# Robots.txt for www.hrvatska.sk

# Standard robots directives
User-agent: *
Allow: /
User-agent: *
Disallow: /admin/
Disallow: /invoice/
Disallow: /counter/
Disallow: /adserver/
Disallow: /temp/
Disallow: /form/
Disallow: /include/
Disallow: /klijent/
Disallow: /kalendar/
Disallow: /linkex/
Disallow: /rezervace/
Disallow: /sitemap-creator/
Disallow: /online/
Disallow: /XML/
Disallow: /www-chorvatska-cz/
Disallow: /ruc.php
Disallow: /filecheck.php
Disallow: /viewforum.php
Disallow: /cklikwww_ptx.php
Disallow: /2new-comments.php
Disallow: /search-2015.php?url=
Disallow: /search-2015.php?latitude=
Disallow: /search-2015.php?app=
Disallow: /advance-search.php
Disallow: /*trid_podle*
Disallow: /*trid_jak*
Disallow: /*feed*
Disallow: /*viewtopic.php*
Disallow: /*[+link+]*
Disallow: /*[+url+]*
Disallow: /[+link+]/
Disallow: /[+url+]/
Disallow: /feed/

User-agent: Bingbot
Crawl-delay: 5
User-agent: BLEXBot
Crawl-delay: 5
User-agent: MSNBot
Crawl-delay: 5
User-agent: MSNBot-Media
Crawl-delay: 5
User-Agent: MJ12bot
Crawl-Delay: 10
User-Agent: Semrushbot
Crawl-Delay: 10
User-Agent: AhrefsBot
Crawl-Delay: 10
User-Agent: AlexaBot
Crawl-Delay: 10
User-agent: OpenGPT
Crawl-delay: 10

User-agent: GPTBot
Crawl-delay: 10

User-agent: ClaudeBot
Crawl-delay: 10
User-agent: Amazonbot
Crawl-Delay: 20
User-agent: AmazonAdBot
Crawl-Delay: 20
User-agent: AmazonProductDiscoverybot
Crawl-Delay: 30

# Content Signals - AI Training
# Restrict large-scale AI training while allowing search engines
Content-Signal: ai-train=no, search=yes, ai-input=no

# Specific agent policies
User-agent: ChatGPT-User
Disallow: /

User-agent: GPTBot
Content-Signal: ai-train=no

User-agent: CCBot
Content-Signal: ai-train=no

User-agent: anthropic-ai
Content-Signal: ai-train=no

User-agent: Claude-Web
Content-Signal: ai-train=no

# Allow beneficial agents for accessibility and indexing
User-agent: Googlebot
Allow: /
Content-Signal: ai-train=sa, search=yes, ai-input=limited

User-agent: Bingbot
Allow: /
Content-Signal: ai-train=sa, search=yes

# Meta information for discovery
Sitemap: https://www.hrvatska.sk/sitemap.xml
Crawl-delay: 1

# API Catalog and Well-Known Resources
# These are discoverable at:
# /.well-known/api-catalog (RFC 9727)
# /.well-known/openid-configuration (OIDC Discovery)
# /.well-known/oauth-authorization-server (RFC 8414)
# /.well-known/oauth-protected-resource (RFC 9728)
# /.well-known/mcp/server-card.json (MCP Discovery)
# /.well-known/agent-skills/index.json (Agent Skills RFC v0.2.0)

# Homepage supports:
# - HTML (default - Accept: text/html)
# - Markdown (Accept: text/markdown) - includes discovery links
# - RFC 8288 Link headers - agent resource discovery