azerbaijan-website-build

azerbaijan-website-build is a skill for Claude Code, Codex from mhrsdev/AI-Agent-Skills-Library. It costs 54 tokens per session (7,454 once invoked), scanned A, original, MIT.

A workflow for building websites for Azerbaijani businesses in Azerbaijani, Russian, and English. It uses Astro and Tailwind CSS and includes brand, content, accessibility, and language-routing guidance.

In plain words
What is it for?
Use it to gather business information, create multilingual pages, add language switching and search metadata, use suitable fonts and images, and deploy the finished site.
Why use it?
It provides a consistent way to create one site that serves three language audiences. It also helps avoid broken translations, missing language links, and poor support for Latin and Cyrillic text.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to gather business information, create multilingual pages, add language switching and search metadata, use suitable fonts and images, and deploy the finished site.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mhrsdev/ai-agent-skills-library/07-azerbaijan-website-build
Install

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.

Any agent
npx skills add mhrsdev/AI-Agent-Skills-Library --skill 07-azerbaijan-website-build
Clone the repo
git clone --depth 1 https://github.com/mhrsdev/AI-Agent-Skills-Library

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for azerbaijan-website-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/mhrsdev/ai-agent-skills-library/07-azerbaijan-website-build/github.svg)](https://agentmods.dev/skills/mhrsdev/ai-agent-skills-library/07-azerbaijan-website-build)
Your own site
<a href="https://agentmods.dev/skills/mhrsdev/ai-agent-skills-library/07-azerbaijan-website-build"><img src="https://agentmods.dev/badge/skills/mhrsdev/ai-agent-skills-library/07-azerbaijan-website-build/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.

agentmods 80×15 button for azerbaijan-website-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/mhrsdev/ai-agent-skills-library/07-azerbaijan-website-build"><img src="https://agentmods.dev/badge/skills/mhrsdev/ai-agent-skills-library/07-azerbaijan-website-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 7,454 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00054 $0.07454
Opus 5 $0.00027 $0.03727
Sonnet 5 $0.00011 $0.01491
Haiku 4.5 $0.00005 $0.00745

Measured 8d ago against content hash 03d0da999bc2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

azerbaijan-website-build 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/contrast-check.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

organized-skills/website-business-builds/07-azerbaijan-website-build/SKILL.md · 831 lines

How it starts

The opening of the file, as written. The whole thing — 831 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Azerbaijan Website Build

Build a stunning, $75K+ agency-quality website from scratch for an Azerbaijani business. Every site is tri-lingual (Azerbaijani, Russian, English) with a language switcher, built on Astro 5.x + Tailwind CSS v4, and deployed to Vercel.

Quick Reference

Item Value
Tech stack Astro 5.x, Tailwind CSS v4 (Vite plugin), npm
Languages Azerbaijani (primary), Russian, English
i18n approach Directory-based: /az/, /ru/, /en/
Images Unsplash (local), scraped assets, NanoBanana 2
Fonts @fontsource, must support Latin Extended + Cyrillic
Deploy GitHub repo → Vercel
Project location ~/Azerbaijan/projects/<slug>/
Quality bar Apple/Stripe/Linear tier. AI Slop Test must pass.

Reference Files

Read these before building — they contain non-negotiable rules and technical specs:

  • references/design-rules.md — Visual design rules, banned fonts/colors/layouts, component architecture
  • references/accessibility-spec.md — WCAG AA requirements, contrast minimums, keyboard nav
  • references/i18n-spec.md — Astro i18n routing, LanguageSwitcher component, hreflang, JSON strings
  • references/interview-questionnaire.md — Structured interview for businesses with no online presence
  • references/azerbaijani-design-guide.md — Cultural design considerations, font coverage, image selection
  • references/nano-banana-logo.md — Logo generation via NanoBanana 2 / Gemini API

Project Structure

~/Azerbaijan/projects/<slug>/
├── BUSINESS_PROFILE.md         # Phase 1 output
├── BRAND_BRIEF.md              # Phase 2 output
├── SITE_PLAN.md                # Phase 3 output
├── COPY_CHANGES.md             # Phase 6 output
├── QA_REPORT.md                # Phase 7 output
├── scraped/
│   ├── website/                # Crawled website content (markdown)
│   ├── instagram/              # Instagram data
│   ├── facebook/               # Facebook data
│   └── assets/                 # Downloaded images, logos
│       ├── logos/
│       ├── photos/
│       └── gallery/
└── site/                       # Astro project
    ├── src/
    │   ├── layouts/
    │   │   └── BaseLayout.astro
    │   ├── pages/
    │   │   ├── index.astro     # Redirects to /az/
    │   │   ├── az/             # Azerbaijani pages
    │   │   ├── ru/             # Russian pages
    │   │   └── en/             # English pages
    │   ├── components/
    │   │   ├── Header.astro
    │   │   ├── LanguageSwitcher.astro
    │   │   ├── Footer.astro
    │   │   ├── Hero.astro
    │   │   └── ...sections
    │   ├── content/
    │   │   └── i18n/
    │   │       ├── az.json
    │   │       ├── ru.json
    │   │       └── en.json
    │   ├── utils/
    │   │   └── i18n.ts
    │   ├── styles/
    │   │   └── global.css
    │   └── assets/
    │       └── images/
    ├── public/
    │   ├── images/
    │   ├── favicon.svg
    │   └── robots.txt
    ├── astro.config.mjs
    └── package.json

Read the full file on GitHub · 831 lines

Files

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.

Changes

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.

  1. 8d ago First seen · 831 lines · 54 tokens per session scan A 03d0da999bc2

Subscribe to this mod's changes

azerbaijan-website-build is a skill published in the GitHub repository mhrsdev/AI-Agent-Skills-Library (6 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 7,454 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

web-clone

URL-driven website cloning with visual + functional verification.

IAPro-Community/Orquestrador-Maestro · 13 tokens

skill-premium-web-experience

Use for creating, redesigning, or transforming websites into premium, cinematic, conversion-focused web experiences with visual research, storytelling, scroll-driven interaction, responsive design, motion, performance, accessibility, and visual QA.

IAPro-Community/Orquestrador-Maestro · 49 tokens

skill-frontend-ux-guardrails

Use as a frontend UX quality gate for responsive behavior, overflow, accessibility, interaction usability, touch targets, typography, layout stability, mobile behavior, focus states, reduced motion, and final visual validation.

IAPro-Community/Orquestrador-Maestro · 49 tokens

skill-impeccable

Orquestra melhorias de frontend inspiradas no Impeccable a partir de pedidos conversacionais de design, UX, acessibilidade, responsividade, tipografia, layout, cor, motion, clareza, hardening e polish.

IAPro-Community/Orquestrador-Maestro · 53 tokens

skill-modern-ui-patterns

Use for professional frontend UI implementation with modern component composition, interaction states, forms, tables, cards, navigation, dashboards, SaaS surfaces, and maintainable design-system consistency.

IAPro-Community/Orquestrador-Maestro · 41 tokens

web-artifacts-builder-jp

A guide for building responsive, single-file HTML web applications with Japanese interface components and language settings. It is intended for requests involving Japanese web artifacts or tools.

LinkX-Japan/ai-souken-workflows · 64 tokens