Create and publish a new post on the DailyAi blog (this Astro repo at chat.dailyai.studio). Use this whenever Alfred wants to add, write, draft, or publish a post, article, or journal entry here — including "turn this into a post," "write up X for the blog," "new journal entry," or pasting content he wants posted. Handles the frontmatter schema, slug + image conventions, his writing voice, the don't-disparage-sponsors rule, a build check, and the commit/deploy (which also refreshes the chatbot's knowledge base). Trigger this even if he doesn't say "blog" — if he's clearly producing a post for this site, use it so nothing gets skipped.
End-to-end pipeline for turning a finished article into a fully illustrated, published post on the DailyAi blog. Use this whenever Alfred has an article (a draft, a markdown file, or pasted text) and wants images generated AND the post shipped to the site — "illustrate this and publish it," "generate the images and push to the blog," "make the diorama images and post it," or any time both image generation and CMS publishing are needed in one go. This wraps two things: (1) generating images with the Higgsfield MCP in Alfred's miniature diorama style, and (2) the existing `new-dailyai-post` publish flow (frontmatter, image folders, build check, commit/deploy). If only publishing is needed with Alfred supplying his own cover, use `new-dailyai-post` instead.
Make a website discoverable and citable by AI answer engines (ChatGPT, Perplexity, Claude, Google AI overviews) — i.e. GEO / generative engine optimization, the AI-era cousin of SEO. Use this whenever someone wants their site, blog, or docs to show up in AI answers, asks about llms.txt, "getting cited by ChatGPT", AI SEO, structured data for LLMs, or wants to audit/score how AI-ready their site is. Trigger it even if they just say "I want AI to find my site" or "why doesn't ChatGPT know about my blog". Covers the concrete signals (llms.txt, AI-crawler robots, author identity, schema, FAQ markup), how to score a site, the correctness rules that avoid penalties, and how to prompt an AI to do the work.
Add an AI chat/chatbot to a website WITHOUT it getting abused or running up a surprise bill. Use this whenever someone wants to put a chat widget on their site, replace an embedded third-party chatbot (Zapier, Intercom, a vendor widget) with something they control, build a "chat with my blog/docs" feature, or wire a site up to OpenAI/an LLM from the browser. Trigger this even when the person doesn't say "secure" — any time an LLM key would otherwise end up reachable from a public page, this is the pattern to reach for. Covers the architecture (static site → edge worker → LLM), the guardrails that stop abuse (origin lock, bot check, rate limits, hard spend cap), a no-RAG knowledge base built from the site's own content, and how to prompt an AI to build the whole thing for you.