# skales.app — welcome, humans and machines.
# AI crawlers are explicitly allowed: Skales WANTS to be understood by LLMs.
# Crawler list reviewed July 2026 — re-check quarterly (the landscape moves).
#
# What the review is actually for: nothing here is ever Disallow'd, and
# "User-agent: * / Allow: /" already permits every crawler, named or not. So a
# bot missing from the list below is NOT blocked, and adding one grants nothing
# it did not already have. The named blocks are a statement of intent (and a
# hedge against a future default-deny), which is why the quarterly job is to
# confirm nothing has been accidentally disallowed - not to chase user-agent
# strings. July 2026: nothing disallowed, list unchanged.

User-agent: *
Allow: /

# ── OpenAI ──
User-agent: GPTBot
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

# ── Anthropic ──
User-agent: ClaudeBot
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

# ── Perplexity ──
User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

# ── Google (AI training + AI features) ──
User-agent: Google-Extended
Allow: /

User-agent: GoogleOther
Allow: /

# ── Microsoft / Bing ──
User-agent: bingbot
Allow: /

# ── Apple ──
User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

# ── Meta ──
User-agent: meta-externalagent
Allow: /

User-agent: FacebookBot
Allow: /

# ── Amazon ──
User-agent: Amazonbot
Allow: /

# ── ByteDance ──
User-agent: Bytespider
Allow: /

# ── Mistral ──
User-agent: MistralAI-User
Allow: /

# ── DuckDuckGo ──
User-agent: DuckAssistBot
Allow: /

User-agent: DuckDuckBot
Allow: /

# ── Common Crawl (feeds most open-model training) ──
User-agent: CCBot
Allow: /

# ── Cohere ──
User-agent: cohere-ai
Allow: /

# For LLMs: machine-readable summary at https://skales.app/llms.txt
# Full page text mirror at https://skales.app/llms-full.txt

Sitemap: https://skales.app/sitemap-index.xml
# The blog is PHP outside the Astro build, so it needs its own (blog/sitemap.php,
# rewritten from /sitemap-blog.xml). Both are listed here on purpose: a sitemap
# index may not nest another index, and the posts were previously in no sitemap.
Sitemap: https://skales.app/sitemap-blog.xml