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

221–230 of 443 posts

Re: Claude Skills

#221

Post by libraryofbabel »

ibejoeb wrote: post #209
libraryofbabel wrote: post #180

Earlier quoted context omitted.

You forgot mcp-everything! Yes, it's a mess, and there will be a lot of churn, you're not wrong, but there are foundational concepts underneath it all that you can learn and then it's easy to fit insert-new-feature into your mental model. (Or you can just ignore the new features, and roll your own tools. Some people here do that with a lot of success.) The foundational mental model to get the hang of is really just:…

Pretty true, and definitely a good exercise. But if we're going to actual use these things in practice, you need more. Things like prompt caching, capabilities/constraints, etc. It's pretty dangerous to let an agent go hog wild in an unprotected environment.

Oh sure! And if I was talking someone through building a barebones agent, I'd definitely tag on a warning along the lines of "but don't actually use this without XYZ!" That said, you can add prompt caching by just setting a couple of parameters in the api calls to the LLM. I agree constraints is a much more complex topic, although even in my 100-line example I am able to fit in a user approval step before file write or bash actions.

Re: Claude Skills

#223

Post by james_marks »

iLoveOncall wrote: post #168
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.

Except in reality it's ALL marketing terms for 2 things: additional prompt sections, and APIs.

I more or less agree, but it’s surprising what naming a concept does for the average user.

You see a text file and understand that it can be anything, but end users can’t/won’t make the jump. They need to see the words Note, Reminder, Email, etc.

Re: Claude Skills

#224

Post by jrh3 »

The tools I build for Claude Code keep reducing back to just using Claude Code and watching Anthropic add what I need. This is my tool for brownfield projects with Claude Code. I added skills based on https://blog.fsck.com/2025/10/09/superpowers/

https://github.com/RossH3/context-tree - Helps Claude and humans understand complex brownfield codebases through maintained context trees.

Re: Claude Skills

#226

Post by outlore »

I'm struggling to see how this is different from prepackaged prompts. Simon's article talks about skill metadata being used by the model to look up the full prompt as a way to save on context usage. That is analogous to the model calling --help when it needs to use a CLI tool without needing to load up the full man pages ahead of time.

But couldn't an MCP server expose a "help" tool?

Re: Claude Skills

#227

Post by pants2 »

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."

Re: Claude Skills

#228

Post by kingkongjaffa »

awb wrote: post #162
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.

Hopefully there’s a similar “don’t make me think” mantra that comes to AI product design. I like the trend where the agent decides what models, tooling and thought process to use. That seems to me far more powerful than asking users to create solutions for each discreet problem space.

Where I've seen it be really transformative is giving it additive tools that are multiplicative in utility. So like giving an LLM 5 primitive tools for a specific domain and the agent figuring out how to use them together and chain them and run some tools multiple times etc.
Post reply on HN