Topic
Structured skills, prompts and step sequences used to direct AI coding agents through planning and implementation.
Version 1.0.0 landed as one signed commit into an empty repository, with CI-built binaries. When agents write most of the code, the release becomes the only boundary a reviewer can hold.
Reality
A vendor walkthrough has a coding agent build an endoscopic segmentation app from HoloHub examples, with the CLI as the shared execution surface and named skills as the spec.
Reality
A New Stack column argues AI-generated diffs have made careful review impossible. The automatable half of the job is bug-catching; the half nobody has staffed is knowledge transfer.
Reality
Teams now maintain agent context files line by line because tokens are metered. The same teams left the human wiki to rot for a decade.
Reality
Anthropic says the model now verifies by default, so the double-check lines can go. The four-hundred-line diff behind the green check still has to be read by someone.
Reality
A nine-hour Istio Ambient debugging session ended with an agent recommending its own retirement. The edits were fine. The verification step is where the loop ran out of hypotheses it could see.
Reality
An agent-built resume generator passed generation, rendering and ATS checks while three product requirements were still wrong. None of the three tripped a script.
Reality
A dev.to post describes grill-me, a manually invoked skill that interviews you one question at a time and inspects the repo instead of asking you to recall it, before code exists.
Reality