logoalt Hacker News

zachwlewis • today at 2:28 AM • 3 replies • view on HN

I got tired of doing this and set up a /question skill that forbids the agent from doing anything that would modify my files. It makes it very clear what the intent of every prompt is.

Similarly, I have an /info skill that tells the agent to read my prompt, update any memories it thinks it should, then pass the turn.


Replies

illiac786 • today at 2:56 AM

>Similarly, I have an /info skill that tells the agent to read my prompt, update any memories it thinks it should, then pass the turn.

Could you give me a quick example? I think I’m not getting it, but it sounds interesting.

demibabs • today at 3:15 AM

Very simple but clever solution. I’ll probably do something like this as well

RussianCow • today at 2:40 AM

This is clever and I can't believe I didn't think of it. I'm so used to appending "don't make any changes" to the end of my prompts.