seo

How to build an article research workflow on AI agent skills: three core capabilities, editorial patterns to adopt, and a 2026 security audit.

How to wire the avoid-ai-writing skill into an article pipeline as a detect-only gate, plus a lesson from the Stanford study on AI-detector bias.

A WhatsApp CTA with a generic lucide chat icon made visitors hesitate. The fix: an inline brand SVG, a real label, and better button contrast.

Refactoring a long accordion column into a 3-column grid with Show More lists. The trade-off: sliced points never reach the initial DOM Google indexes.

We deleted the daily 6+6 article cap and went event-driven: per-entry cursor, cycle budgets, and a local bge-m3 embedding dedup.

Cloudflare blocks Python's default urllib User-Agent with a 403, even when the API key is correct. Set a custom UA on every agent request to get through.

The embed pipeline now renders tokens inside <pre>/<code> as literal code, degrades to a fallback on broken payloads, and re-highlights Quarto/Pandoc blocks.

Next 16 rejects a sitemap.xml route folder that collides with the metadata convention. I reverted two commits; the old /sitemaps/ rewrite setup was enough.

How I split a Next.js sitemap into 200-URL child files, listed them in robots.txt, and what Google actually reads from a sitemap.