Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Ask HN: How do you manage skills files?

news.ycombinator.com

Post reply on HN
Print view View original

151–160 of 292 posts

Re: Ask HN: How do you manage skills files?

#151

Post by jbeninger »

stanmancan wrote: post #47
pletnes wrote: post #29

Earlier quoted context omitted.

I make skills for «this is how I like to do things in this company / project». Query test database, git branch names, commit message style, which cloud things can be inspected like logs etc. I don’t see the point in trying to teach the models things that is in the documentation of git, python, what have you. They already know.

Isn’t that what the agents.md in your project is for?

It's possible I invented skills before they were common. I've always had some instructions in agents.md that are something like "when working with typescript, read prompts/conventions.ts.md, when working with our fooBar module, read prompts/foobar.md"

I'm not sure if this differs greatly from skills. Maybe my wording makes these "skills" less likely to be read at the correct times, but I haven't seen an issue.

Re: Ask HN: How do you manage skills files?

#153

Post by Narciss »

avaer wrote: post #105

Skills are mostly snake oil, the way people use them (the aspiration to download kung foo from a celebrity). There was a time when maybe it mattered (last year), but with good repos and good prompts today's agents can find exactly what they need without any skills. "Skills" as developer macros can be useful, but at most those are things shared with the team (in the repo), not something you download from the internet.…

Woaaah buddy this is such a wrong statement that I’d delete it if I were you.

Can’t believe that people confidently spew blatantly false statements like this.

Skills matter, a lot, to every action that requires the AI to find stuff out, so that it doesn’t have to find the same stuff out again. Operating a website, building PowerPoints the way you like them, operating across different surfaces like APIs + GUIs…otherwise the AI has to relearn how to do it every time.

Be confident about things you know. Study about things you don’t.

Re: Ask HN: How do you manage skills files?

#157

Post by misja111 »

avaer wrote: post #105

Skills are mostly snake oil, the way people use them (the aspiration to download kung foo from a celebrity). There was a time when maybe it mattered (last year), but with good repos and good prompts today's agents can find exactly what they need without any skills. "Skills" as developer macros can be useful, but at most those are things shared with the team (in the repo), not something you download from the internet.…

It's not about giving hints to agents because they wouldn't find it out otherwise. It's about saving the work of them having to find out. Good skills files save tokens.

Re: Ask HN: How do you manage skills files?

#158

Post by ekns »

I haven't used skills files at all. I think my codebase scaffolding and AGENTS.md just kind of does everything I need.

E.g. https://github.com/eliask/lawvm/blob/master/AGENTS.md

EDIT: Ah, but what I do instead is I constantly refer to my various public essays. I think it's very useful to have externalized thinking like that available for use with LLM contexts.

Re: Ask HN: How do you manage skills files?

#159

Post by nottorp »

jeffreygoesto wrote: post #61
dxjxjdjsssb wrote: post #26

Earlier quoted context omitted.

I use skills for offloading work onto subagents. By configuring the skill to use a specific model it gets enforced at the harness instead of depending on the good will of the orchestrating model to actually delegate. This also saves context. Today Fable had to fetch a zip file from a web page with a eula prompt, then get at a file in a disk image in the zip. This is something that will need to happen a lot as part of…

Did you consider writing a small Python script for that?

... or telling the LLM to write a small python script for that and install it as a mcp or something ...
Post reply on HN