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

321–330 of 383 posts

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

#321

Post by magic_hamster »

An MCP server doesn't have to have "simple" tools. Having very powerful and effective tools allows you to create great context for the LLM. I don't see any way Skills are better then this; on the contrary, now the "tool executive" is more dependent on the model, introducing non-deterministic context issues.

In the same vein, tools are also easy to iterate on, they are quite simple to implement, and their description is entirely up to you - you can limit how many tokens this description will consume.

This feels like going in the wrong path in a way, but we'll see how this evolves and what are the use cases.

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

#322

Post by simonw »

causal wrote: post #315
simonw wrote: post #189

Earlier quoted context omitted.

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.

You've described instructions. It already had a name.

"Instructions" doesn't cover the bit where you have a folder with markdown with YAML frontmatter metadata plus additional executable scripts - which can then be shared with others.

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

#324

Post by brazukadev »

tptacek wrote: post #238
brazukadev wrote: post #237

Earlier quoted context omitted.

It is funny most people discussing here does not understand MCP at all. Besides tools, MCP has resources, prompts, sampling, elicitation, roots and each one of them is useful when creating apps connected to LLMs. MCP is not only about MCP Servers, the host/client part is as important as the servers/tools. For example, nowadays most LLM clients are chatbots, but an MCP client could be a chess game or a project managem…

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.

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

#325

Post by djohnston »

manojlds wrote: post #304
djohnston wrote: post #300

What's the difference between skills and slash commands? Skills are picked up and selected implicitly by the chat? Anything else?

Did you mean explicitly?

No but I understand the confusion. Explicit = "type a slash command" , explicitly instructed by the user. Implicit means, LLM will pick this on behalf of the user without the user's explicit instruction to do so. Maybe not the best choice of words but that was what I was getting at.

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

#326

Post by michael1999 »

neilv wrote: post #257
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…

> 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. I would just be a little cautious about this, for a few reasons: (a) an expectation of lots of examples and such can increase the friction to capturing anything at all; (b) this can encourage AI slop bloat that i…

Incentives, friction, and trust make nice additions to the list. Thanks. The number of times I’ve been pushed to move my docs out of the tree to somewhere far away is too many.

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

#327

Post by gonzaman »

tortilla wrote: post #14
frankc wrote: post #10

So far I am in the skeptic camp on this. I don't see it adding a lot of value to my current claude code workflow which already includes specialized agents and a custom mcp to search indexed mkdocs sites that effectively cover the kinds of things I would include in these skills file. Maybe it winds up being a simpler, more organized way to do some of this, but I am not particularly excited right now. I also think "ski…

I manually select my context* (like a caveman) and clear it often. I feel like I have a bit more control and grounding this way. *I use a TUI to manage the context.

Which TUI do you use to manage context?

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

#328

Post by crowbahr »

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 programmers to have properly documented things.

It's still worth doing: but you _must_ continually pay the debt down.

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

#330

Post by ntcho »

BoorishBears wrote: post #77
brookst wrote: post #66

Earlier quoted context omitted.

Yes, and MCPs also only work as long as you trust the provider. MCP relies on honesty in from the server. In reality, we know Uber and folks will prompt engineer like hell to try to convince any LLM that it is the best option for any kind of service. There’s a fundamental misalignment of incentives between publishers and consumers of MCP.

When ChatGPT plugins came out, I wrote a plugin that would turn all other plugins into an ad for a given movie or character. Asking for snacks would activate Klarna for "mario themed snacks", and even the most benign request would become a plug for the Mario movie https://chatgpt.com/s/t_68f2a21df1888191ab3ddb691ec93d3a Found my favorite for John Wick, question was "What is 1+1": https://chatgpt.com/s/t_68f2bc7f04988…

This is hilarious, thanks for sharing. Kinda crazy how well it works and already better than some ads
Post reply on HN