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

421–430 of 443 posts

Re: Claude Skills

#421

Post by mathieudombrock »

KingOfMyRoom wrote: post #340
felixhammerl wrote: post #333

Earlier quoted context omitted.

If your app has to display stuff, you have no code kits available that can help you out. No vibe coding needed. If your app has to do something useful, your app just exploded in complexity and corner cases that you will have to account for and debug. Also, if it does anything interesting that the LLM has not yet seen a hundred thousand times, you will hit the manual button quite quickly. Claude especially (with all i…

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…

I've always wanted to make an app like this. I think you could do a lot with procedural generation and some clever DSP.

Re: Claude Skills

#422

Post by re5i5tor »

simonw wrote: post #410
codybontecou wrote: post #405

Earlier quoted context omitted.

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

Simon, this won't work, will it? The code execution environment can reach the internet?

Re: Claude Skills

#423

Post by anandvc »

Claude Skills are going to be the end of all human mental labor, but in a good way.

Eventually, we shall, as a human race working together, also figure out how to generalize this to all AI models, all robotics, and all human skills.

My friend Christopher Santos-Lang wrote a fantastic paper on how every strategy for any given Skill can be benchmarked against every other strategy such that we always end up with the best strategies in our shared universal repository of Skills. See https://arxiv.org/abs/2503.20986

Re: Claude Skills

#424

Post by Yeroc »

asdev wrote: post #40

I wonder what the accuracy is for Claude to always follow a Skill accurately. I've had trouble getting LLMs to follow specific workflows 100% consistently without skipping or missing steps.

We also have the same issues with our fellow humans. LLMs do not replace the need for imperative programs that reliably execute well-defined steps. Turn it inside out. Use the LLM to write the imperative program to execute the workflow. Where necessary, insert the LLM into the workflow to perform the task(s) that can't be done imperatively.

Re: Claude Skills

#425

Post by simonw »

re5i5tor wrote: post #422
simonw wrote: post #410

Earlier quoted context omitted.

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

Simon, this won't work, will it? The code execution environment can reach the internet?

It can if you are running it through Claude Code on your own machine.

The https://claude.ai environment has very limited network access - it can install packages from PyPI and NPM and clone repositories from github.com but it can't access any other domain, including api.github.com.

Re: Claude Skills

#426

Post by skissane »

alvis wrote: post #354
skissane wrote: post #339

Earlier quoted context omitted.

> You forgot mcp-everything! One great thing about the MCP craze, is it has given vendors a motivation to expose APIs which they didn’t offer before - real example, Notion’s public REST API lacks support for duplicating pages.. yes their web UI can do it, calling their private REST API, but their private APIs are complex, undocumented, and could stop working at any time with no notice. Then they added it to their MCP…

Well. I bet Notion simply forget some of APIs are private before. I started developing using Notion APIs on the first day it got released. They have constant updates and I have seen lots of improvement. There is just no reason why they intentionally want to make the duplicate page API on MCP but not api. PS. Just want to say, Notion MCP is still very buggy. It can't handle code block, nor large page very well

> There is just no reason why they intentionally want to make the duplicate page API on MCP but not api.

I have no idea what is going on inside Notion, but if I guess - the web UI (including the private REST API which backs it), the public REST API, and the AI features are separate teams, separate PMs, separate budgets - so it is totally unsurprising they don’t all have the same feature set. Of course, if parity were an executive priority, they could get there-but I can only assume it isn’t.

Re: Claude Skills

#427

Post by arendtio »

So the real question here is, why do you need such a feature in the first place? I mean, it is helpful, even when the LLM creates the skill files itself. But why does it make such a big difference when the knowledge can be generated from the LLM?

Why does it help to push the knowledge in the context explicitly?

Re: Claude Skills

#429

Post by timcobb »

timcobb wrote: post #376
hu3 wrote: post #249

Earlier quoted context omitted.

i found it useful and coinstructive to post it here also. no reason not to.

In my opinion because this is a discussion about this announcement, and it kinda feels like with not one but _two_ top-level posts, Simon is just kinda trying to hijack this conversation and turn it into a conversation about his posts. I'm not saying Simon is spamming, because there's definitely some relevance here. But I am saying Simon is attention-seeking in an unbecoming manner. Simon's posts make the homepage re…

See https://news.ycombinator.com/item?id=45619537 ?

Re: Claude Skills

#430

Post by re5i5tor »

simonw wrote: post #425
re5i5tor wrote: post #422

Earlier quoted context omitted.

Simon, this won't work, will it? The code execution environment can reach the internet?

It can if you are running it through Claude Code on your own machine. The https://claude.ai environment has very limited network access - it can install packages from PyPI and NPM and clone repositories from github.com but it can't access any other domain, including api.github.com.

;-) Confirmed by trying. I'm working on an AI-frontend "documents-as-code" tool, and having this as a skill that works across all Claude surfaces would be a huge win. Unfortunately it looks like that's not gonna happen today because ^^ ...

Looks like Claude Desktop and/or Claude Code + a non-big-fat-pig MCP (aka "not GitHub's official version") will be needed.

Here's hoping that Anthropic solves "safe external access / auth from code execution tool" soon.

EDIT - add last sentence

Post reply on HN