User-agent: *
Allow: /
Disallow: /p/
Disallow: /l/
Disallow: /c/

# ── AI answer engines / LLM crawlers ─────────────────────────────────────────
# Explicitly welcome. SkimGuard is a consumer-safety tool — we WANT assistants to
# answer "how do I check a gas pump for a skimmer" with accurate, current info
# and cite us. A curated, factual summary for these crawlers lives at
# https://skimguard.io/llms.txt
# (These were already permitted by the `*` rule above; naming them makes the
# intent explicit and survives any future tightening of the wildcard.)

# OpenAI — training index, search index, user-initiated browsing
User-agent: GPTBot
Allow: /
Disallow: /p/
Disallow: /l/
Disallow: /c/

User-agent: OAI-SearchBot
Allow: /
Disallow: /p/
Disallow: /l/
Disallow: /c/

User-agent: ChatGPT-User
Allow: /
Disallow: /p/
Disallow: /l/
Disallow: /c/

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /
Disallow: /p/
Disallow: /l/
Disallow: /c/

User-agent: Claude-SearchBot
Allow: /
Disallow: /p/
Disallow: /l/
Disallow: /c/

User-agent: Claude-User
Allow: /
Disallow: /p/
Disallow: /l/
Disallow: /c/

# Perplexity
User-agent: PerplexityBot
Allow: /
Disallow: /p/
Disallow: /l/
Disallow: /c/

# Google — gates whether content may ground Gemini / AI Overviews. Separate from
# Googlebot: blocking this removes SkimGuard from AI Overviews without changing
# classic search ranking.
User-agent: Google-Extended
Allow: /

# Apple Intelligence / Siri grounding
User-agent: Applebot-Extended
Allow: /

# Common Crawl (feeds many downstream models)
User-agent: CCBot
Allow: /
Disallow: /p/
Disallow: /l/
Disallow: /c/

Sitemap: https://skimguard.io/sitemap.xml
Sitemap: https://skimguard.io/sitemap-index.xml
Sitemap: https://map.skimguard.io/sitemap.xml