# timer.ly — crawl policy
# Level A (allow all): the site ships citable schema (Article, FAQPage,
# Organization, Person, Event) specifically so search and AI engines can
# extract and quote it. Both classic search bots and AI bots are welcome.

User-agent: *
Allow: /

# AI / LLM bots — explicitly allowed (matches the * group). Listed so the
# policy is auditable and so any future change is one place to edit.
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: CCBot
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Bytespider
Allow: /

Sitemap: https://www.timer.ly/sitemap.xml

# NLWeb Schema Feeds — points to a structured-data feed index for retrieval-
# augmented agents that ingest JSONL rather than HTML.
Schemamap: https://www.timer.ly/schemamap.xml

# Cloudflare Content-Signals: declare the intended use of crawled content.
# timer.ly is happy to be searched, used as live AI input, and used in training —
# the data is curated for citation and the site itself is the product.
Content-Signal: search=yes, ai-input=yes, ai-train=yes

# AI / LLM discovery files
# - /llms.txt: Markdown index of canonical URLs and locale variants
# - /llms-full.txt: full single-request manifest with URL grammar + holiday data
# - /.well-known/ai.txt: explicit AI training & retrieval policy
# - /.well-known/mcp.json: MCP server discovery
# - /.well-known/agent.json: agent capabilities advertisement
# - /.well-known/agent-card.json: A2A protocol agent card
# - /openapi.json: OpenAPI 3.1 spec
# - /docs: developer docs