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

Claude Skills are awesome, maybe a bigger deal than MCP

simonwillison.net

Post reply on HN
Print view View original

351–360 of 383 posts

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#351

Post by brazukadev »

ming030890 wrote: post #331
brazukadev wrote: post #324

Earlier quoted context omitted.

The LLM can only use MCP tools, but the Client you use the model can access resources, prompts, elicitation and sampling, which are tools to help with querying the model. So one MCP server that implements some or all these features can act as an agent for the LLM dispatching tasks IF the client is also an MCP host/client.

But most of these can really be just a tool. For example, A resource can be just a getter tool, like getFile.

MCP is a protocol, a proposal on standardizing how to do things so we can reuse tools. Whatever thing you want to do with MCP you can do without MCP, that is obvious. But when lots of people agree to write and consume using the same protocol there is a big productivity rise.

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#352

Post by consumer451 »

habitue wrote: post #341
causal wrote: post #318

Earlier quoted context omitted.

It's also not clear to me why using "skills" would consume less context once invoked. It's just instructions with RAG. The more I read about this the more convinced I am that this is just marketing.

Skills wont use less context once invoked, the point is that MCP in particular frontloads a bunch of stuff into your context on the entire api surface area. So even if it doesn't invoke the mcp, it's costing you. That's why it's common advice to turn off MCPs for tools you dont think are relevant to the task at hand. The idea behind skills us that they're progressively unlocked: they only take up a short description…

Your reply unlocked some serious, yet simple understanding for me. Thank you.

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#353

Post by lukeschlather »

jychang wrote: post #287
evanmoran wrote: post #280

Earlier quoted context omitted.

I know this is highly controversial, but I now leave the comments in. My theory is that the “probability space” the LLM is writing code in can’t help but write them, so if i leave them next LLM that reads the code will start in the same space. Maybe it’s too much, but currently I just want the code to be right and I’ve let go of the exact wording of comments/variables/types to move faster.

I think the code comments straight up just help understanding, whether human or AI. There's a piece of common knowledge that NBA basketball players can all hit over 90% on free throws, if they shot underhand (granny style). But for pride reasons, they don't throw underhand. Shaq just shot 52%, even though it'd be free points if he could easily shoot better. I suspect there's similar things in software engineering. I'…

I can't speak to LLMs, but one of my first tasks was debugging a race condition in a piece of software. (I had no idea that it was a race condition, or even what part of the code it was in.) I spent months babysitting the service and reading the codebase. When I finally fixed the issue the source turned out to be a comment that said the opposite of what the code actually did. The code was a very convoluted one-line guard involving a ternary if / several || && statements. If the comment hadn't been there I think I would've read the code sooner and realized the issue.

Personally, I remove redundant comments AI adds specifically to demonstrate that I have reviewed the code and believe that the AI's description is accurate. In many cases AIs will even add comments that only make sense as a response to my prompt and don't make any sense in-context.

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#354

Post by lukeschlather »

ls612 wrote: post #260
Wowfunhappy wrote: post #252

Earlier quoted context omitted.

Your LLMs get rid of comments? Mine add them incessantly.

I have to yell at Gemini to not add so many comments it almost writes more comments than code by default.

I think it's very valuable. If there are a bunch of redundant comments I know I haven't actually validated this code does anything useful. I go through line by line and delete all the comments while validating that they do in fact reflect what the code does.

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#355

Post by tasuki »

simonw wrote: post #151
tasuki wrote: post #148

Earlier quoted context omitted.

What is pseudo-XML?

Looks like XML but isn't actually valid XML. This for example: This & that Simon Article content goes here If you ask an LLM for the title, author and body it will give you the right answer, even though that is not a valid XML document.

Quite obvious, how didn't I think of it? Thanks!

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#356

Post by neves »

7thpower wrote: post #232
michael1999 wrote: post #203

We're doing something like this internally. Our monorepo context files were much too big, so we built a progressive tree of fragments to load up for different tasks. I am struck by how much these kinds of context documents resemble normal developer documentation, but actually useful and task-oriented. What was the barrier to creating these documents before? Three theories on why this is so different: 1) The feedback…

It is primarily a principal agent problem, with a hint of marshmallow test. If you are a developer who is not writing the documents for consumption by AI, you are primarily writing documents for someone who is not you; you do not know what this person will need or if they will ever even look at them. They may, of course, help you, but you may not understand that, have the time, or discipline. If you are writing them…

I always write documentation thinking of myself in the future.

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#357

Post by simonw »

hansmayer wrote: post #350
simonw wrote: post #335

Earlier quoted context omitted.

What would "unbiased" even mean for a blog like mine? I don't particularly try to be unbiased because I don't think that's an achievable goal. What I aim for instead is honesty and truthfulness. I try very hard not to put false information out into the world, and when I do that I work hard to retract it - here's a recent example: https://simonwillison.net/2025/Oct/7/gemini-25-computer-use-... I'm also take care to di…

unbiased as in: not immediately claiming a new feature would be big, mere 24h after it was released to the general public?

How is that "bias", especially if it's a thing I believe to be true?

Are we going to have a break out the dictionaries again?

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#358

Post by hansmayer »

simonw wrote: post #357
hansmayer wrote: post #350

Earlier quoted context omitted.

unbiased as in: not immediately claiming a new feature would be big, mere 24h after it was released to the general public?

How is that "bias", especially if it's a thing I believe to be true? Are we going to have a break out the dictionaries again?

On dictionaries: you're the one who insisted on dictionaries, only to produce wikipedia links instead :)

Now how is it bias? Well, it's in your own answer. You are literally claiming things based on what you believe them to be, not based on what they likely are. For the latter, we'd need a longer timespan and more usage data. So you fiddled with it a bit in a timespan of a week or so and based on this tiny sample, came to a conclusion, that as you specify is your belief, but not really hard data. That is quintessentially what a bias is. Or to borrow from Mirriam-Webster again: an inclination of temperament or outlook especially : a personal and sometimes unreasoned judgment : prejudice

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#359

Post by simonw »

hansmayer wrote: post #358
simonw wrote: post #357

Earlier quoted context omitted.

How is that "bias", especially if it's a thing I believe to be true? Are we going to have a break out the dictionaries again?

On dictionaries: you're the one who insisted on dictionaries, only to produce wikipedia links instead :) Now how is it bias? Well, it's in your own answer. You are literally claiming things based on what you believe them to be, not based on what they likely are. For the latter, we'd need a longer timespan and more usage data. So you fiddled with it a bit in a timespan of a week or so and based on this tiny sample, ca…

I assumed bias was meant to mean I'm biased towards Anthropic, or to reflect some other unfair semi-hidden agenda that influences my writing.

I do have a relevant bias here I guess: I'm biased towards the pattern of granting an LLM the ability to execute commands in a Unix-style environment. I've been a huge fan of that approach ever since ChatGPT Code Interpreter launched in early 2023 and I'm excited that skills further solidifies why that pattern is such a good bet.

Re: Claude Skills are awesome, maybe a bigger deal than MCP

#360

Post by cindyllm »

simonw wrote: post #357
hansmayer wrote: post #350

Earlier quoted context omitted.

unbiased as in: not immediately claiming a new feature would be big, mere 24h after it was released to the general public?

How is that "bias", especially if it's a thing I believe to be true? Are we going to have a break out the dictionaries again?

[dead]
Post reply on HN