logoalt Hacker News

Agent Skills

68 pointsby BOOSTERHIDROGENyesterday at 9:40 PM13 commentsview on HN

Comments

turlockmiketoday at 12:13 AM

The best way to prompt an LLM is to describe the outcome you want, that's it. They are trained as task completers. A clear outcome is way better than a process.

If the LLM fails, either you didn't describe your outcome sufficiently or is misinterpreted what you said or it couldn't do it (rare).

Common errors should be encoded as context for future similar tasks, don't bloat skills with stuff that isn't shown to be necessary.

show 2 replies
CharlesWyesterday at 11:39 PM

From an SEO/LLMO perspective, the discoverability of these skills will be difficult without a rename: https://agentskills.io/

If Addy reads this, how do you pitch this vs. Superpowers? https://github.com/obra/superpowers

show 3 replies
gavmortoday at 12:12 AM

Naming things is such a hard problem that many devs don't even bother trying.

That being said, this post is full of reasonable assertions, so I'm looking forward to experimenting with this... whatever it is.

show 1 reply
ElijahLynnyesterday at 11:01 PM

I've been using Agent Skills on a new side project and I'm really impressed so far! It really holds my hand a lot of the way and really lets me focus on developing a product instead of figuring out how to build it. I get to focus much more energy on high level architecture and product design.

Very grateful for this repository and everyone who contributed to it!

senkoyesterday at 11:48 PM

> This isn’t a coincidence. It’s the same SDLC every functioning engineering organisation runs, just in different vocabulary. [...] Amazon calls it the working-backwards memo and the bar raiser. Every healthy team has some version of this loop.

This (sdlc == working backwards & bar raiser) is so horribly wrong, that I hope this was an LLM hallucination.

In general, I'm starting to see these agent scaffolding systems as an anti-pattern: people obsess over systems for guiding agents and construct elaborate rube-goldberg machines and then others cargo-cult them wholesale, in an effort to optimize and control a random process and minimize human involvement.

show 2 replies
y-curiousyesterday at 10:55 PM

Thanks for this, going to steal a lot of this. I would install your plugin, but I worry about being able to delete it later. I also think that each one of these is better served customized to a developer. That said, I'm still going to grab some of these, thanks!

gosukiwiyesterday at 11:43 PM

I wonder how does this compare to superpowers

encodereryesterday at 10:34 PM

I adopted a couple of these, the api design and ui testing ones have been particularly helpful.

stevenpetrykyesterday at 11:49 PM

[dead]

saluc28yesterday at 9:47 PM

[dead]