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

391–400 of 443 posts

Re: Claude Skills

#391

Post by ashtonshears »

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…

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 steps, but for a new user it can help see ways to use the tools

Re: Claude Skills

#392

Post by jon-wood »

ewoodrich wrote: post #272
kmacdough wrote: post #154

Earlier quoted context omitted.

This is one of known hardest parts of RL. The short answer is human feedback. But this is easier said than done. Current models require vastly more learning events than humans, making direct supervision infeasable. One strategy is to train models on human supervisors, so they can bear the bulk of the supervision. This is tricky, but has proven more effective than direct supervision. But, in my experience, AIs don't s…

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 deciding the problem lies anywhere but their initial model of how this should work. Quite often that developer has been me, although I like to hope I've learned to be more skeptical when that thought crosses my mind now.

Re: Claude Skills

#393

Post by ashtonshears »

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…

Maybe react native if you like react

Re: Claude Skills

#394

Post by ashtonshears »

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…

Learning how to get it to run build steps was a big boost in my initial productivity when learning the cli tools

Re: Claude Skills

#395

Post by dang »

skylurk wrote: post #207
simonw wrote: post #89

I accidentally leaked the existence of these last Friday, glad they officially exist now! https://simonwillison.net/2025/Oct/10/claude-skills/

Woah, Jesse's blog has really come alive lately. Thanks for highlighting this post.

Discussed here btw:

Superpowers: How I'm using coding agents in October 2025 - https://news.ycombinator.com/item?id=45547344 - Oct 2025 (231 comments)

Re: Claude Skills

#396

Post by rafaelmn »

JimDabell wrote: post #308
pants2 wrote: post #227

Earlier quoted context omitted.

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 disagree. You wrap this up in a container / runtime spec. + package index and suddenly you’ve got an agent that can dynamically extend its capabilities based upon any skill that anybody has shared. Instead of `uv add foo` for Python packages you’ve got `skill add foo` for agent skills that the agent can run whenever they have a matching need.

Fundamentally you're getting hyped over a framework to append text to your prompt ?

Re: Claude Skills

#397

Post by exographicskip »

lukev wrote: post #112
pixelpoet wrote: post #56

Aside: I really love Anthropic's design language, so beautiful and functional.

I agree 100%, except for the logo, which persistently looks like something they... probably did not intend.

First time I saw it I immediately thought of Vonnegut's logo

Re: Claude Skills

#398

Post by KingOfMyRoom »

Arkhaine_kupo wrote: post #386
KingOfMyRoom wrote: post #330

Earlier quoted context omitted.

You have a great way of demystifying things. Thanks for the insights here! Do you think a non-programmer could realistically build a full app using vibe coding? What fundamentals would you say are essential to understand first? For context, I’m in finance, but about 8 years ago I built a full app with Angular/Ionic (live on Play Store, under review on Apple Store at that time) after doing a Coursera specialization. T…

> Do you think a non-programmer could realistically build a full app using vibe coding? For personal or professional use? If you want to make it public I would say 0% realistic. The bugs, security concerns, performance problems etc you would be unable to fix are impossible to enumerate. But even if you had a simple loging and kept people's email and password, you can very easily have insecure dbs, insecure protection…

Ideally, I want this to grow into a proper startup. I’m starting solo for now, but as things progress, I’d like to bring in more people. I’m not a tech, product or design person, but AI gives me hope that I can at least get an MVP out and onboard a few early users.

For auth, I’ll be using Supabase, and for the MVP stage I think Lovable should be good enough to build and test with maybe a few hundred users. If there’s traction and things start working, that’s when I’d plan to harden the stack and get proper security and code reviews in place.

Re: Claude Skills

#399

Post by babyshake »

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/

MCP is a protocol meant for general use for clients, which Claude Skills seems more proprietary. To what extent is Skills expected to be something that other clients, such as web based clients could adopt? To some extent it would probably make sense to expose through the MCP SDK?

Re: Claude Skills

#400

Post by saltwounds »

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…

OpenAI and Anthropic's real moat is hardware. For local LLMs, context length and hardware performance are the limiting factors. Qwen3 4B with a 32,768 context window is great. Until it begins filling up and performance drops quickly.

I use local models when possible. MCPs work well, but their large context injection makes switching to an online provider the no-brainer.

Post reply on HN