	Phase
`init`	Primary deliverable — full working cinematic page, one pass	`references/commands/init.md`	—
`brand`	Read/scaffold `brand.json`; token → CSS variable mapping	`references/commands/brand.md`	1
`clone-brand`	Extract `brand.json` tokens from an existing site/PDF/logo	`references/commands/clone-brand.md`	1
`media`	Provider selection + asset pipeline (keyframes → clips → frames → cutout)	`references/commands/media.md`	2
`film`	Canvas frame-sequence build + `FRAME_COUNT` sync	`references/commands/film.md`	2
`hero`	Hero entrance — cutout/establishing-shot/device-mockup per layout	`references/commands/hero.md`	2
`theme`	Light/dark palette derivation (gold-deep/gold-bright, ambient tween)	`references/commands/theme.md`	2
`typeface`	Distinctive Arabic (+ Latin accent) font pairing selection	`references/commands/typeface.md`	2
`transitions`	Boundary-matched clip transitions between film segments	`references/commands/transitions.md`	2
`i18n`	Arabic/English direction, RTL, modesty & identity rules	`references/commands/i18n.md`	3
`perf`	Performance budget check — frame sequence, asset, and font weight	`references/commands/perf.md`	3
`a11y`	Accessibility pass — canvas alt-text, contrast, focus states, keyboard scroll	`references/commands/a11y.md`	3
`convert`	Retrofit an existing landing page onto the cinematic engine	`references/commands/convert.md`	—
`audit`	Quality-bar + brand.json verification checklist as a standalone report	`references/commands/audit.md`	—
`variant`	Produce an A/B page from an already-built project	`references/commands/variant.md`	—
`deploy`	Preview, asset optimization, static-hosting export	`references/commands/deploy.md`	3
`polish`	Mobile nav drawer, WhatsApp CTA, scroll-to-top & favicon	`references/commands/polish.md`	3

⚡ Memory Load Routing (Token Budget Optimization)

To keep AI agent token usage minimal (~80% reduction), read ONLY the specific memory module required for the current command:

Command	Load ONLY these memory files
`init`	`memory/10-use-cases.md` + `memory/11-brand-json.md` + chosen layout file
`brand`	`memory/11-brand-json.md`
`clone-brand`	`memory/11-brand-json.md` + `memory/15-brand-extraction.md`
`media`	`memory/06-media-pipeline.md` + provider file (`nanobanana`/`qwen`/`higgsfield`)
`film`	`memory/02-scroll-film-canvas.md`
`hero`	`memory/04-cinematic-hero.md`
`theme`	`memory/05-theming.md`
`typeface`	`memory/12-arabic-typography.md`
`perf`	`memory/13-performance-budget.md`
`a11y`	`memory/14-accessibility.md`
`convert`	`memory/15-brand-extraction.md` + `memory/10-use-cases.md`
`audit`	`memory/09-quality-bar.md`
`variant`	`memory/16-variants.md`
`deploy`	`memory/08-preview-and-env-gotchas.md`
`polish`	`memory/08-preview-and-env-gotchas.md` + `memory/09-quality-bar.md`

🔄 Command Sequencing & Execution Phases

For convert/improve work on an existing project:

Phase 1 — Brand Foundation: brand (or clone-brand when extracting an identity).
Phase 2 — Engine Build: media → film → hero → theme → typeface → transitions.
Phase 3 — Scale & Delivery: i18n → perf → a11y → deploy (always last).

📋 Quality Bar & Non-Negotiables

No video.currentTime scrubbing — canvas frame-sequence only.
No mix-blend-mode on animated elements — breaks under GSAP 3D transforms; use transparent PNG cutouts.
No manuscript / Amiri fonts above 24px — use El Messiri for display headings, Tajawal for body copy (or mood pair from memory/12-arabic-typography.md).
Modesty mandatory — conservative attire for human subjects in generated imagery.
prefers-reduced-motion fallback required on canvas animations.
Canvas ARIA attributes — <canvas aria-hidden="true"> with container aria-label.
Strict brand.json compliance — no hardcoded hex colors or font families when brand tokens exist.

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 Cinematic Landing Kit AI skill do?

Why use Cinematic Landing Kit on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/alwkala/Cinematic-Landing-Kit/tree/main/.agents/skills/cinematic-landing-kit. 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 Cinematic Landing Kit?

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 Landing Kit?

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

Is the Cinematic Landing Kit AI skill free?

Yes. It is published on GitHub by alwkala 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

Grill With Docs

mattpocock

CommunityPopular

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Grill Me

A relentless interview to sharpen a plan or design.

Brand Discovery

Use when a brand needs to discover or articulate its identity through structured multi-session interviews. Covers purpose, positioning, audience, personality, voice, narrative, and founder-brand…

Competitive Platform Analysis

affaan-m

CommunityPopular

Use when scoping a competitive landscape — identifying, categorising, and score-filtering a competitor set before any benchmarking begins. Decides who counts as a competitor, which tier they belong…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Universal AI Agent Skill — Cinematic Landing Kit

🤖 Agentic Tool Integration & Native Capabilities

🏛️ Critical Architecture (The Locked Engine)

🧭 Operational Modes

⚡ Command Index & Reference Architecture

⚡ Memory Load Routing (Token Budget Optimization)

🔄 Command Sequencing & Execution Phases

📋 Quality Bar & Non-Negotiables

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now