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 rampstackco/claude-skills --skill vertical-site-conventionsgit clone --depth 1 https://github.com/rampstackco/claude-skillsWrote 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/rampstackco/claude-skills/vertical-site-conventions)<a href="https://agentmods.dev/skills/rampstackco/claude-skills/vertical-site-conventions"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/vertical-site-conventions/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/rampstackco/claude-skills/vertical-site-conventions"><img src="https://agentmods.dev/badge/skills/rampstackco/claude-skills/vertical-site-conventions.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 | $0.00190 | $0.04001 |
| Opus 5 | $0.00095 | $0.02001 |
| Sonnet 5 | $0.00038 | $0.00800 |
| Haiku 4.5 | $0.00019 | $0.00400 |
Grade A, and why
vertical-site-conventions 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 6d 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 — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vertical Site Conventions
Compose pages and whole sites to the layout, density, and merchandising conventions that make a build read as a credible member of its vertical. Stack-agnostic. Works on any framework that can express server-rendered pages and component composition.
This skill owns vertical-level composition: which modules go where, how dense the page is, how much of the catalog or offering is surfaced, and which paths the navigation serves. It routes the day-to-day visual decisions to design-standards, the aesthetic register to creative-direction, the site-structure modeling to information-architecture, and the component implementation to frontend-component-build. It does not duplicate any of them; it composes their outputs into a vertical-correct site.
It is the build-side counterpart to competitor-experience-audit. The audit measures the field on seven dimensions; this skill builds to those same seven, dimension by dimension. The two are deliberately structured as two sides of one standard so an experience bar produced by the audit maps one-to-one onto what this skill builds.
When to use
- Building a new site in a vertical you have not built in before
- Fixing a build that reads as generic or off-vertical even though it is technically clean (the SEO, accessibility, and component implementation are correct, but the page does not read like its category)
- Building to an experience bar produced by
competitor-experience-audit(the audit-fed path is the intended use) - Adding the merchandising, density, and navigation conventions a site in this category is expected to carry
- Building a showcase or demo where the build must read as its vertical, not as a generic SaaS landing page
When NOT to use
- Day-to-day visual decisions on a known build (use
design-standards) - Defining the brand register or aesthetic from scratch (use
creative-direction,brand-archetype-system,brand-discovery) - Building one component well (use
frontend-component-build) - Modeling site structure and navigation hierarchy from scratch (use
information-architecture) - Building a formal design system or token system (use
design-system) - Auditing the competitive field for what conventions exist (use
competitor-experience-audit; this skill consumes that audit's output, it does not produce it)
What ships with it
11 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.
- references/shape-b2b-manufacturer.md 14 KB
- references/shape-conventions-checklist.md 6.3 KB
- references/shape-directory-marketplace.md 1.5 KB
- references/shape-ecommerce-catalog.md 13 KB
- references/shape-ecommerce-standout.md 1.8 KB
- references/shape-hospitality-experience.md 1.7 KB
- references/shape-hospitality-food.md 11 KB
- references/shape-institution-mission.md 1.9 KB
- references/shape-inventory-listing.md 1.5 KB
- references/shape-local-service-booking.md 11 KB
- references/shape-subscription-app.md 1.5 KB
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.
- 6d ago First seen · 214 lines · 190 tokens per session scan A f7477db56b1a
vertical-site-conventions is a skill published in the GitHub repository rampstackco/claude-skills (832 stars, last pushed yesterday), licensed MIT. It adds 190 tokens to every session and 4,001 once invoked, about $0.0010 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 2026-09-03.
Other skills, from other repositories
popular-web-designs
54 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
interaction-skill
Layer A interaction-mechanics reference anchored to the beui.dev catalog. Stacks on any style skill whenever work adds or changes motion or interaction — micro-interactions, animated components, transitions, gestures, hover/press/state feedback, loading/success/error morphs, 'make it feel alive'. Mandates reading the…
layout-skill
Layer A layout-mechanics reference. Stacks on any style skill when the screen is an app shell, dashboard, settings, list-detail, mail/inbox, or any layout with fixed regions plus a scrolling body — or when a layout breaks under long, empty, or unbroken content. Owns spatial structure and scroll ownership; owns zero…
suede-design
Suede Labs AI design skill for making an interface feel intentional instead of templated: design tokens, color strategy, OKLCH ramps, type scale, fluid type, visual hierarchy, dark mode, spacing, component laws, motion, and source-to-implementation visual QA. Use when asked to design, restyle, polish, or audit a…
frontend-design-review
Design, review, and visually QA web and app interfaces against explicit design laws so shipped screens look intentional instead of generic AI output.
design-loop
Autonomous multi-page site builder using a baton-passing loop. Each iteration reads a task from .design/next-prompt.md, generates a page in HTML/Tailwind, integrates it into the site, verifies visually, then writes the next task to keep the loop alive. Use whenever the user asks to build an entire site autonomously…