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

331–340 of 383 posts

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

#331

Post by ming030890 »

brazukadev wrote: post #324
tptacek wrote: post #238

Earlier quoted context omitted.

What can I do with MCP that I can't do with the function calling interface in the OpenAI Responses API? Besides, obviously, grafting function calls into agents I didn't write; we all understand that's the value prop of MCP. But you're suggesting it's more than that. Fill in the blanks for us.

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.

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

#332

Post by simonw »

crowbahr wrote: post #328
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…

The moment you write documentation it becomes stale. It's additional debt you've incurred and the upkeep must be payed every modification to the code. That doesn't mean you should skip it - but it's vital to recognize the costs. When I joined my current company they had extensive documentation on several systems, all of it outdated, stale or even just straight up wrong. I wasted cumulative weeks depending on other pr…

The fix for that is to keep the documentation in the same repository as the code it documents, and then to enforce that it gets updated as part of your code review process. Don't let a PR land if it doesn't also update any relevant documentation at the same time.

Keeping documentation in a separate system - like a wiki - is an anti-pattern in most cases. It leads to documentation that nobody trusts (and hence nobody consults) because it inevitable falls out of sync with the system it is documenting.

Plus... LLMs are good enough now that having one automatically check PRs to warn if the change affects the existing documentation might actually work well enough to be useful.

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

#333

Post by hansmayer »

simonw wrote: post #313
hansmayer wrote: post #297

Earlier quoted context omitted.

While it's very honest of you to disclose in full your various affiliations to the LLM vendors, and it does look like you're not being paid by them - the reason they are inviting you for the early previews and all that is precisely because they either expect or assume you won't go to critical on them. And that shows in your writing to be honest. I'd assume the same in their place. So yeah, not paid obviously, but it…

Just in the past two weeks: I wrote about how good skills are... but pointed out the flaws in MCP at the same time. Anthropic have invested way more in MCP. I called out Claude Haiku 4.5 as being more expensive than previous Haiku models when the thing I was hoping for was something that was price competitive with GPT-5 Mini/Nano and Gemini Flash Lite. NVIDIA sent me a review unit of their Spark and I wrote about how…

Don't know what to tell you. I read through your blog quite often and it just...does not come across as fully unbiased. While I am sure you are putting in a lot of effort and genuinely want to be impartial, it just does not come across as such. Now, you are making another assumption here. You may think you are getting early access because you are a trusted independent voice. But think about the alternative possibility: Would it not be a very simple logic to conclude you are getting early access because it is a way to affect your writing subtly (you may not be even aware) and trigger some un-concious self-censoring? From the reader's perspective, this is kind of like that "embedded reporting" in war theaters since early 2000s that was applied for propaganda purposes in the past.

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

#334

Post by tidbeck »

crowbahr wrote: post #328
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…

The moment you write documentation it becomes stale. It's additional debt you've incurred and the upkeep must be payed every modification to the code. That doesn't mean you should skip it - but it's vital to recognize the costs. When I joined my current company they had extensive documentation on several systems, all of it outdated, stale or even just straight up wrong. I wasted cumulative weeks depending on other pr…

That is why I like the idea of having as much of the documentation as possible in code. Tests that describe how things are supposed to work, infrastructure as code the describes the parts of the system and so on. Then you are forced to keep them up to date.

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

#335

Post by simonw »

hansmayer wrote: post #333
simonw wrote: post #313

Earlier quoted context omitted.

Just in the past two weeks: I wrote about how good skills are... but pointed out the flaws in MCP at the same time. Anthropic have invested way more in MCP. I called out Claude Haiku 4.5 as being more expensive than previous Haiku models when the thing I was hoping for was something that was price competitive with GPT-5 Mini/Nano and Gemini Flash Lite. NVIDIA sent me a review unit of their Spark and I wrote about how…

Don't know what to tell you. I read through your blog quite often and it just...does not come across as fully unbiased. While I am sure you are putting in a lot of effort and genuinely want to be impartial, it just does not come across as such. Now, you are making another assumption here. You may think you are getting early access because you are a trusted independent voice. But think about the alternative possibilit…

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 disclose things that could potentially influence my coverage, even if I don't personally think they influenced what I wrote.

