Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

arps18.github.io

Post reply on HN
Print view View original

271–280 of 297 posts

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#271

Post by alfiedotwtf »

vitno wrote: post #252
alfiedotwtf wrote: post #107

Earlier quoted context omitted.

Ngl, that’s gold right here. I’ve been trying to automate my sessions, and what I’ve found cool is that you can ask Claude about how to improve on how to ask Claude things, and from there ask Claude to iterate on your session cycles

> ask Claude about how to improve on how to ask Claude things How do you evaluate this? Claude is horrible at performance analysis without data, does it have a feedback loop here that actually moves the needle.

Yes damn, I guess my own vibes more than anything

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#272

Post by dyauspitr »

mil22 wrote: post #168

We really need some consolidation around commands, skills, subagents, and plugins. For example, if you want to, say, review code, you have five options now: - Write a .claude/commands/review.md. Simple but deprecated. - Use a /code-review skill, either one you install or one you just write yourself (it's just Markdown, after all). - Use the /pr-review subagent. Also just Markdown, but it runs "in the background" and…

Honestly I don’t like that we’re coming back around to command line terminology you have to know and remember on a natural language intelligence. Codex doesn’t do this crap yet right?

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#273

Post by port11 »

esafak wrote: post #238
port11 wrote: post #234

Earlier quoted context omitted.

If you wrote this yourself, congratulations are in order. I was genuinely annoyed. It’s not easy. It’s hard. It’s not entertaining. It’s infuriating.

You're absolutely right! I was at a restaurant the other day and my kid noticed how the waiter started every sentence with "Absolutely!" That reminded me of the Anthropic Super Bowl ad, and got me thinking if the waiter's speech patterns had been influenced by AI.

In my time in the US, way before LLMs, very agreeable and helpful waiters/Whole Foods staff would already be using ‘absolutely!’ in that enthusiastic manner. Helping someone out was always possible, I enjoyed that.

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#274

Post by port11 »

mohamedkoubaa wrote: post #249
garethsprice wrote: post #243

Earlier quoted context omitted.

Yes: https://arxiv.org/abs/2409.01754

Eventually we will just speak tokenese rather than english

Nonsense. We grew up quoting our favourite shows, abhorring certain words, preferring others. This is just another cultural modification engine, like everything else humans do.

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#275

Post by sshine »

toastal wrote: post #202
sshine wrote: post #13

The number one power move I have is Nix integration. The availability of tooling, secrets, environment and the ability for the agent to modify its own environment is... well, I don't know how people live without it. I guess you guys still install things using commands and hope everything you need is present on the next machine? Developer machine, CI environment, deployment environment: They're all derived from a sing…

Yikes. That Nix code is a mess without meaningful organization & only usable via experimental flakes.

There are two kinds of organization happening here that you might not see:

1. All .nix files (besides flake.nix) are flake-parts modules: https://flake.parts/

2. It's not only usable with experimental flakes. Works fine with unflake or trix.

The experimental part of flakes is enabling flake support in the `nix` CLI.

Flakes are also a design pattern in pure Nix syntax that can be evaluated fine without the experimental flag.

If you're curious about this meaningful organization, it's pretty well-documented:

https://denful.dev/

As for the experimental nature of flakes, it's more of a social experiment by now:

https://simonshine.dk/articles/if-flakes-are-experimental-wh...

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#276

Post by wiseowise »

garethsprice wrote: post #158
mindwok wrote: post #101

How many times can I read the same shallow guidance written by AI on using a coding agent? Good god when will it stop

You're absolutely right to call this out — and honestly? I want to sit with that for a moment. Here's the thing: this isn't really about AI writing. It's not even about coding agents. It's about something much deeper. What's genuinely worth knowing: while I generally agree, many people may not. I think there's a really interesting conversation to be had here. Thanks for naming this. It needed to be named. (/s - Blarg…

“Chat, raise my vitriol”

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#278

Post by crassus_ed »

isodev wrote: post #92

This was very difficult to read. We really need to snap out of letting LLMs write posts. Even if there is some added value in this post, the feeling of chewing sand is just distracting and unnecessary.

Agreed. I don't get how this article has almost 400 points.. There must be bots upvoting this slop..

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#279

Post by sshine »

uberduper wrote: post #173
sshine wrote: post #13

The number one power move I have is Nix integration. The availability of tooling, secrets, environment and the ability for the agent to modify its own environment is... well, I don't know how people live without it. I guess you guys still install things using commands and hope everything you need is present on the next machine? Developer machine, CI environment, deployment environment: They're all derived from a sing…

I do the same. Codex manages a per project flake.nix and uses `nix develop` for all testing. nix-direnv for my own convenience. I generally have it generate dockerfiles or other deployment assets at some point. Codex is way better at nix than I am.

If you generate Dockerfiles using Nix code, how do you build and run those images? Docker?

I use NixOS on my self-hosted CI runners, and I generate the OCI image using Nix via pkgs.dockerTools:

https://git.shine.town/infra/runners/src/branch/main/nix/nix...

It has nothing to do with Docker as such, it's just named that.

https://nix.dev/tutorials/nixos/building-and-running-docker-...

Re: Claude Code as a Daily Driver: Claude.md, Skills, Subagents, Plugins, and MCPs

#280

Post by notgenerated »

xenadu02 wrote: post #228
alexwwang wrote: post #86

Earlier quoted context omitted.

Understandable. You don’t want to lose control to your codebase and don’t trust LLM is competent in handling that fully.

The percentage of times I prompt claude "what about checking if there are any child processes running?" or "Would using a lock here greatly simplify the design?" only to have myself be correct is approaching 100%. That is it isn't just claude sycophantically agreeing with me. The code itself becomes smaller, simpler, and more reliable with fewer bugs. The agents tend to produce working code but the larger the scope t…

I also feel like we still need to steer Claude. It doesn't always help to have stuff in the CLAUDE.md (even when it's lean). I have a lot of cases where I still need to remind the agent to do something even if it's routine.

To me I think that connects with working longer on the planning and specs. It requires reading and re-reading, but when that's done, implementation is usually much cleaner and adheres to your standards

Post reply on HN