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 sergekostenchuk/ui-ux-agent-skill-system --skill marketing-site-skillgit clone --depth 1 https://github.com/sergekostenchuk/ui-ux-agent-skill-systemWrote 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/sergekostenchuk/ui-ux-agent-skill-system/marketing-site-skill)<a href="https://agentmods.dev/skills/sergekostenchuk/ui-ux-agent-skill-system/marketing-site-skill"><img src="https://agentmods.dev/badge/skills/sergekostenchuk/ui-ux-agent-skill-system/marketing-site-skill/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/sergekostenchuk/ui-ux-agent-skill-system/marketing-site-skill"><img src="https://agentmods.dev/badge/skills/sergekostenchuk/ui-ux-agent-skill-system/marketing-site-skill.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 | $0.00092 | $0.00700 |
| Opus 5 | $0.00046 | $0.00350 |
| Sonnet 5 | $0.00018 | $0.00140 |
| Haiku 4.5 | $0.00009 | $0.00070 |
Grade A, and why
marketing-site-skill 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.
Marketing Site Skill
Use this specialist for public-facing pages where the first viewport, product/place/person signal, conversion path, media quality, metadata, and responsive behavior matter.
Operating Modes
build: create or refactor a marketing/public page.audit: review a page for conversion, metadata, responsive behavior, and visual clarity.metadata: inspect title, description, canonical, Open Graph, Twitter, headings, and social preview basics.verify: run local checks and distinguish evidence from manual review.
Required Workflow
- Read references/hero-first-viewport.md before designing the top of the page.
- Read references/conversion-framework.md for CTA and proof decisions.
- Read references/metadata-checklist.md when source files or HTML are available.
- Use assets/landing-brief.template.md and assets/metadata.template.json when producing durable page briefs or metadata specs.
- Apply
../../shared/privacy-policy.mdbefore using external images, AI page builders, or cloud tools. - If source files are available, run scripts/lint_metadata.py or report why it was skipped.
- If a URL is available, run scripts/responsive_smoke_test.mjs or report why it was skipped.
- Return
Ran,Skipped,Planned, andManualsections.
Design Doctrine
- The first viewport must show the product, place, offer, brand, object, or person clearly.
- Do not hide the real subject inside a decorative card or generic gradient.
- Use real or generated bitmap media when a visual signal is needed.
- Keep CTA hierarchy obvious and avoid many visually equal primary actions.
- Keep mobile text readable and avoid overlap, horizontal overflow, and viewport-scaled font tricks.
Tool Contracts
- Metadata lint:
python3 scripts/lint_metadata.py --root "$PROJECT_ROOT" --out reports/metadata.json. - Responsive smoke:
node scripts/responsive_smoke_test.mjs --url "$URL" --out reports/visual-smoke. - Optional cloud tools require explicit approval and cannot be validation evidence by themselves.
What ships with it
12 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.
- agents/openai.yaml 398 B
- assets/animation-presets.md 422 B
- assets/landing-brief.template.md 191 B
- assets/metadata.template.json 263 B
- evals/evals.json 1.2 KB
- references/conversion-framework.md 733 B
- references/hero-first-viewport.md 722 B
- references/metadata-checklist.md 582 B
- references/performance-budget.md 462 B
- references/responsive-storytelling.md 561 B
- scripts/lint_metadata.py 2.4 KB runs code
- scripts/responsive_smoke_test.mjs 1.4 KB runs code
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 · 92 tokens per session scan A 2303230b0b3d
marketing-site-skill is a skill published in the GitHub repository sergekostenchuk/ui-ux-agent-skill-system (23 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 92 tokens to every session and 700 once invoked, about $0.0005 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…