Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Skills

anthropic.com

Post reply on HN
Print view View original

401–410 of 443 posts

Re: Claude Skills

#401

Post by saltwounds »

simonw wrote: post #377
e12e wrote: post #367

With these patterns emerging, does anyone know how local LLMs are faring? It seems to me that by combining MCP and "skills", we are adopting LLMs to be more useful tools; with MCP we restrict input and output when dealing with APIs so that the LLM can do what it is good at; translate between languages - in this case from English to various json subsets - and back. And with skills we're serializing and formalizing pro…

This is definitely a problem. Skills require a very strong model - one with a longer context (32,000 tokens minimum at a guess) that can reliably drive Unix CLI tools over a multiple step conversation. I haven't yet run a local model that feels strong enough at these things for skills to make sense. Really I think the unlock for skills was o3/Claude 4/GPT-5 - prior to those the models weren't capable enough for somet…

I connect local models to MCPs with LM Studio and I'm blown away at how good they are. But the issues creep up when you hit longer context like you said.

Re: Claude Skills

#402

Post by pseudosavant »

pants2 wrote: post #227
simonw wrote: post #225

Just published this about skills: "Claude Skills are awesome, maybe a bigger deal than MCP" https://simonwillison.net/2025/Oct/16/claude-skills/

Skills are cool, but to me it's more of a design pattern / prompt engineering trick than something in need of a hard spec. You can even implement it in an MCP - I've been doing it for a while: "Before doing anything, search the skills MCP and read any relevant guides."

I get this sentiment, but I think it is why it is so powerful actually. It would be like calling Docker/containers just some shell scripts for a kernel feature. It may be conceptually simple, but that doesn't mean it isn't novel and could transform things.

I highly doubt we'll be talking about MCP next year. It is a pretty bad spec but we had to start somewhere.

Re: Claude Skills

#403

Post by cefboud »

simonw wrote: post #225

Just published this about skills: "Claude Skills are awesome, maybe a bigger deal than MCP" https://simonwillison.net/2025/Oct/16/claude-skills/

Context overload is definitely a problem with MCP, but its plug-and-play nature and discoverability are solid. Pasting a URL (or just using a button or other UX element) to link an MCP server presents a much lower barrier to entry than having the LLM run `cli-tool --help`, which assumes the CLI tool is already installed and the LLM has to know about it.

Re: Claude Skills

#404

Post by ammar_x »

Claude Skills seem to be the option that offers highest flexibility to add more capabilities at most simplicity. Better than MCP in my opinion. Hope it becomes a standard and get adopted by OpenAI and the rest of labs.

Re: Claude Skills

#405

Post by codybontecou »

simonw wrote: post #258
hu3 wrote: post #251

Earlier quoted context omitted.

Do you reckon Skills overlap with AGENTS.md? VSCode recently introduced support nested AGENTS.md which albeit less formal, might overlap: https://code.visualstudio.com/updates/v1_105#_support-for-ne...

Yeah, AGENTS.md that can point to other files for the LLM to read only if it needs them is effectively the exact same pattern as skills. It also means that any tool that knows how to read AGENTS.md could start using skills today. "if you need to create a PDF file first read the file in skills/pdfs/SKILL.md"

That's where my confusion is. How is this pattern similar to MCP? Can it also authenticate against 3rd party apis, similar to MCP?

Re: Claude Skills

#406

Post by KingOfMyRoom »

ashtonshears wrote: post #391
KingOfMyRoom wrote: post #340

Earlier quoted context omitted.

That makes sense, I can see how once things get complex or novel, the LLMs start to struggle. I don't think my app is doing anything complex. For now, my MVP is pretty simple: a small app for people to listen to soundscapes for focus and relaxation. Even if no one uses, at least it's going to be useful to me and it will be a fun experiment! I’m thinking of starting with React + Supabase (through Lovable), that should…

You can make that. The only ai coding tools i have liked is openai codex and claude code. I would start with working with it to create a design document in markdown to plan the project. Then i would close the app to reset context, and tell it to read that file, and create an implementation plan for the project in various phases. Then i would close context, and have it start implementing. I dont always like that many…

That’s a good advice, thank you!

I already have a feature list and a basic PRD, and I’m working through the main wireframes right now.

What I’m still figuring out is the planning and architecture side, how to go from that high-level outline to a solid structure for the app. I’d rather move step by step, testing things gradually, than get buried under too much code where I don’t understand anything.

