User-agent: *
Allow: /

# Core search crawlers
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

# AI search/citation crawlers (allow for discoverability)
User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# Training crawlers (blocked by policy)
User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

# Block search result pages with query parameters
Disallow: /search
Disallow: /search?*
Disallow: /job-search?*

# Block template variable URLs (encoded curly braces)
Disallow: /*?q=%7B*
Disallow: /*?*=%7B*

# Block malformed URL patterns (safety net for crawlers)
Disallow: /*https:/*
Disallow: /*http:/*

# Block malformed social media paths
Disallow: /linkedin.com/*
Disallow: /github.com/*

# Block deprecated subdomains (toolkit is deprecated)
# Note: This only works if crawlers respect robots.txt for subdomains
# Server-side 301 redirects are still required

# Canonical domain: fluxresume.io (without www)
# All other subdomains should redirect to this

Sitemap: https://fluxresume.io/sitemap.xml