The directory tells you what exists; the blog tells you what to trust. Each post takes one job your agent needs done — debugging, ADRs, payments, testing — reads that capability’s skills end to end, and says which ones to hand your agent and why. A new post lands as new capabilities join the index.
An agent debugging on instinct thrashes. It reads the error, guesses at a cause, edits a line, reruns, guesses again — and three edits later the original symptom is buried under new ones. It "fixes"…
Ask an agent to "write an ADR" with no skill loaded and you get something that looks right and rots fast. It invents a section layout that doesn't match the three-digit-numbered files already sitting…
Ask an agent to "generate an image" or "make a short video" and, working from general knowledge, it will improvise the parts it can't see. It guesses a model id that shifted last quarter, invents an…
Your agent will write you a clean architecture decision record. Point it at a choice — Postgres over Mongo, a modular monolith over microservices — and it picks a template, fills in the context,…
An agent gets handed a simple brief: make a short promotional clip for a product launch. It does the hard part well. It writes a prompt, calls an image model, gets a crisp 4K hero frame. It animates…