# Signature Garden - robots.txt
# Website: https://signaturegarden.ca

# Default: allow all crawlers
User-agent: *
Allow: /
Disallow: /config/
Disallow: /search/
Disallow: /account/
Disallow: /api/
Allow: /api/ui-extensions/
Disallow: /static/
Disallow: /*?*author=*
Disallow: /*?*tag=*
Disallow: /*?*month=*
Disallow: /*?*view=*
Disallow: /*?*format=*

# Keep llms.txt crawlable for AI agents but out of the search index
Noindex: /llms.txt

# AI / LLM crawlers - allow content discovery, exclude legal pages
User-agent: GPTBot
User-agent: ChatGPT-User
User-agent: OAI-SearchBot
User-agent: CCBot
User-agent: anthropic-ai
User-agent: Claude-Web
User-agent: ClaudeBot
User-agent: Google-Extended
User-agent: PerplexityBot
User-agent: FacebookBot
User-agent: Meta-ExternalAgent
User-agent: cohere-ai
User-agent: Bytespider
Allow: /
Disallow: /privacy-policy.html
Disallow: /terms-of-use.html

# Google Ads bots
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: AdsBot-Google-Mobile-Apps
Allow: /

# Crawl delay for heavy bots
User-agent: Baiduspider
Crawl-delay: 10

# Sitemap location
Sitemap: https://signaturegarden.ca/sitemap.xml