What matters most to me is that I have an audience who finds me credible and trusts me not to mislead them, either accidentally or on purpose.

That's why I'm defensive against accusations of being a paid shill, which crop up on almost a weekly basis at this point.

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

#336

Post by hansmayer »

simonw wrote: post #309
hansmayer wrote: post #285

Earlier quoted context omitted.

> That's what a prediction IS. If I waited until the feature had proven itself it wouldn't be much of a prediction. No, that's merely guessing mate. Predictions are, at least in modern meaning, based on at least some data and some extrapolation model that more or less reliably predicts the development of your known dataset into future (uknown) values. I don't see you presenting either in your post, so that's not pred…

I think you and I are operating from different dictionaries. What you're describing is more what I'd call a hypothesis or maybe a forecast. I'm comfortable with my use of "prediction" to mean the same thing as a guess.

Well, if we do, those would be very different dictionaries indeed. Do you not know "forecast" is a synonym to "prediction" ? I was going to qualify this with a "practically", but then it turns out according to Mirriam-Webster, prediction is literally a synonym of "forecast". So explain again, what exactly is your "dictionary definition" for "prediction" again? Unless it's guessing, but then, anyone can then make "predictions" like that.

(If we stick to Mirriam-Webster again, here is what I found : to calculate or predict (some future event or condition) usually as a result of study and analysis of available pertinent data - i.e. - basically what I already told you a "prediction" is).

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

#337

Post by trvz »

OJFord wrote: post #329

Why are Skills being compared to MCP everywhere; not Projects, context, chat separation? Wouldn't you (potentially) give different MCP tools to different Skills even?

To confuse the people who hold the money and power, so they won't notice how simplistic all this really is.

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

#338

Post by tptacek »

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.

Right. My understanding of these APIs and model capabilities is imperfect, but at the level I interact with them at, there are only two things: prompts (more broadly: context chunks) and tool calls. I don't see how MCP could meaningfully expand that; it seems like anything I could do with MCP, I could do with context chunks and tool calls --- perhaps better, because I'd have finer-grained control of both security and of context management.

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

#339

Post by oblio »

thenanyu wrote: post #303
jychang wrote: post #287

Earlier quoted context omitted.

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 hate this analogy. NBA players can all hit 90% of their free throws shooting overhand too. Just some of them are much worse at handling the pressure and pace change of the situation in a game context.

The underhanded throw is mechanically just better for free throws. Much easier to put backspin, for example. It's just a shot that doesn't help anywhere else.

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

#340

Post by simonw »

hansmayer wrote: post #336
simonw wrote: post #309

Earlier quoted context omitted.

I think you and I are operating from different dictionaries. What you're describing is more what I'd call a hypothesis or maybe a forecast. I'm comfortable with my use of "prediction" to mean the same thing as a guess.

Well, if we do, those would be very different dictionaries indeed. Do you not know "forecast" is a synonym to "prediction" ? I was going to qualify this with a "practically", but then it turns out according to Mirriam-Webster, prediction is literally a synonym of "forecast". So explain again, what exactly is your "dictionary definition" for "prediction" again? Unless it's guessing, but then, anyone can then make "pre…

Is this perhaps some weird British vs American English thing I was unaware of?

Oxford Learners Dictionary (because the Oxford English Dictionary is behind a paywall): "a statement that says what you think will happen; the act of making such a statement" https://www.oxfordlearnersdictionaries.com/us/definition/eng...

The current Wikipedia definition looks like a good fit for how I'm using the term here:

A prediction (Latin præ-, "before," and dictum, "something said"[1]) or forecast is a statement about a future event or about future data. Predictions are often, but not always, based upon experience or knowledge of forecasters. There is no universal agreement about the exact difference between "prediction" and "estimation"; different authors and disciplines ascribe different connotations. https://en.wikipedia.org/wiki/Prediction

Post reply on HN