NVIDIA Elements is a design system and agent-oriented toolkit for building operational interfaces for AI/ML, robotics, and autonomous-vehicle software. Its CLI and MCP tools provide component APIs, design tokens, examples, imports, validation, and setup guidance across several web frameworks.
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 NVIDIA/elements --skill summarize-video-releasesgit clone --depth 1 https://github.com/NVIDIA/elementsWrote 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/nvidia/elements/summarize-video-releases)<a href="https://agentmods.dev/skills/nvidia/elements/summarize-video-releases"><img src="https://agentmods.dev/badge/skills/nvidia/elements/summarize-video-releases/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/nvidia/elements/summarize-video-releases"><img src="https://agentmods.dev/badge/skills/nvidia/elements/summarize-video-releases.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 | $0.00109 | $0.03726 |
| Opus 5.5 | $0.00044 | $0.01490 |
| Sonnet 5.5 | $0.00022 | $0.00745 |
| Haiku 4.5 | $0.00011 | $0.00373 |
Grade A, and why
summarize-video-releases 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 21d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Summarize Video Releases
Turn a monthly What’s New post into a short, fast-paced marketing video that shows the month’s changes with real Elements components, CLI output, and lint results. The post is the source of truth. This skill runs after summarize-releases and adds a WebM video, its WebP poster, a static WebP snapshot of each showcased feature in the corresponding post section, and three video metadata fields in the post frontmatter.
The video should make someone who has never used Elements want to read the post. It should be accurate to the release, legible at 1080p, and consistent with the Elements design language.
How the pieces fit
The scripts own everything that must be exact; you own the story and the markup.
scripts/read-post.jsparses the post into a JSON outline and resolves the input and output paths.- You write a storyboard JSON: scene order, copy, durations, and
nve-*demo markup. See references/storyboard.md. scripts/compose-video.jsturns the storyboard into one static HTML page fromassets/video-shell.html. It computes all timing, escapes code, and rejects videos outside 24–36 seconds.scripts/render-video.jsserves the page with Elements CDN URLs mapped to this repository’s built packages, captures frames on a virtual clock, and encodes VP9 with the browser’s built-in WebCodecs encoder.scripts/webm.jswrites the WebM file. The video workflow uses no external encoder: VP9 and its encoder are royalty-free and BSD-licensed. The renderer uses the pinned Sharp dependency to convert PNG screenshots to lossless WebP posters and stills. Output is deterministic: the same storyboard renders the same video.
Prerequisites
Run everything from the repository root.
Run mise run install to install repository dependencies, including the Sharp image encoder.
mise exec -- pnpm run playwright
Generate and regenerate videos with the latest published Elements package versions available at generation time, regardless of the release month. Resolve them with nve packages.list or nve packages.get <name>, then pin the exact versions in the storyboard's versions and imports. The monthly post determines the story, claims, and release labels; its released-package list does not determine the rendering dependencies. Refresh version pins when adapting an example or regenerating an older month's video.
What ships with it
8 files 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.
- 21d ago Changed · +36 lines · +8 tokens per session 3e4ad8a9dc89
- 22d ago First seen · 154 lines · 101 tokens per session scan A f61cffa2cd27
summarize-video-releases is a skill published in the GitHub repository NVIDIA/elements (102 stars, last pushed today), licensed Apache-2.0. It adds 109 tokens to every session and 3,726 once invoked, about $0.0004 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 2026-10-01.
Other skills, from other repositories
vue-application-structure
Establishes or reviews the directory layout, component conventions, composable design, Pinia store structure, and Vue Router configuration for a Vue 3 TypeScript application. Invoked when the user asks to structure a Vue app, set up the project layout, or review Vue architecture.
react-application-structure
Establishes or reviews the directory layout, feature boundaries, state design, routing approach, and data-fetching conventions for a React 18+ TypeScript application. Invoked when the user asks to structure a React app, set up a scalable architecture, or review React project organization.
vue-component-design
Designs or reviews Vue 3 component APIs. Handles prop drilling decisions, applies compound component patterns with provide/inject, defines minimal public API surfaces with typed props/emits/slots, and enforces Vue 3.4+ composition conventions. Invoked when creating new components, refactoring existing ones, or…
next-application-structure
Establishes or reviews directory layout, server/client boundaries, routing, data-fetching strategy, and testing structure for Next.js 14+ App Router TypeScript applications. Invoked when the user asks to structure a Next app, set App Router conventions, or review architecture for React parity.
react-component-design
Designs or reviews React component APIs. Handles prop drilling decisions, composition patterns, controlled/uncontrolled contracts, and minimal public API surfaces for React 18+ TypeScript components. Invoked when creating new components, refactoring existing ones, or reviewing component contracts.
beui
Pick and install beUI (@beui) animated React components through public MCP or the shadcn registry. Use when building motion UI, agent/chat interfaces, toasts, docks, bottom sheets, drawers, popovers, sliders, loaders, 404 pages, or any beui.dev component. Maps user intent to exact @beui install slugs instead of…