Make a Skill
A skill is a saved set of rules an AI model loads when the topic fits. They take ten minutes to build and end the constant re-explaining.
I am Geordie.
Essays from George Everitt — published under the name his mother used. On names, places, language, and how things end up the way they are. Writing from Spain by way of everywhere else.
The Four Geordies
I.
The Demographic
Tyneside, England
A Geordie is someone from Tyneside — Newcastle upon Tyne and the surrounding parishes, the north bank of the river. The demonym predates all the others. Strong accent, strong opinions about Newcastle Brown Ale, strong attachment to a very specific strip of northeastern England.
II.
The Memorial
Star Trek: TNG, 1987
Gene Roddenberry named the Enterprise's chief engineer after a real fan — George "Geordie" La Forge Jr., who had muscular dystrophy and died in 1975. The character moves through registers without ceremony: Geordi among friends, La Forge on the bridge, Commander La Forge up the chain.
III.
The Discarded
Gordon Sumner, Wallsend
Gordon Sumner grew up in Wallsend, on the north bank of the Tyne — which made him geographically a Geordie. His bandmates called him Sting because of a yellow-and-black striped sweater. He kept the invented name and walked away from the inherited one. The Geordie didn't make the credits.
IV.
The Inherited
George Everitt, various
My legal name is George. My father was George. My grandfather was George. My mother ran out of patience for the disambiguation project and started calling me Geordie. I'm in my sixties, living in Spain, publishing essays under the name she used in the kitchen. Sting moved away from his inherited Geordie. I've leaned into mine.
Recent Writing
All posts →
What You're Really Giving Up in Every Agreement
One prompt turns an unreadable agreement into a list of what you are giving up. It pays off most on the contracts nobody would ever pay a lawyer to look at — which is nearly all of them.
The Secret to Perfect AI Outputs: Name the Canon
Nearly every established discipline has a canonical reference that already settled the argument you're having with a model. Name it, hand it over, and let the model regularize its own work against a standard instead of your improvised feedback.