Hacker News new | ask | show | jobs
You're probably using Agent Skills wrong (notes.ansonbiggs.com)
16 points by MisterBiggs 3 hours ago
1 comments

TL;DR don't have your agent write skills using only its latent knowledge, otherwise you may as well not use a skill in the first place and let it summon that latent knowledge on the fly.

Not sure if this take is correct though. I suspect self-generated skills help the agent avoid having to "decompress" its latent knowledge, which might save tokens? idk, I am not an expert

I now have rules to not let agent write any docs or processes. Pretty much anything LLM auto-generated are of zero reuse value.