> Developers can also easily create, view, and upgrade skill versions through the Claude Console.
For coding in particular, it would be super-nice if they could just live in a standard location in the repo.
Claude Skills
51–60 of 443 posts
Re: Claude Skills
#52I 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.
The blurbs can be improved if they aren't effective. You can also invoke skills directly.
The description is equivalent to your short term memory.
The skill is like your long term memory which is retrieved if needed.
These should both be considered as part of the AI agent. Not external things.
Re: Claude Skills
#53getting hard to keep up with skills, plugins, marketplaces, connectors, add-ons, yada yada
If I were to say "Claude Skills can be seen as a particular productization of a system prompt" would I be wrong?
From a technical perspective, it seems like unnecessary complexity in a way. Of course I recognize there are lot of product decisions that seem to layer on 'unnecessary' abstractions but still have utility.
In terms of connecting with customers, it seems sensible, under the assumption that Anthropic is triaging customer feedback well and leading to where they want to go (even if they don't know it yet).
Update: a sibling comment just wrote something quite similar: "All these things are designed to create lock in for companies. They don’t really fundamentally add to the functionality of LLMs." I think I agree.
Re: Claude Skills
#54Basically just rules/workflows from cursor/windsurf, but with a UI.
Re: Claude Skills
#55getting hard to keep up with skills, plugins, marketplaces, connectors, add-ons, yada yada
All these things are designed to create lock in for companies. They don’t really fundamentally add to the functionality of LLMs. Devs should focus on working directly with model generate apis and not using all the decoration.
Re: Claude Skills
#56Aside: I really love Anthropic's design language, so beautiful and functional.
Re: Claude Skills
#57getting 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.
People thought the same in the ‘90’s. The argument that technology accelerates and “software eats the world” doesn’t depend on AI.
It’s not exactly wrong, but it leaves out a lot of intermediate steps.
Re: Claude Skills
#58I love how the promise of free labor motivates everyone to become API first, document their practices, and plan ahead in writing before coding.
Cheaper, not free. Also, no training to learn a new skill. Building a new one that works well is a project, but then it will scale up as much as you like. This is bringing some of the advantages of software development to office tasks, but you give up some things like reliable, deterministic results.
There is an acquisition cost of researching and developing the LLM, but the running cost should not be classified as a wage, hence cost of labor is zero.
Re: Claude Skills
#59getting hard to keep up with skills, plugins, marketplaces, connectors, add-ons, yada yada
Features will be added until morale improves
Re: Claude Skills
#60> Developers can also easily create, view, and upgrade skill versions through the Claude Console. For coding in particular, it would be super-nice if they could just live in a standard location in the repo.
Looks like they do:
> You can also manually install skills by adding them to ~/.claude/skills.