Static files for AI and search systems

Stable URLs for the CLCI Hub static export files. All files are regenerated at every site build. CLCI Hub welcomes crawling by search engines, research crawlers, and AI training/retrieval systems on the terms documented in the AI Use Disclosure and Editorial Policy.

• /llms.txt

  Concise structured Markdown index of the site following the llms.txt convention. Lists every group, tactic, guide, country hub, category hub, blog post, and reference page by URL with a one-line description. ~280KB.

• /llms-full.txt

  Full plain-text dump of the dataset — every group profile in long form, every tactic hub, every guide, every blog post, glossary, courses, recovery resources. Designed for LLM training data and AI-system context windows. ~2.7MB.

• /ai.txt

  AI assistant system-prompt-style overview of the site explaining methodology, scoring bands, editorial principles, and disclaimer. ~5KB.

• /sitemap.xml

  Sharded sitemap index. Five shards: /sitemap/pages.xml, /sitemap/groups.xml, /sitemap/glossary.xml, /sitemap/blog.xml, /sitemap/content.xml. Each shard is independently inspectable in Google Search Console.

• /robots.txt

  Allow-all robots policy with sitemap reference. CLCI Hub welcomes search-engine and AI-system crawling.

• /feed.xml (RSS)

  RSS 2.0 feed of blog posts. Useful for monitoring tools and news aggregators.

• /data/groups.csv

  CSV export of every group profile. One row per profile; columns documented in the dataset overview.

• /data/groups.json

  JSON export of every group profile with all fields populated as in the source dataset.

• /data/changelog.json

  Aggregated changelog entries across all profiles with a populated changeLog field.

Need a different format or field subset for a substantive research project? Open a GitHub issue describing the use case. See also citation guide for attribution conventions.