# robots.txt for inakm.github.io
# Anjani Kumar Mishra - Finance & Analytics Portfolio

# Allow all standard search engines full access
User-agent: *
Allow: /
Disallow: /v0/
Disallow: /testdata/
Disallow: /Data/testdata-skylimit/
Disallow: /Data/SQL_Proj/
Disallow: /Data/RMM/
Disallow: /Data/VEVOi/
Disallow: /myprojects/ACCA-FM/
Disallow: /todo

# Explicitly allow AI search crawlers for AI discovery
User-agent: GPTBot
Allow: /
Allow: /page/projects/
Allow: /llms.txt
Allow: /llms-full.txt
Disallow: /v0/
Disallow: /testdata/

User-agent: ClaudeBot
Allow: /
Allow: /page/projects/
Allow: /llms.txt
Allow: /llms-full.txt
Disallow: /v0/
Disallow: /testdata/

User-agent: PerplexityBot
Allow: /
Allow: /page/projects/
Allow: /llms.txt
Allow: /llms-full.txt
Disallow: /v0/
Disallow: /testdata/

User-agent: Google-Extended
Allow: /
Allow: /page/projects/
Allow: /llms.txt
Disallow: /v0/
Disallow: /testdata/

# Bing Webmaster Guidelines - explicit rules for Bingbot
User-agent: Bingbot
Allow: /
Disallow: /v0/
Disallow: /testdata/

# Allow archive.org to cache resources
User-agent: ia_archiver
Allow: /

# Crawl rate optimization for GitHub Pages
Crawl-delay: 2

# Sitemaps
Sitemap: https://inakm.github.io/sitemap.xml