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.
npx skills add Kainiko943/beautiful-ui --skill cinematic-web-experiencegit clone --depth 1 https://github.com/Kainiko943/beautiful-uiWrote 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.
[](https://agentmods.dev/skills/kainiko943/beautiful-ui/cinematic-web-experience)<a href="https://agentmods.dev/skills/kainiko943/beautiful-ui/cinematic-web-experience"><img src="https://agentmods.dev/badge/skills/kainiko943/beautiful-ui/cinematic-web-experience/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.
<a href="https://agentmods.dev/skills/kainiko943/beautiful-ui/cinematic-web-experience"><img src="https://agentmods.dev/badge/skills/kainiko943/beautiful-ui/cinematic-web-experience.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00051 | $0.01128 |
| Opus 5.5 | $0.00020 | $0.00451 |
| Sonnet 5.5 | $0.00010 | $0.00226 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
cinematic-web-experience 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cinematic Web Experience
Overview
Use this skill when the user wants the kind of web experience that looks impressive in a short demo: full-screen composition, premium art direction, motion, depth, and a strong first-viewport reveal. This is for demo-worthy cinematic web experiences, not ordinary dashboards or static pages.
Start with beautiful-ui for product intent and visual direction, then use this skill to turn the direction into an implementable web experience. Pair with platform-web-ui for browser behavior and ui-verification before completion.
When To Trigger
- "Build something like this cinematic website."
- "Make a site that looks like a premium studio/portfolio."
- "Create a WebGL/Three.js landing page."
- "Make Claude build a wow-factor demo."
- "Add particles, bloom, glass, smoke, scroll animation, or interactive 3D."
- "Make this look like a viral AI-built website demo."
Required Workflow
- Identify the cinematic promise in one sentence.
- Define the first-viewport composition: subject, backdrop, focal point, lighting, navigation, and CTA.
- Choose the motion model: ambient loop, pointer response, scroll reveal, scene transition, or staged sequence.
- Select implementation primitives:
- Start with the Cinematic Technology Ladder and choose the simplest primitive that can deliver the intended impact.
- Use video, image sequences, Lottie, Rive, Spline, or pre-rendered assets when the scene is mostly atmospheric, decorative, or fixed.
- Use Three.js, React Three Fiber, or custom shaders only when runtime interaction, procedural motion, 3D camera control, particle behavior, or scene composition truly requires it.
- Use CSS and lightweight canvas only for simple particles or glow fields.
- Use GSAP, Framer Motion, or existing project motion tools only when already available or clearly justified.
- Design responsive fallbacks for mobile, reduced motion, slow devices, and non-WebGL browsers.
- Implement a real first screen, not a marketing placeholder.
- Verify with browser preview, Playwright screenshots, and a nonblank canvas/visual asset check.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 103 lines · 51 tokens per session scan A 436d35fee8ae
cinematic-web-experience is a skill published in the GitHub repository Kainiko943/beautiful-ui (12 stars, last pushed 6mo ago), licensed MIT. It adds 51 tokens to every session and 1,128 once invoked, about $0.0002 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 2026-08-31.
cinematic-web-experience compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| cinematic-web-experienceKainiko943/beautiful-ui | Skill | 12 | 6mo ago | MIT | A | 51 | Claude Code, Codex |
| antislop-uimiqdadbadjuber/anti-slop | Skill | 8.4k | yesterday | MIT | A | 39 | Claude Code |
| proto-bot-getting-startedmakecindy/cindy | Skill | 9.3k | yesterday | Apache-2.0 | A | 43 | Claude Code, Codex |
| proto-bot-opsmakecindy/cindy | Skill | 9.3k | yesterday | Apache-2.0 | A | 38 | Claude Code, Codex |
| design-doctrineplugin87/ux-ui-agent-skills | Skill | 3.1k | 10d ago | MIT | A | 92 | Claude Code |
| scroll-craftnateherkai/scroll-craft | Skill | 4.6k | 1mo ago | MIT | A | 177 | Claude Code |
| image-to-codeplugin87/ux-ui-agent-skills | Skill | 3.1k | 10d ago | MIT | A | 77 | Claude Code |