counterpoint: i am pretty sure i can do everything i want text-wise for the rest of my life with just the skills i make and a reliable harness.

agree the prompting style in OP is a little over the top tho lol

Coding agents are unusable without skills and mcp tools

> without skills

This is not even remotely true

It's silly until you realize how similar they are to the weird kludges we apply when we need to get deterministic behavior out of humans. Airline pilots have a number of "skill files" (although they call them checklists) which they open and use on an as-needed basis, and are trained to respect a number of "hook" conditions when specific actions must be immediately performed.

I might not be smart enough to grasp what you're saying because it sounds a little ridiculous to me.

Do you mean the AI will "figure out" how to just do the things we use skills and hooks for today? Do you understand the difference between deterministic and probabilistic behavior and why the difference matters a lot when doing technical tasks?

> Do you understand the difference between deterministic and probabilistic behavior and why the difference matters a lot when doing technical tasks?

Do you understand that there is nothing deterministic in skills and hooks? it is the same text in -> text out.

Hooks are meant to be 'deterministic' because they are only used for executing scripts on a specific step. So, for instance, you can execute your lint on PostEdit so every time it edits a file in your project, the harness runs your linter.

With that said, part of hooks is you can return a json object to the agent which gives it instructions such as stop, continue, etc but those to my understanding are all very explicit constants rather than loosey-goosey prompts you can pass it.

If this person looked into hooks more, they could write a script that would run their project's tests and then tell Claude to stop if tests end via a non-0 exit code.

No, it's not just text in -> text out.

Skills can include scripts, tools, etc.

The entire point of hooks is deterministic responses to signals from the LLM. You run a function in response to some event and the function is given json data that conforms to a specific schema.

ULTRATHINK stop.

Rain dance go!

Yes an no. Some skills are very very tuned to our own workflows. The model providers may come up with some similar alternatives but not always. Also, sometimes you need a solution now and not in three months.

"....using HTML tables as bastardized CSS"

Bro, the gazzilion DIV inside DIV spilled nonsense by all these modern frameworks is driving me crazy. TABLE as bastardized CSS is instant rendering. But hey, you're young, I get it.

And now we finally have CSS grid. Remember centering a div? Haha

Because a deterministic shell around the model gives the best of both worlds. It’s able to achieve its goals but you define what “done” looks like and deterministically enforce checking of that in a way the model can’t cheat its way out of or forget to check on.