Claude Skills • Hacker News Board

Re: Claude Skills

#31

Post by candiddevmike » Thu, Oct 16, 2025, 5:09 PM UTC

crancher wrote: post #11

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.

> The potential to "one shot" any request is plausible with the right context.

You too can win a jackpot by spinning the wheel just like these other anecdotal winners. Pay no attention to your dwindling credits every time you do though.

Re: Claude Skills

#32

Post by matthewaveryusa » Thu, Oct 16, 2025, 5:09 PM UTC

hansonkd wrote: post #28

phildougherty wrote: post #4

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

Thats the start of the singularity. The changes will keep accelerating and less and less people will be able to keep up until only the AIs themselves know how to use.

Nah, we'll create AI to manage the AI....oh

Re: Claude Skills

#33

Post by azraellzanella » Thu, Oct 16, 2025, 5:09 PM UTC

"Keep in mind, this feature gives Claude access to execute code. While powerful, it means being mindful about which skills you use—stick to trusted sources to keep your data safe."

Yes, this can only end well.

Re: Claude Skills

#34

Post by dang » Thu, Oct 16, 2025, 5:10 PM UTC

meetpateltech wrote: post #14

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

Thanks, we'll put that link in the toptext as well

Re: Claude Skills

#35

Post by ebiester » Thu, Oct 16, 2025, 5:10 PM UTC

sshine wrote: post #10

I love how the promise of free labor motivates everyone to become API first, document their practices, and plan ahead in writing before coding.

It helps that you can have the "free" labor document the processes and build the plan.

Re: Claude Skills

#36

Post by m3kw9 » Thu, Oct 16, 2025, 5:10 PM UTC

I feel like this is making things more complicated than it needs to be. LLMs should automatically do this behind you, you won’t even see it.

Re: Claude Skills

#37

Post by Imnimo » Thu, Oct 16, 2025, 5:11 PM UTC

I feel like a danger with this sort of thing is that the capability of the system to use the right skill is limited by the little blurb you give about what the skill is for. 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. But Claude is always starting from ground zero and skimming your descriptions.

Re: Claude Skills

#38

Post by fridder » Thu, Oct 16, 2025, 5:12 PM UTC

All of these random features is just pushing me further towards model agnostic tools like goose

Re: Claude Skills

#39

Post by RamtinJ95 » Thu, Oct 16, 2025, 5:13 PM UTC

j45 wrote: post #27

nperez wrote: post #13

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

If so it would be most welcome since LLMs doesn't always consistently follow the folder full of MD files to the same depth and consistency.

what makes it more likely that claude would read these .md files then?

Re: Claude Skills

#40

Post by asdev » Thu, Oct 16, 2025, 5:17 PM UTC

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.