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

201–210 of 383 posts

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

#201

Post by ajtejankar »

simonw wrote: post #189
causal wrote: post #185

Earlier quoted context omitted.

Strong disagreement on the helpfulness of the name- if anything calling a context file a skill is really misleading. It evokes something like a LoRA or pluggable modality. Skill is the wrong name imo

I think skill is the perfect name for this. You provide the LLM with a new skill by telling it how to do a thing and providing supporting scripts to help it do that thing.

Yup! I fully agree. It also taps into the ability of LLMs to write code given good prompts. All you need is for the LLM to recognize that it needs something, fetch it into the context, and write exactly the code that is needed in the current combination of skill + previous context.

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

#202

Post by michael1999 »

darth_avocado wrote: post #95
AJRF wrote: post #82

This is a fairly negative comment, but putting it out there to see if other people are feeling the same thing If you told the median user of these services to set one of these up I think they would (correctly) look at you like you had two heads. People want to log in to an account, tell the thing to do something, and the system figures out the rest. MCP, Apps, Skills, Gems - all this stuff seems to be tackling the wr…

> MCP, Apps, Skills, Gems - all this stuff seems to be tackling the wrong problem My fairly negative take on all of this has been that we’re writing more docs, creating more apis and generally doing a lot of work to make the AI work, that would’ve yielded the same results if we did it for people in the first place. Half my life has been spent trying to debug issues in complex systems that do not have those available.

I am also struck by how much these kinds of context documents resemble normal developer documentation, but actually good. What was the barrier to creating these documents before?

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

#203

Post by michael1999 »

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 loop was too long. If you wrote some docs, you might never learn if they were any good. If you did, it might be years later. And if you changed them, doing an A/B test was impractical. Now, you can write up a context markdown, ask Claude to do something, and iterate in minutes.

2) The tools can help build them. Building good docs was always hard. Especially if you take the time to include examples, urls, etc. that make the documentation truly useful. These tools reduce this cost.

3) Many programmers are egotists. Documentation that helps other people doesn't generate internal motivation. But documentation that allows you to better harness a computer minion to your will is attractive.

Any other theories?

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

#204

Post by TeMPOraL »

zkmon wrote: post #93
AJRF wrote: post #82

This is a fairly negative comment, but putting it out there to see if other people are feeling the same thing If you told the median user of these services to set one of these up I think they would (correctly) look at you like you had two heads. People want to log in to an account, tell the thing to do something, and the system figures out the rest. MCP, Apps, Skills, Gems - all this stuff seems to be tackling the wr…

>> but deep problems aren't being solved There is no problem to solve. These days, solutions come in a package which includes the problems they intend to solve. You open the package. Now you have a problem that jumped out of the package and starts staring at you. The solution comes out of the package and chases the problem around the room. You are now technologically a more progressed human.

This is where GP is wrong, I think. The problem are being solved, for now, because the businesses are still too excited about the whole AI thing to notice it's not in their interest, and properly consolidate against it.

And the problem being solved is, LLMs are universal interfaces. They can understand[0] what I mean, and they understand what those various "solutions" are, and they can map between them and myself on the fly. They abstract services away.

The businesses will eventually remember that the whole point of marketing is to prevent exactly that from happening.

--

[0] - To a degree, and conditioned on what one considers "understanding", but still - it's the first kind of computer systems that can do this, becoming a viable alternative to asking a human.

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

#205

Post by jgalt212 »

jhallenworld wrote: post #179
magicalhippo wrote: post #138

Earlier quoted context omitted.

Would really like something selfhosted that does the basic Wolfram Alpha math things. Doesn't need the craziest math capability but standard symbolic math stuff like expression reduction, differentiation and integration of common equations, plotting, unit wrangling. All with an easy to use text interface that doesn't require learning.

Try maxima, it's open source: https://maxima.sourceforge.io/ I used it when it was called Macsyma running on TOPS-20 (and a PDP-10 / Decsystem-20). Text interface will require a little learning, but not much.

Maxima is amazing and has a GUI. My only beef with it is it doesn't show its work step by step.

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

#206

Post by ajtejankar »

causal wrote: post #185
simonw wrote: post #170

Earlier quoted context omitted.

Part of it is that they gave a name to a useful pattern that people had already been discovering independently. Names are important, because they mean we can start having higher quality conversations about the pattern. Anthropic also realized that this pattern solves one of the persistent problems with coding agents: context pollution. You need to stuff as little material as possible into the context to enable the to…

Strong disagreement on the helpfulness of the name- if anything calling a context file a skill is really misleading. It evokes something like a LoRA or pluggable modality. Skill is the wrong name imo

IMO LoRAs are no different from context tokens. In fact, before LoRAs tuned prompt vectors were a popular adapter architecture. Conceptually, the only difference is that prompt adapters only interact with other tokens through the attention mechanism while LoRAs allow you to directly modify any linear layer in the model. Essentially, you can think of your KV cache as dynamically generated model weights. Moreover, I can't find the paper, but there is some evidence that in-context learning is powered by some version of gradient descent inside the model.

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

#207

Post by samuelknight »

roflcopter69 wrote: post #129
dist-epoch wrote: post #91

Earlier quoted context omitted.

Funny thing, pseudo-XML is going through a big resurgence right now, because models love it, while they seriously struggle with JSON.

I'd be really interested in what you mean. Are the any studies that quantify this difference in model performance when using JSON or XML? What could be a good intuition for why there might be a big difference? If XML is better than JSON for LLMs, why isn't everyone and the grandma recommending me to use XML instead of JSON? Why is Google Gemini API offering structured output only with JSON schema instead of XML schem…

(1) JSON requires lots of escape characters that mangle the strings + hex escapes and (2) it's much easier for model attention to track when a semantic block begins and ends when it's wrapped by the name of that section

...

...

can be much easier than

{

"instructions": "..\n...\n"

}

especially when there are newlines, quotes and unicode

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

#208

Post by jgalt212 »

tptacek wrote: post #110

I do think the big story here is how hyperfocused and path-dependent people got on MCP, when the actually-interesting thing is simply "tool calls". Tool calls are incredibly interesting and useful. MCP is just one means to that end, and not one of the better ones.

Other than, presumably Skills, what other techniques are better than MCP?

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

#210

Post by ozim »

globular-toast wrote: post #178
svdr wrote: post #167

Earlier quoted context omitted.

I think the difference now is that traditional software ultimately comes down to a long series of if/then statements (also the old AI's like Wolfram), whereas the new AI (mainly LLM's) have a fundamentally different approach.

Look into something like Prolog (~50 years old) to see how systems can be built from rules rather than it/else statements. It wasn't all imperative programming before LLMs. If you mean that it all breaks down to if/else at some level then, yeah, but that goes for LLMs too. LLMs aren't the quantum leap people seem to think they are.

maybe not on their own - but having enough computing power to use LLMs in a way we do now and actually using them is quite a leap.
Post reply on HN