Hacker News Reader

Comment by estetlinus | Hacker News Reader

That’s a bold assumption. I would be surprise if they even read those skills (I don’t know anyone actually reading SKILL files)

View on HN

I do, I like to know how badly my agents' context is wasted and what unexpected side effects to watch for (like, "always start with ${clitool} --help" == always waste few hundred tokens when even touching the skill; or instructions asking it to do something that generalize into stupid thing in larger context).

If those skills were unreadable, however, that would imply proper engineering - like e.g. the skills themselves being an output of iterative RL over set of evals.

I don't think unreadable skills implies proper engineering at all. It's just as or more likely that they're the result of a blind iterative process with no clear improvement signal. (And whether iterative RL over a set of evals is actually proper engineering here is another question...)

> And whether iterative RL over a set of evals is actually proper engineering here is another question...

I'd put it like this: regardless of the merit of how they're applied, it would at least demonstrate possession of the advanced skills expected of experienced software engineers.

I generate them using LLMs, but optimize them by manually removing chunks or rearranging the order of the instructions. It works well.

I had more success starting from scratch. Especially claude's skill-creator skill, it micromanages, which is in fact worse for 5+ models than just leaving the instructions out and crossing your fingers.

Start from scratch, do some test runs, find the bugs, add the minimal possible text to avoid the bug, iterate

You can get 95% of my impl workflow skill by just telling Claude "split the work into slices and use ephemeral subagents" and the other 5% takes like 10x as much text to achieve

Reply on news.ycombinator.com