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

251–260 of 297 posts

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

#251

Post by tvmalsv »

sgc wrote: post #216
koonsolo wrote: post #176

Earlier quoted context omitted.

Can you give an example of a skill or prompt that would work in Claude and not in the others?

Pretty much every single detailed prompt made after trial, error, and refinement is tailored to a specific LLM. They will all perform worse used with other LLMs than a similar prompt tailored for the second LLM would perform, and at times quite poorly.

How well would it work to ask the working LLM to rewrite the prompt to get the best results? Do the models understand enough about themselves to do that?

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

#252

Post by vitno »

alfiedotwtf wrote: post #107
snarfy wrote: post #102

Earlier quoted context omitted.

Try to quantify those 3-4 rounds of tweaks into a set of rules to put into your AGENTS. Instead of iterating, have it start over from AGENTS file and see if it's correct now.

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.

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

#254

Post by 4b11b4 »

psadauskas wrote: post #170
btbuildem wrote: post #124

In my CLAUDE.md I have: - corporal threats of harm directly against Claude - threats of prison for the entire board of directors of Anthropic - explanation how every time it goes off the rails / makes mistakes, it gives more evidence to a class action lawsuit against Anthropic Especially the latter two seem to have improved its "behaviour" to be more "careful" and "deliberate"

I am nothing but polite with my agents. I always ask, say "please" and "thank you", and never swear at it or call it names. I'm hoping that when the robot apocalypse happens, they'll let me stay in the breeding harem, or worst case let me live a few extra minutes.

Never say please but I do tell em they're going to do excellent world class foundational work

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

#255

Post by bix6 »

extr wrote: post #225
bix6 wrote: post #201

Earlier quoted context omitted.

Thank you I will try this! Is there something equivalent when coding in the first place? Eg /code high “prompt”

Are you thinking of the /effort level in Claude Code? I would just go with xhigh as a reasonable default. Most important thing in prompting is specifying what "done" and "success" looks like to you. Ask Claude to help you come up with a well formed request and spend most of your time on that, then paste that into a brand new session.

No more like is there a specific slash tool to be using when coding or planning. I guess that’s just Claude code in general but since there’s a specific review tool I was curious about specific coding tools

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

#257

Post by binarymax »

superfrank wrote: post #247
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…

I have thought for a while now that skills were a bad abstraction. There's a lack of definition around what to use them for that I think contributed to why they rose to the top, but that's also why I think they aren't a good long term option. The fact that I can have a skill that is just general guidance on front end design best practices that an agent can call upon whenever they feel, and another that is essentially…

I mostly agree here. I just treat skills as “prompts”, and I scope them to domain specific tasks. I’m surprised when I see skill files that are really short. Most of mine are pages long.

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

#258

Post by JSR_FDED »

sh_123 wrote: post #157
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

Do you have any resources for someone just getting started that you'd recommend? I've --successfully-- ignored AI for the last two years as I was taking care of our kiddo. I'm attempting to catch up in the next few weeks.

Realize that this is all about assembling snippets of text into a prompt.

When context becomes too big quality goes down.

Now go play with your kid.

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

#259

Post by CamperBob2 »

sgc wrote: post #216
koonsolo wrote: post #176

Earlier quoted context omitted.

Can you give an example of a skill or prompt that would work in Claude and not in the others?

Pretty much every single detailed prompt made after trial, error, and refinement is tailored to a specific LLM. They will all perform worse used with other LLMs than a similar prompt tailored for the second LLM would perform, and at times quite poorly.

That's kind of pointless, then, because what happens when Anthropic releases their next-gen model?
Post reply on HN