Kubik AI LLM Content Generator (.md & llms.txt)

Kubik AI LLM Content Generator converts real, fully rendered WordPress pages into clean, AI-ready Markdown endpoints that can be consumed by large language models, RAG pipelines, and AI-powered search tools.

Unlike traditional exporters that rely on raw post content, this plugin captures the final rendered HTML output of your site, intelligently removes non-content UI elements, and produces structured Markdown optimized for machine understanding.

The plugin automatically strips navigational and interactive noise such as menus, navigation bars, language switchers, social/share blocks, search forms, and newsletter widgets — leaving only meaningful, semantic content.

In addition, the plugin generates an llms.txt file — a curated, human-readable index of your AI-ready content, similar in spirit to a sitemap, but designed specifically for AI systems.

Kubik AI is built for developers, content owners, and teams preparing datasets for LLMs, AI search engines, and retrieval-augmented generation (RAG) systems.

Features:

✅ Metadata block (URL, language, last updated) on Markdown and llms.txt output
✅ Markdown output for pages at /slug.md
✅ Optional Markdown output for posts
✅ Direct link to generated llms.txt from the admin UI
✅ Automatic or manual llms.txt generation
✅ Clean content extraction without theme layout
✅ Removal of language switchers and common UI widgets (social, search, newsletters)
✅ Correct handling of sites with a custom homepage (home ≠ /)
✅ Proper taxonomy and category URL output
✅ Removal of duplicate H1 headings
✅ Conversion of links, headings, and lists
✅ Content summaries from SEO meta, excerpts, or content
✅ Admin settings with exclusions and content search

The plugin is designed for AI integration, dataset preparation, and LLM-friendly content delivery.

Both /slug.md endpoints and the generated llms.txt index include a metadata block directly under the page title:

URL: canonical page or site URL
Language: WordPress site locale (e.g. en_US)
Last Updated: content last-modified date (YYYY-MM-DD)

For individual Markdown pages, URL and Last Updated reflect the specific post or page. For llms.txt, URL is the site home URL and Last Updated is the most recent modified date among indexed pages and posts.