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

Academic Research Skills for Claude Code

github.com

Post reply on HN
Print view View original

1–10 of 32 posts

Re: Academic Research Skills for Claude Code

#6

Post by AndyNemmity »

apwheele wrote: post #2

There needs to be a new name for people creating these with no obvious validation. Skill spam?

Define obviously validation? What is the signal that tells you one is reasonable vs another?

I find the only way to do that is to look at it, if it passes some visual tests, try it, and then a/b test if it's any better than without it.

Re: Academic Research Skills for Claude Code

#7

Post by apwheele »

AndyNemmity wrote: post #6
apwheele wrote: post #2

There needs to be a new name for people creating these with no obvious validation. Skill spam?

Define obviously validation? What is the signal that tells you one is reasonable vs another? I find the only way to do that is to look at it, if it passes some visual tests, try it, and then a/b test if it's any better than without it.

So yes a/b broadly speaking is what I was saying (test cases and can show it is actually better).

Even this repo just the "b" showcase, showing the outputs as is (with no clear documentation how those were generated, is it headless in a CI pipeline somewhere?), is not good, https://github.com/Imbad0202/academic-research-skills/tree/m....

Re: Academic Research Skills for Claude Code

#8

Post by theptip »

AndyNemmity wrote: post #6
apwheele wrote: post #2

There needs to be a new name for people creating these with no obvious validation. Skill spam?

Define obviously validation? What is the signal that tells you one is reasonable vs another? I find the only way to do that is to look at it, if it passes some visual tests, try it, and then a/b test if it's any better than without it.

Some sort of eval. Eg TermBench, implemented in Harbor.

It’s an insane amount of effort to build shareable, reusable, comprehensive evals, hence why so almost all skills are stuck in the “vibes” phase.

That said I think it’s quite easy to skim/intuit these sort of skills and do horizontal gene transfer into your own vibes-based system. If you use the skills regularly you can construct a cheap personal eval that is a lot easier to maintain and use it to compare a new skill/plugin. Just things like “please write a paper on ” is a good starting point here. You get a good feel for whether a skill is better than vanilla by running it a couple times and watching the failure modes.

Re: Academic Research Skills for Claude Code

#9

Post by AndyNemmity »

apwheele wrote: post #7
AndyNemmity wrote: post #6

Earlier quoted context omitted.

Define obviously validation? What is the signal that tells you one is reasonable vs another? I find the only way to do that is to look at it, if it passes some visual tests, try it, and then a/b test if it's any better than without it.

So yes a/b broadly speaking is what I was saying (test cases and can show it is actually better). Even this repo just the "b" showcase, showing the outputs as is (with no clear documentation how those were generated, is it headless in a CI pipeline somewhere?), is not good, https://github.com/Imbad0202/academic-research-skills/tree/m... .

I run a lot of a/b testing. But I'm not sure showing it actually communicates all that much. Since these are non deterministic systems, even showing you an a/b test from when i made the decision a month ago, doesn't really mean a whole lot.

I agree we need more clear indications of value, I don't quite understand how to legitimately do that in a fair, and honest way.

Post reply on HN