Claude Skills • Hacker News Board

Re: Claude Skills

#11

Post by crancher » Thu, Oct 16, 2025, 4:55 PM UTC

bicx wrote: post #3

Interesting. For Claude Code, this seems to have generous overlap with existing practice of having markdown "guides" listed for access in the CLAUDE.md. Maybe skills can simply make managing such guides more organized and declarative.

It's interesting (to me) visualizing all of these techniques as efforts to replicate A* pathfinding through the model's vector space "maze" to find the desired outcome. The potential to "one shot" any request is plausible with the right context.

Re: Claude Skills

#12

Post by _pdp_ » Thu, Oct 16, 2025, 4:56 PM UTC

At first I wasn't sure what this is. Upon further inspection skills are effectively a bunch of markdown files and scripts that get unzipped at the right time and used as context. The scripts are executed to get deterministic output.

The idea is interesting and something I shall consider for our platform as well.

Re: Claude Skills

#13

Post by nperez » Thu, Oct 16, 2025, 4:56 PM UTC

Seems like a more organized way to do the equivalent of a folder full of md files + instructing the LLM to ls that folder and read the ones it needs

Re: Claude Skills

#14

Post by meetpateltech » Thu, Oct 16, 2025, 4:56 PM UTC

Detailed engineering blog:

"Equipping agents for the real world with Agent Skills" https://www.anthropic.com/engineering/equipping-agents-for-t...

Re: Claude Skills

#15

Post by jampa » Thu, Oct 16, 2025, 4:56 PM UTC

I think this is great. A problem with huge codebases is that CLAUDE.md files become bloated with niche workflows like CI and E2E testing. Combined with MCPs, this pollutes the context window and eventually degrades performance.

You get the best of both worlds if you can select tokens by problem rather than by folder.

The key question is how effective this will be with tool calling.

Re: Claude Skills

#16

Post by crancher » Thu, Oct 16, 2025, 4:57 PM UTC

Seems like the exact same thing, from front page a few days ago: https://github.com/obra/superpowers/tree/main

Re: Claude Skills

#17

Post by Flux159 » Thu, Oct 16, 2025, 4:57 PM UTC

I wonder how this works with mcpb (renamed from dxt Desktop extensions): https://github.com/anthropics/mcpb

Specifically, it looks like skills are a different structure than mcp, but overlap in what they provide? Skills seem to be just markdown file & then scripts (instead of prompts & tool calls defined in MCP?).

Question I have is why would I use one over the other?

Re: Claude Skills

#18

Post by gordonhart » Thu, Oct 16, 2025, 4:59 PM UTC

phildougherty wrote: post #4

getting hard to keep up with skills, plugins, marketplaces, connectors, add-ons, yada yada

Agree — it's a big downside as a user to have more and more of these provider-specific features. More to learn, more to configure, more to get locked into.

Of course this is why the model providers keep shipping new ones; without them their product is a commodity.

Re: Claude Skills

#19

Post by irtemed88 » Thu, Oct 16, 2025, 5:00 PM UTC

Can someone explain the differences between this and Agents in Claude Code? Logically they seem similar. From my perspective it seems like Skills are more well-defined in their behavior and function?

Re: Claude Skills

#20

Post by ryancnelson » Thu, Oct 16, 2025, 5:00 PM UTC

The uptake on Claude-skills seems to have a lot of momentum already! I was fascinated on Tuesday by “Superpowers” , https://blog.fsck.com/2025/10/09/superpowers/ … and then packaged up all the tool-building I’ve been working on for awhile into somewhat tidy skills that i can delegate agents to:

http://github.com/ryancnelson/deli-gator I’d love any feedback