# skls.to — robots policy
#
# We welcome traditional search engines (Googlebot, Bingbot) for discovery.
# We do NOT consent to LLM training or bulk catalog scraping.
#
# Skills metadata is curated, security-reviewed content. Use the public API
# for programmatic access:
#   POST https://skills.agentsandswarms.ai/api/public/recommend
#   GET  https://skills.agentsandswarms.ai/api/skills/community
#
# Bulk scraping of /s/* profile pages is prohibited by our Terms.

# ─── Allow traditional search engines ───
User-agent: Googlebot
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

# ─── Block AI/LLM training crawlers ───
# Anthropic
User-agent: ClaudeBot
Disallow: /

User-agent: Claude-Web
Disallow: /

User-agent: anthropic-ai
Disallow: /

# OpenAI
User-agent: GPTBot
Disallow: /

User-agent: ChatGPT-User
Disallow: /

User-agent: OAI-SearchBot
Disallow: /

# Common Crawl (used by many LLM training sets)
User-agent: CCBot
Disallow: /

# Google AI
User-agent: Google-Extended
Disallow: /

# Perplexity
User-agent: PerplexityBot
Disallow: /

User-agent: Perplexity-User
Disallow: /

# Meta
User-agent: FacebookBot
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: Meta-ExternalFetcher
Disallow: /

# ByteDance
User-agent: Bytespider
Disallow: /

# Apple
User-agent: Applebot-Extended
Disallow: /

# Cohere
User-agent: cohere-ai
Disallow: /

User-agent: cohere-training-data-crawler
Disallow: /

# Mistral
User-agent: MistralAI-User
Disallow: /

# Diffbot
User-agent: Diffbot
Disallow: /

# Amazonbot
User-agent: Amazonbot
Disallow: /

# Other AI scrapers
User-agent: AI2Bot
Disallow: /

User-agent: Timpibot
Disallow: /

User-agent: omgili
Disallow: /

User-agent: ImagesiftBot
Disallow: /

User-agent: PetalBot
Disallow: /

# ─── Default for unknown crawlers ───
# Catalog scraping is prohibited. Use the public API.
User-agent: *
Disallow: /s/
Disallow: /c/
Disallow: /api/
Crawl-delay: 10

Sitemap: https://skls.to/sitemap.xml