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 buildfastwithai/gen-ai-experiments --skill demo-site-buildergit clone --depth 1 https://github.com/buildfastwithai/gen-ai-experimentsWrote 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/buildfastwithai/gen-ai-experiments/demo-site-builder)<a href="https://agentmods.dev/skills/buildfastwithai/gen-ai-experiments/demo-site-builder"><img src="https://agentmods.dev/badge/skills/buildfastwithai/gen-ai-experiments/demo-site-builder/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/buildfastwithai/gen-ai-experiments/demo-site-builder"><img src="https://agentmods.dev/badge/skills/buildfastwithai/gen-ai-experiments/demo-site-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.01183 |
| Opus 5 | $0.00036 | $0.00592 |
| Sonnet 5 | $0.00014 | $0.00237 |
| Haiku 4.5 | $0.00007 | $0.00118 |
Grade A, and why
demo-site-builder 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 12d 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo Site Builder
Turn a repository analysis into ONE self-contained demo.html that a reader can open in any browser and immediately understand what the project does and why it matters. The page both explains and, where feasible, demonstrates the functionality.
Non-negotiables
- Single file. Everything — HTML, CSS, JS — lives in one
demo.html. No build step, nonode_modules, no local asset files. - Works offline by double-click. It must render fully when opened directly from disk (
file://). Only optional enhancements (a web font, a syntax-highlight CDN, an icon set) may load from a CDN, and the page must still look correct if those fail. - Grounded in the analysis. Every feature, number, code sample, and claim comes from the
analyze_repooutput (description, README, languages, topics, stars, commits). Never invent capabilities, benchmarks, or quotes. If the README shows a real usage snippet, reuse it verbatim. - No secrets, no live network calls to the user's services. A demo may simulate behavior in-browser, but must not require API keys or hit private endpoints.
Page structure (in order)
- Hero — project name, a one-line tagline distilled from the description, 2-4 badges (language, license, stars, latest version if any), and two buttons: "View on GitHub" (links to the repo URL) and a "See it in action" anchor to the demo section.
- Problem → Solution — 1-2 short paragraphs: the problem the repo solves and how it solves it. Pulled from the README intro.
- Key features — a responsive grid of 3-6 cards, each with an icon/emoji, a title, and one sentence. Only features evidenced by the analysis.
- Live demo or walkthrough — the centerpiece:
- If the repo is a browser-runnable JS/TS library or produces visual/text output that can be reproduced client-side, embed a genuinely interactive widget (inputs → live result) implemented in inline JS.
- If it is a CLI, backend, or non-browser tool, build a realistic simulated terminal / API playground: the user clicks example commands and sees representative output (clearly labelled "sample output"), driven by canned data taken from the README. Do not fake success of things you cannot actually run.
- Always label simulated output honestly.
- Usage / code example — the real install + minimal usage from the README, in a styled, copy-to-clipboard code block.
- Tech stack — languages (with the analyzed percentages) and notable topics as pills.
- Footer — repo link, license, "Generated launch demo" note, contributor credit.
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.
- 12d ago First seen · 62 lines · 71 tokens per session scan A 4d651499cc9c
demo-site-builder is a skill published in the GitHub repository buildfastwithai/gen-ai-experiments (763 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 1,183 once invoked, about $0.0004 per session on Opus 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 2026-08-30.
Other skills, from other repositories
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
create-site
Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…
prototype-web
A clickable, high-fidelity web product prototype with navigation, a hero section, feature cards, steps, social proof, and optional pricing. It is designed to resemble a finished landing page while remaining a prototype.
menu-transitions-rtl
Animate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless…