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

51–60 of 383 posts

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

#51

Post by markusw »

simonw wrote: post #46
lillecarl wrote: post #12

Isn't this just repackaged RAG pretty much?

Depends which definition of RAG you're talking about. RAG was originally about adding extra information to the context so that an LLM could answer questions that needed that extra context. On that basis I guess you could call skills a form of RAG, but honestly at that point the entire field of "context engineering" can be classified as RAG too. Maybe RAG as a term is obsolete now, since it really just describes how w…

I’d rather say you can use skills to do RAG by supplying the right tools in the skill (“here’s how you query our database”).

Calling the skill system itself RAG is a bit of a stretch IMO, unless you end up with so many skills that their summaries can’t fit in the context and you have to search through them instead. ;)

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

#52

Post by simonw »

SV_BubbleTime wrote: post #49
simonw wrote: post #37

Earlier quoted context omitted.

You don't need MCP if you can instead drop in a skill markdown file that says "to access the GitHub API, use curl against api.github.com and send the GITHUB_API_KEY environment variable in the authorization header. Here are some examples. Consult github-api.md for more."

Am I the only person left that is still impressed that we have a natural language understanding system so good that its own tooling and additions are natural language?

I still can't believe we can tell a computer to "use playwright Python to test this new feature page" and it will figure it out successfully most of the time!

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

#53

Post by mudkipdev »

vunderba wrote: post #16
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'm inclined to agree. I've read through the Skill docs and it looks like something I've been doing all along - though I informally referred to it as the "Table of Contents" approach. Over time I would systematically create separate specialized docs around certain topics and link them in my CLAUDE.md file but noticeably without using the "@" symbol which to my understanding always causes CLAUDE to ingest the linked f…

I just tag all the relevant documentation and reference code at the beginning of the session

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

#55

Post by rednafi »

MCP gives me early days gRPC vibes - when the protocol felt heavy and the toolings had many sharp edges. Even today, after many rounds of improvements, people often eschew gRPC and Protobuf.

Similarly, my experience writing and working with MCPs has been quite underwhelming. It takes too long to write them and the workflow is kludgy. I hope Skills get adopted by other model vendors, as it feels like a much lighter way to save and checkout my prompts.

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

#58

Post by prophesi »

lillecarl wrote: post #12

Isn't this just repackaged RAG pretty much?

I think RAG is out of favor because models have a much larger context these days, so the loss of information density from vectorization isn't worth it, and doesn't fetch the information surrounding what's retrieved.

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

#59

Post by simonw »

prophesi wrote: post #58
lillecarl wrote: post #12

Isn't this just repackaged RAG pretty much?

I think RAG is out of favor because models have a much larger context these days, so the loss of information density from vectorization isn't worth it, and doesn't fetch the information surrounding what's retrieved.

That's true if you use RAG to mean "extra context found via vector search".

I think vector search has shown to be a whole lot more expensive than regular FTS or even grep, so these days a search tool for the model which uses FTS or grep/rg or vectors or a combination of those is the way to go.

Post reply on HN