I think this does a great job of explaining the .claude directories in a beginner friendly way. And I don’t necessarily read it as “you have to do all this, before you start”.
It has a few issues with outdated advice (e.g. commands has been merged with skills), but overall I might use share it with co-workers who needs an introduction to the concept.
I really like the jig analogy. But that the software jig is no different from production software, I don't buy. Saying that the bytes are the same, is like saying that the atoms of a jig is the same as the atoms in the final product.
GenAI generally makes software cheaper. But there is a huge difference in how much. Prototypes and jigs may be 90% cheaper (just making up numbers here), while for production software it may be closer to 10%.
I guess that depends on how you use agents (SRE or in general). If you ask it a question (even implicitly) and blindly trust the answer, I agree. But if you have it help you find the needle in the haystack, and then verify that did indeed find the needle, suddenly it’s a powerful tool.
I built this to solve a personal annoyance - reformatting recipes
from messy sources (blog posts, screenshots, social media comments).
Instead of trying to parse every possible recipe format, I treat it as
a transformation problem. Paste messy text, AI interprets the structure,
you get clean output. The app preserves attribution and stores both
versions so you can verify the interpretation.
Tech: Next.js + PostgreSQL + OpenAI API, deployed on Vercel.
I have to admit that my first thought was “April’s fool”. But you are right. It makes a lot of sense (if they can get it to work well). Not only is Excel the world’s biggest “programming language”. It’s probably also one of the most unintuitive ways to program.
This is already a feature in an app called MacroFactor. But there is definitely room for improvement in the field.
One thing that I miss in MacroFactor is that it should have some memory of my previous choice.
Example:
If I take a picture of a glass of milk, it always assumes it to be whole milk (3.5% fat). Then I change it to a low fat milk (0.5% fat). But no matter how many times I do that, it keeps assuming that the milk in the photo is whole milk.
As mentioned, HTML is indeed a programming language. But it’s one that is rarely used on its own. So you could argue that having it as a thing of itself in these lists, makes little sense.