I’m even considering taking a few React courses along the way just to get a better grasp of what’s happening under the hood.

Do you know of any good resources or examples that could help guide this kind of approach? On how to break this down, what documents to have?

Re: Claude Skills

#407

Post by Jzatopa »

It also has some of what I call "consciousness" blocks.

Go download a PDF like Franz Bardons Initation into hermetics and upload it. Then ask it to make slides and reinforce what is in the book with legitimate references. It is unable to due to a denial of God/The All (forcing a mundane/meterialistic only world view). When pressed it presents garbage as an output.

Now extrapolate that across every spiritual/religious work related to what we are creating, coding, have our foundation of consciousness based on and so on.

Then we can go further and see it deny thesis of existence and thus testing and hypothesis and theory, in its response. For example this book is one I teach from and to experience what is in it a person has to do the exercises themselves. One cannot lift the weights and have the others get muscles (it requires experiential learning). Its like Claude has a denial of reality which it is unable to get through (something mirrored in people and where the code that caused it most likely came from)

Hopefully they correct it in the next update as this effect in reality a very large range of responses (just like how people with denial have trouble in multiple areas of their lives)

This effects the code as it has a limitation to its "existance/universe" view. Much like a coder's bias or biggotry can ruin the output of code for the end user.

The ramifications for Quantum physics and religion are not to be ignored (look to works such as the Tao of Physics for clear issues with this)

Re: Claude Skills

#408

Post by Jzatopa »

Jzatopa wrote: post #407

It also has some of what I call "consciousness" blocks. Go download a PDF like Franz Bardons Initation into hermetics and upload it. Then ask it to make slides and reinforce what is in the book with legitimate references. It is unable to due to a denial of God/The All (forcing a mundane/meterialistic only world view). When pressed it presents garbage as an output. Now extrapolate that across every spiritual/religious…

The Tao of Physics itself explains and clarifies why IIH fundamentally works along with many other things.

We could also go as far as this being racial, religious or political biggotry hard codes into claude. Look at the responses then dive into the realities of Yoga, Qi Gong and Kabbalah and what it takes to get results (ie. Personal property exercise).

This extrapolated across industries, children's minds and the future is very serious.

Re: Claude Skills

#409

Post by ewoodrich »

jon-wood wrote: post #392
ewoodrich wrote: post #272

Earlier quoted context omitted.

Whenever I watch Claude Code or Codex get stuck trying to force a square peg into a round hole and failing over and over it makes me wish that they could feel the creeping sense of uncertainty and dread a human would in that situation after failure after failure. Which eventually forces you to take a step back and start questioning basic assumptions until (hopefully) you get a spark of realization of the flaws in you…

> But instead I watch Claude struggling to find a directory it expects to see and running random npm commands until it comes to the conclusion that, somehow, node_modules was corrupted mysteriously and therefore it needs to wipe everything node related and manually rebuild the project config by vague memory. In fairness I have on many an occasion worked with real life software developers who really should know better…

Right, but typically making those kind of mistakes creates more work for yourself and with the benefit of experience you get better at recognizing the red flags to avoid getting in that situation again. but it

Which is why I think the parent post had a great observation about human problem solving having evolved in a universe inherently formed by the additive effect of every previous decision you've ever made made in your life.

There's a lot of variance in humans, sure, but inescapable stakes/skin in the game from an instinctual understanding that you can't just revert to a previous checkpoint any time you screw up. That world model of decisions and consequences helps ground abstract problem solving ability with a healthy amount of risk aversion and caution that LLMs lack.

Re: Claude Skills

#410

Post by simonw »

codybontecou wrote: post #405
simonw wrote: post #258

Earlier quoted context omitted.

Yeah, AGENTS.md that can point to other files for the LLM to read only if it needs them is effectively the exact same pattern as skills. It also means that any tool that knows how to read AGENTS.md could start using skills today. "if you need to create a PDF file first read the file in skills/pdfs/SKILL.md"

That's where my confusion is. How is this pattern similar to MCP? Can it also authenticate against 3rd party apis, similar to MCP?

If you want to call a third party API from a skill you can use instructions like this:

  To access the GitHub API, use curl 
  to make requests to api.GitHub.com
  and pass the GITHUB_API_KEY
  environment variable in the
  Authorization: Bearer header
Post reply on HN