# Default rule: Allow all crawlers to access the website
User-agent: *
Allow: /

# Disallow internal and administrative paths
# These paths contain technical files and should not be indexed
Disallow: /api/
Disallow: /_nuxt/
Disallow: /admin/
Disallow: /.well-known/
Disallow: /storybook/

# Security: Block common exploit paths
# These are commonly targeted by malicious crawlers and should not be accessed
Disallow: /.env
Disallow: /.git/
Disallow: /wp-
Disallow: /wordpress/
Disallow: /backup/
Disallow: /phpmyadmin/
Disallow: /cgi-bin/

# Explicitly allow important public assets for SEO and indexing
# These assets are important for search engines and AI crawlers to understand the website
Allow: /fonts/
Allow: /favicon.ico
Allow: /favicon.svg
Allow: /apple-touch-icon.png
Allow: /favicon-*.png
Allow: /site.webmanifest
Allow: /robots.txt
Allow: /sitemap_index.xml

# Specific rules for major search engines
# Google Search Engine
User-agent: Googlebot
Allow: /
Crawl-delay: 0

# Google Image Search Bot
User-agent: Googlebot-Image
Allow: /

# Microsoft Bing Search Engine
User-agent: Bingbot
Allow: /
Crawl-delay: 0

# Yandex Search Engine (for international SEO)
User-agent: Yandex
Allow: /
Crawl-delay: 1

# AI and LLM Crawlers
# ChatGPT, Perplexity, and other AI crawlers
User-agent: GPTBot
Allow: /
Crawl-delay: 1

User-agent: ChatGPT-User
Allow: /
Crawl-delay: 1

User-agent: CCBot
Allow: /
Crawl-delay: 1

User-agent: anthropic-ai
Allow: /
Crawl-delay: 1

User-agent: Claude-Web
Allow: /
Crawl-delay: 1

# Sitemap location
# This tells crawlers where to find the sitemap with all available pages
Sitemap: /sitemap.xml