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 skillmds/skillmd --skill nvidia-design-analysisgit clone --depth 1 https://github.com/skillmds/skillmdWrote 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/skillmds/skillmd/nvidia-design-analysis)<a href="https://agentmods.dev/skills/skillmds/skillmd/nvidia-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/nvidia-design-analysis/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/skillmds/skillmd/nvidia-design-analysis"><img src="https://agentmods.dev/badge/skills/skillmds/skillmd/nvidia-design-analysis.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 | $0.00155 | $0.09173 |
| Opus 5.5 | $0.00062 | $0.03669 |
| Sonnet 5 | $0.00031 | $0.01835 |
| Haiku 4.5 | $0.00015 | $0.00917 |
Grade A, and why
NVIDIA-design-analysis 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 4d 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 — 641 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
NVIDIA's marketing system is built like a piece of engineering documentation that learned graphic design — every page is a structured cascade of dense, factual information arranged on a paper-white grid, framed top and bottom by deep black hero/footer chapters. There is exactly one accent color in the entire system, and it is doing all the work: NVIDIA Green ({colors.primary} — #76b900), used for every primary CTA, every active tab, every link affordance on dark surfaces, and the small decorative corner squares that mark out card containers. Nothing else competes for attention.
The system's character comes from extreme typographic restraint and an almost punishingly angular geometry. Every container, button, and image uses {rounded.sm} (2px) — a token that's barely-there but never zero, giving the system the precise, technical feel of CAD output rather than warm consumer software. Cards sit on plain {colors.canvas} with a hairline {colors.hairline} border (no shadow, no elevation), separated by tight 8px-base spacing rhythm. Long-form pages stack 6–10 of these cards into multi-column technical grids without ever introducing decorative breaks.
The black-canvas hero and footer chapters are the system's "headline moments" — a single full-bleed photographic or 3D-rendered image with {typography.display-xl} headline copy laid in white, a single green CTA button, and a small green corner square as the only ornamentation. Everything else is subordinate.
Key Characteristics:
- Single-accent system:
{colors.primary}carries every CTA, active state, and decorative motif. The rest is monochrome black/white/gray. - Two-mode surface architecture:
{colors.surface-dark}for hero/footer chapters;{colors.canvas}for body — alternating in a predictable rhythm down the page - Hyper-angular geometry:
{rounded.sm}(2px) on every interactive element. There are no pill buttons, no rounded cards, no soft chrome. - NVIDIA-EMEA proprietary sans-serif at weights 400 and 700, scaled across a 12-tier hierarchy from
{typography.utility-xs}(10px) up to{typography.display-xl}(48px) - Card library leans on hairline
{colors.hairline}borders and{colors.surface-soft}backgrounds rather than shadows for separation - Signature decorative element: the small
{component.corner-square}(~12px green square) anchored to one corner of resource and feature cards - Dense multi-column footer with 4–6 link columns on
{colors.surface-dark}— every page closes with the same structured global navigation
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.
- 4d ago First seen · 641 lines · 155 tokens per session scan A 9c0562969ea9
NVIDIA-design-analysis is a skill published in the GitHub repository skillmds/skillmd (1 stars, last pushed yesterday), licensed MIT. It adds 155 tokens to every session and 9,173 once invoked, about $0.0006 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 2026-09-19.
Other skills, from other repositories
get-context
Mandatory design-brief gate for clarifying the product and outcome. Use before ideation, image-to-code builds, redesigns, or product UI work to clarify missing product information and play back the brief before proceeding.
frontend
Builds, styles, and polishes web UI and UX. Use for any frontend, page, component, styling, layout, animation, or visual-quality task, or when asked to make an interface look or feel a certain way.
designlang-tokens
Use when styling UI for cal.com — references the extracted design system tokens instead of inventing colors, spacing, or typography.
antv-x6-editor
A skill for creating and troubleshooting interactive diagrams with AntV X6, a JavaScript engine for editors made of connected nodes and lines. It supports diagram types such as flowcharts, dependency graphs, entity-relationship diagrams, and organization charts.
antv-infographic
Create beautiful infographics based on given text content. Use when users request to create infographics.
app-screenshot-debug
Drive the running termio app via AppleScript / System Events to reach a UI state (focus the window, click a sidebar project, a terminal pane, a control), capture a pixel-accurate screenshot of just that window, and read it back for visual analysis — for diagnosing layout / spacing / alignment / 'this looks ugly'…