I agree with the notion here that things are moving so fast that most blog posts will be outdated quickly.
However posts like this is valuable for new people to get a basic understanding of how these tools could be used in a very simple, beginner friendly, setup.
- I wouldn’t outsource my brain to CC when it comes to checking CC’s output. Very mixed results in my experience, and it might discourage further exploration/thinking if you’ve already performed the checklist CC has given you (satisficing).
- Slash commands are the idiomatic way to memoize often used prompts, I wonder why author put them in CLAUDE.md?
- I’m also a bit skeptical that, aside from strict rules CC needs to follow, the encouragements/enchantments for writing good code author put in CLAUDE.md really work. But who knows.
- I DO like the caveats section at the end a lot. This is probably the most important piece of the article, when it comes to large codebases. Never just accept the first draft. Review everything with high suspicion and bend the output to your own style and taste. Otherwise, you‘re pushing legacy code.
I agree. I remember a year ago some a submission on this forum by Sabrina where she was evaluating LLMs on SAT math problems. The post was called like “ChatGPT-4o vs. Math”. I thought it was pretty insightful, but now that post is deleted from her blog and it seems like the blog as a whole is leaning into attracting people who are nontechnical and want to use it to generate social media content. Weird vibe in the comments of her posts and videos too.
Am I the only one who uses CC in a one-shot fashion?
I rely on what has been generated by the init slash command at the root of my monorepo and then when I have a complex task I manually create a md file called CONTEXT.md inside the package/area where I want to implement the new task.
I try to be as detailed as possible, think like writing a ticket for a junior dev.
Then my only command for CC is something like: “Focus on the project structure described in CLAUDE.md and work through the task planned in CONTEXT.md. Follow current codebase standards, keep code reusable and easy to follow and modify.”
This is like 99% of my CC interactions working on top of a well structured codebase and it just works perfectly for almost any task I throw at it.
11 comments
[ 1.3 ms ] story [ 37.4 ms ] threadIt destroys the context for readers, making the thread worse for everyone.
However posts like this is valuable for new people to get a basic understanding of how these tools could be used in a very simple, beginner friendly, setup.
- I wouldn’t outsource my brain to CC when it comes to checking CC’s output. Very mixed results in my experience, and it might discourage further exploration/thinking if you’ve already performed the checklist CC has given you (satisficing).
- Slash commands are the idiomatic way to memoize often used prompts, I wonder why author put them in CLAUDE.md?
- I’m also a bit skeptical that, aside from strict rules CC needs to follow, the encouragements/enchantments for writing good code author put in CLAUDE.md really work. But who knows.
- I DO like the caveats section at the end a lot. This is probably the most important piece of the article, when it comes to large codebases. Never just accept the first draft. Review everything with high suspicion and bend the output to your own style and taste. Otherwise, you‘re pushing legacy code.
At the moment they burn a investor money to gain customers by giving us free tools and cheap LLMs.
That will end at some point.
Maybe it does have some valuable content but I will just close it.
Why would you need that?
> CLAUDE.md is a special file that Claude automatically pulls into context when starting a conversation.
https://www.anthropic.com/engineering/claude-code-best-pract...
This is like 99% of my CC interactions working on top of a well structured codebase and it just works perfectly for almost any task I throw at it.