Claude Skills are awesome, maybe a bigger deal than MCP • Hacker News Board

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

#161

Post by kasey_junk » Fri, Oct 17, 2025, 9:47 PM UTC

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.

MCP seems valuable in that it teaches the llm about oauth. So you can do server based tool calls.

Before that you had to install each cli you wanted and it would invariably be doing some auth thing under the covers.

Took calling was certainly the big llm advantage but “hey tools should probably auth correctly” is pretty valuable.

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

#162

Post by lmeyerov » Fri, Oct 17, 2025, 9:51 PM UTC

simonw wrote: post #143

lmeyerov wrote: post #137

I'm a bit unclear what's different here from how vibe coders already work? Pretty early on folks recognized that most MCPs can just be CLI commands, and a markdown file is fine for describing them. So Claude Code users have markdown files of CLI calls and mini tutorials on how to do things. The 'how to do things' part seems to be what we're now calling skills... Which we're still writing in markdown and using from Cl…

I think skills are mainly just a formalization of the markdown plus CLI patterns that people have been using already. The only material difference with skills is that Claude knows to scan them for YAML descriptions on startup, which means it can trigger them by itself more easily.

Right, the 'knowing' is where I think the interesting thing is today for their evolution

more mature claude.md files already typically index into other files, including guidance which to preload vs lazy load. However, in practice, claude forgets quite easily, so that pattern is janky in practice. A structured mechanism helps claude guarantee less forgetting.

Forward looking, from an automation perspective of autonomous learning, this also makes it more accessible to talk about GEPA-for-everyone to maintain & generate these. We've been playing with similar flows in louie.ai, and came to a similar "just make it folders full of markdown with some learning automation options."

I was guessing that was what was going on here, but the writeup felt like maybe more was being said :) (And thank you for continuing to write!)

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

#163

Post by kobalsky » Fri, Oct 17, 2025, 9:52 PM UTC

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.

MCP servers are basically a tool call registries, how could it be worse than a regular tool call?

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

#164

Post by simonw » Fri, Oct 17, 2025, 9:54 PM UTC

orliesaurus wrote: post #159

Is this different from AGENTS.MD by OPENAI

Yes, it's different. AGENTS.md is a single file that is read by the LLM when the session starts. Skills are multiple .md files which are NOT read on startup - instead, the LLM harness scans them for descriptions and populates the context with those, such that it can later on decide to read the full skills/pdf/skill.md file because the user indicates they want to do something (like create a PDF) for which the skill is relevant.

Plus skill folders can also include additional reference documents and executable scripts, like this one here: https://github.com/anthropics/skills/tree/main/document-skil...

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

#165

Post by NuclearPM » Fri, Oct 17, 2025, 9:55 PM UTC

idk-92 wrote: post #108

crvdgc wrote: post #76

> imagine a folder full of skills that covers tasks like the following: > Where to get US census data from and how to understand its structure Reminds me of my first time using Wolfram Alpha and got blown away by its ability to use actual structured tools to solve the problem, compared to normal search engine. In fact, I tried again just now and am still amazed: https://www.wolframalpha.com/input?i=what%27s+the+total…

tbh wolfram alpha was the craziest thing ever. haven't done much research on how this was implemented back in the day but to achieve what they did for such complex mathematical problems without AI was kind of nuts

Thank you for being honest.

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

#166

Post by smrtinsert » Fri, Oct 17, 2025, 9:55 PM UTC

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.

Im already doing "skills" via 1 mcp tool calling a db and its works fine

Not sure what skills adds here other than more meat for influencers to 10x their 10xed agent workflows. 100x productivity what a time to be alive

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

#167

Post by svdr » Fri, Oct 17, 2025, 9:58 PM UTC

phs318u wrote: post #149

globular-toast wrote: post #127

Earlier quoted context omitted.

Wolfram Alpha is AI. It's just not an LLM. AI has been a thing since the 60s. LLMs will also become "not AI" in a few years probably.

Not sure why you’re getting downvoted. The marketing that LLM=AI seems to have been interpreted as “_only_ LLM=AI”

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.

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

#168

Post by darth_avocado » Fri, Oct 17, 2025, 10:01 PM UTC

XenophileJKO wrote: post #114

darth_avocado wrote: post #95

Earlier quoted context omitted.

> 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.

This is true, but the reason the economics have inverted is that we can pay these new "people" <$20 for the human equivalent of ~300 hours worth of non-stop typing.

That is not true at all. The economics you’re seeing right now are akin to Uber handing out $5 airport pickups to kill the taxi industry. And even then the models are nowhere as cheap as <$20 for ~300 hours of human work.

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

#169

Post by bird0861 » Fri, Oct 17, 2025, 10:02 PM UTC

primer42 wrote: post #157

I've been able to build the equivalent of skills with a few markdown files. I need to remind my agent every so often to use a skill but usually once per session at most. I don't get what's so special about Claude doing this?

I'm wondering the same, I've been doing this with Aider and CC for over a year.

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

#170

Post by simonw » Fri, Oct 17, 2025, 10:03 PM UTC

primer42 wrote: post #157

I've been able to build the equivalent of skills with a few markdown files. I need to remind my agent every so often to use a skill but usually once per session at most. I don't get what's so special about Claude doing this?

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 tool to get things done. AGENTS.md and MCP both put too much stuff in there - the skills pattern is a much better fit.