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

291–300 of 443 posts

Re: Claude Skills

#291

Post by fragmede »

corytheboyd wrote: post #177
fragmede wrote: post #146

Earlier quoted context omitted.

Can you be more specific? The simple case seems to be solved, eg if I have an mcp for foo enabled and then ask about a list of foo, Claude will go and call the list function on foo.

> […] and then ask about a list of foo Not OP, but this is the part that I take issue with. I want to forget what tools are there and have the LLM figure out on its own which tool to use. Having to remember to add special words to encourage it to use specific tools (required a lot of the time, especially with esoteric tools) is annoying. I’m not saying this renders the whole thing “useless” because it’s good to have…

I've got a project that needs to run a special script and not just "make $target" at the command line in order to build, and with instructions in multiple . MD files, codex w/ gpt-5-high still forgets and runs make blindly which fails and it gets confused annoyingly often.

ooh, it does call make when I ask it to compile, and is able to call a couple other popular tools without having to refer to them by name. if I ask it to resize an image, it'll call imagemagik, or run ffmpeg and I don't need to refer to ffmpeg by name.

so at the end of the day, it seems they are their training data, so better write a popular blog post about your one-off MCP and the tools it exposes, and maybe the next version of the LLM will have your blog post in the training data and will automatically know how to use it without having to be told

Re: Claude Skills

#292

Post by isodev »

mediaman wrote: post #111
mbesto wrote: post #90

Earlier quoted context omitted.

> Contrast with the way a human learns skills - as we gain experience with a skill, we get better at understanding when it's the right tool for the job. Which is precisely why Richard Sutton doesn't think LLMs will evolve to AGI[0]. LLMs are based on mimicry, not experience, so it's more likely (according to Sutton) that AGI will be based on some form of RL (reinforcement learning) and not neural networks (LLMs). Mor…

It's a false dichotomy. LLMs are already being trained with RL to have goal directedness. He is right that non-RL'd LLMs are just mimicry, but the field already moved beyond that.

Let’s not overstate what the technology actually is. LLMs amount to random token generators that try their best to have their outputs “rhyme” with their prompts, instructions, skills, or what humans know as goals and consequences.

Re: Claude Skills

#294

Post by sharts »

Isn’t all of everything just a bundle of prompts and scripts in various folders with some shortcuts to them all?

So we just narrow the scope of the each thing but all of this prompt organizing feels like we’ve gone from programming with YAML to now Markdown.

Re: Claude Skills

#295

Post by zeroonetwothree »

simonw wrote: post #269
stego-tech wrote: post #248

I’m kind of in stitches over this. Claude’s “skills” are dependent upon developers writing competent documentation and keeping it up to date…which most seemingly can’t even do for actual code they write, nevermind a brute-force black box like an LLM. For those few who do write competent documentation and have well-organized file systems and the risk tolerance to allow LLMs to run roughshod over data, sure, there’s so…

LLMs reward developers who can write. Maybe that's one of the reasons so many developers are pushing back against them!

The classic "you're doing it wrong" response to criticism.

Re: Claude Skills

#296

Post by CryptoBanker »

mbesto wrote: post #190
munchler wrote: post #181

Earlier quoted context omitted.

I agree with this description, but I'm not sure we really want our AI agents evolving in real time as they gain experience. Having a static model that is thoroughly tested before deployment seems much safer.

> Having a static model that is thoroughly tested before deployment seems much safer. While that might true, it fundamentally means it's not going to ever replicate human or provide super intelligence.

> While that might true, it fundamentally means it's not going to ever replicate human or provide super intelligence.

Many people would argue that's a good thing

Re: Claude Skills

#298

Post by simonw »

zeroonetwothree wrote: post #295
simonw wrote: post #269

Earlier quoted context omitted.

LLMs reward developers who can write. Maybe that's one of the reasons so many developers are pushing back against them!

The classic "you're doing it wrong" response to criticism.

The classic "the only thing LLM proponents ever say is "you're doing it wrong"" response!

Re: Claude Skills

#299

Post by toobulkeh »

I implemented a rudimentary version of this based on some BabyAGI loops, called autolearn: autolearn.dev

I love this per-agent approach and the roll calling. I don’t know why they used a file system instead of MCP though. MCP already covered this and could use the same techniques to improve.

Re: Claude Skills

#300

Post by typpilol »

catgary wrote: post #159
fny wrote: post #142

I fear the conceptual churn we're going to endure in the coming years will rival frontend dev. Across ChatGPT and Claude we now have tools, functions, skills, agents, subagents, commands, and apps, and there's a metastasizing complex of vibe frameworks feeding on this mess.

These companies are also biased towards solutions that will more-or-less trap you in a heavily agent-based workflow. I’m surprised/disappointed that I haven’t seen any papers out of the programming languages community about how to integrate agentic coding with compilers/type system features/etc. They really need to step up, otherwise there’s going to be a lot of unnecessary CO2 produced by tools like this.

I kind of do this by making LLM run my linter which has typed lint rules.

The way I can get any decent code out of them for typescript is by having no joke, 60 eslint plugins. It forces them to write actual decent code, although it takes them forever

Post reply on HN