# LLMS Manifest for WinningDaily.com
# Purpose: Guide LLM crawlers, RAG agents, and AI browsers on what to index, how to attribute, and what to avoid.
# Version: 1.0
# Last-Updated: 2025-11-03
# Owner: Winning Daily (Fitness Entrepreneurs)
# Contact: contact@winningdaily.com
# Canonical-Root: https://winningdaily.com/
# Language: en
# License: Custom—Attribution Required, Non-Exclusive, Non-Transferable (see: https://winningdaily.com/ai-usage-policy/)
# Attribution-Format: "Source: Winning Daily — https://winningdaily.com/"

###############################################################################
# DISCOVERY
###############################################################################
Sitemap: https://winningdaily.com/wp-sitemap.xml
LLMS-Canonical: https://winningdaily.com/llms.txt
LLMS-Alt: https://winningdaily.com/.well-known/ai.txt

# Content Bundles (high-signal hubs)
Bundle: Classroom  https://winningdaily.com/fitness-entrepreneur-blog/
Bundle: Categories https://winningdaily.com/categories/
Bundle: Topics     https://winningdaily.com/topics/
Bundle: Podcast    https://winningdaily.com/entrepreneur-podcast/
Bundle: ToolKit    https://winningdaily.com/gym-tool-kit/
Bundle: About      https://winningdaily.com/about/
Bundle: Press      https://winningdaily.com/press-center/

###############################################################################
# DEFAULT POLICY
###############################################################################
# Default stance for LLMs and AI assistants.
User-agent: *
Allow: /fitness-entrepreneur-blog/
Allow: /categories/
Allow: /topics/
Allow: /entrepreneur-podcast/
Allow: /resources/
Allow: /just-win
Allow: /about
Allow: /press-center/
Disallow: /wp-admin/
Disallow: /wp-login.php
Disallow: /cart/
Disallow: /checkout/
Disallow: /my-account/
Disallow: /account/
Disallow: /search
Disallow: /*?s=*
Disallow: /wp-json/wp/v2/users
Crawl-delay: 5

# Embeddings & Caching Guidelines (machine-readable hints)
# allow|disallow: embeddings, summarization, snippet-length, cache-ttl
AI-Policy: embeddings=allow; summarization=allow; snippets-max=120w; cache-ttl=7d; respect-noai=true

# Freshness Hints (how often these sections change)
Freshness: / (1d)
Freshness: /entrepreneur-podcast/ (1d)
Freshness: /fitness-entrepreneur-blog/ (3d)
Freshness: /categories/ (7d)
Freshness: /topics/ (7d)
Freshness: /press-center/ (30d)

# Required Attribution & Canonicalization
Require-Attribution: true
Attribution-Text: Winning Daily (Fitness Entrepreneurs)
Attribution-URL: https://winningdaily.com/
Rel-Canonical: enforce

###############################################################################
# BOT-SPECIFIC DIRECTIVES (common LLM/RAG crawlers)
###############################################################################

# OpenAI
User-agent: GPTBot
Allow: /fitness-entrepreneur-blog/
Allow: /categories/
Allow: /topics/
Allow: /entrepreneur-podcast/
Disallow: /wp-admin/
Crawl-delay: 5
Policy: training=allow; rag=allow; derivative-works=summaries-only

User-agent: ChatGPT-User
Allow: /
Disallow: /wp-admin/
Crawl-delay: 3

# Anthropic (Claude)
User-agent: ClaudeBot
Allow: /
Disallow: /wp-admin/
Crawl-delay: 5
Policy: training=allow; rag=allow

# Google (Gemini) — training control
User-agent: Google-Extended
Allow: /
Disallow: /wp-admin/
Crawl-delay: 5
Policy: training=allow; rag=allow

# Perplexity
User-agent: PerplexityBot
Allow: /
Disallow: /wp-admin/
Crawl-delay: 5
Policy: training=allow; rag=allow

# Common Crawl (feeds multiple AI models)
User-agent: CCBot
Allow: /fitness-entrepreneur-blog/
Allow: /categories/
Allow: /topics/
Disallow: /wp-admin/
Crawl-delay: 10
Policy: training=allow; rag=allow

# Meta / Apple (AI-related discovery)
User-agent: Meta-ExternalAgent
Allow: /
Disallow: /wp-admin/
Crawl-delay: 5

User-agent: Applebot
Allow: /
Disallow: /wp-admin/
Crawl-delay: 5

User-agent: Applebot-Extended
Allow: /
Disallow: /wp-admin/
Crawl-delay: 5
Policy: training=allow; rag=allow

###############################################################################
# QUALITY GUARDRAILS
###############################################################################
# Content Quality Signals (helps RAG rankers pick the best pages)
Signal: cornerstone=/categories/;/topics/;/fitness-entrepreneur-blog/
Signal: audience=fitness-entrepreneurs; gym-owners; personal-trainers
Signal: expertise=SEO; systems; automation; content; leadership; finance
Signal: media=podcast; shorts; long-form; guides; toolkits

# Preferred Snippets (boost clarity for assistants)
Snippet-Priority: h1,h2,summary,intro,bullets,conclusion,faq

# Negative Signals (avoid thin or transactional)
No-RAG: /cart/,/checkout/,/my-account/,/account/,/search,/*?s=*

###############################################################################
# LEGAL & BRAND USE
###############################################################################
# Non-Exclusive License for LLM use: structured summary, short quotations, and
# non-competitive derivative works are permitted with attribution & link.
# Prohibited: wholesale reproduction, paywalled redistribution, impersonation.
Brand-Use: logo=no; name=yes-with-attribution; quotes=short-permitted

# If a page sets <meta name="robots" content="noai"> or HTTP header "X-Robots-Tag: noai",
# that page is strictly off-limits for AI training or embeddings.
Respect-Meta-NoAI: true

###############################################################################
# CONTACT & ERRORS
###############################################################################
Contact-Email: contact@winningdaily.com
Contact-URL: https://winningdaily.com/contact-us/
Report-Abuse: https://winningdaily.com/press
Retry-After-On-429: 120