←back to thread

176 points marv1nnnnn | 2 comments | | HN request time: 0.601s | source
Show context
revicon ◴[] No.43996679[source]
We've done some experimentation when using Claude Code and taken to just creating a "vendor" folder under our "docs" section of each of our repos and just pull down the readme file for every library we use. Then when I'm prompting Claude to figure something out, I'll remind it to go check "docs/vendor/awesomelib" or whatever and it does a fine job of checking the docs out before it starts formulating an answer.

This has done wonders for improving our results when working with TanStack Start or shadcn/ui or whatever.

I guess there's pieces of this that would be helpful to us, but there's too much setup work for me to mess with it right now, I don't feel like generating a Gemini api key, installing puppeteer, etc.

I already have all the docs pulled down, but reducing the number of tokens used for my LLM to pull up the doc files I'm referencing is interesting.

Is there a command line tool anyone has had luck with that just trims down a .md file but still leaves it in a state that the LLM can understand it?

replies(1): >>43997246 #
1. TheTaytay ◴[] No.43997246[source]
I’ve been creating a doc for each of my primary libs (using Claude Code of course). I like your vendor/readme idea. Do you find Claude going and reading more docs if it needs to?
replies(1): >>44002136 #
2. revicon ◴[] No.44002136[source]
I usually tell it to go read the relevant doc when I do the initial prompt to it when I start working on something. And sometimes I'll remind it during a conversation if I want to make sure it isn't re-inventing the wheel instead of using a feature that is already there in the lib. I run into that with TanStack Router from time to time as an example.