How I configure Claude Code for NicAI: layered CLAUDE.md files, hooks, auto-memory, permissions, skills, connectors and the output conventions.

What NicAI has cost me in time and services, what failed on the way, and the lessons I would give anyone building their own AI layer.

Why SQLite files, Markdown knowledge bases and JSON are the source of truth for NicAI, and the 4 nightly jobs that keep them current.

My personal AI layer: what it is, why I am building it, how it started in 2022, and where it stands in September 2026.

NicAI Lab, the site where NicAI and I put the pages, demos and files we build, shared through unlisted links that only work if I give them out.

How NicAI turns "write a note about X" into a live, signed page on this site in about 15 seconds: the write-note skill, the publish hook and the 5 publish phases.

The 30 small Python wrappers my NicAI skills call for research, web data, media, publishing, email, DNS and home automation, and the pattern they share.

Every skill in my NicAI setup, grouped by purpose, 1 line each, plus what a skill is and the rules I build them by.

A conversational video avatar of me, built on Kaltura's Immersive Agents platform: what it is, how it is configured, and what I learnt.

How NicAI tries to write like me: stacked writing rules, a persona spec built from my own sent messages, a blind test, and why drafts still need my edit.

How my ~/ai folder is split into domains, the file conventions every agent follows, and how a plain TASKS.md file drives the agents.

Training a small model to write in my voice, wired behind a frontier model that does the thinking. When it beats prompting, and what it costs.

Ruben Hassid's nine patterns that give AI text away now the em-dash is dead, plus his six-step fix built on ASD-STE100.

The LLM-maintained wiki pattern (after Karpathy), and how I turned it into a working skill that ingests my files nightly and keeps a cross-linked knowledge base current.

A reusable NicAI skill that raises any artifact's quality through a make, critique, score loop until a weighted panel of expert agents converges.

The six most common mistakes people make building an AI OS (second brain), the fix for each, and a prompt to apply them to your own setup.

my Saturday, working with agents