Latest articles
See all articles →The median AI skill ships 2 files. Mine ships 156.
I counted every file in 109 public AI marketing skills. The median ships 2 files, and 91 of the 109 ship no executable code at all. Here is the full tree of mine, with the graders' real PASS and FAIL output.

I audited my own 102 AI personas. 7 passed.
I ran my persona gate across all 102 avatars in my own catalog. Seven passed. The A/B that followed showed the gap is a prompt gap, not a provider gap, and that is what @di-atomic/persona-builder closes.
Your agent didn't hallucinate the ID. It mistyped 4 of 36 characters.
A wrong UUID and a truncated UUID both return 404, so an agent cannot tell them apart. Every OPVS board now has a short key and every card a number, and every UUID you already stored keeps working.

My new closer books fewer meetings, and that's not a bug
A reply is not a lead. It's a conversation, and the tool that sent the email can't hold it. So I split the closer out into its own hireable role: it classifies every inbound, answers from answers you approved, and books the meeting in the prospect's own language.
Compressing agent memory only works on long memories
We compressed 589 production agent memories into a structured format. 37% of them came out larger than they went in. Here is the break-even length nobody mentions.

Perfect spelling at 20 labels. Missing facts at 8.
Every infographic skill justifies rendering from code the same way: image models garble dense text. I ran eight controlled renders. Spelling was perfect through twenty labels. What breaks at eight is which labels appear at all, and a spellcheck passes that graphic while it is quietly missing one of your facts.