KaseKun

loved it!

> still have access to some decent model

Not really a requirement, if you did fine without the tools before you would do fine again. The difference is you would know which ones are worth manually maintaining

I have no use for this, however I am stunned by the simple and effective solution of using json+sse instead of an API to allow agent interaction Amazing work

You have to leave your local maximum to find the global maximum.

Code doesn't exist in a vacuum though.

Code bases that you "work in" (maintain, etc) solve real world problems, and solving those problems should trump cleanliness every time

Codebases that are clean are typically showcase examples that sit on a shelf to be admired and appreciated.

I have a (relatively well informed) view that people who aledge that "if you used an llm you did no thinking or problem solving" have never in fact used an a llm to generate anything particular complex.

You do indeed need to do quite a bit of thinking and problem solving, to build things with an llm.

If you disagree, repeat this project, so you can share with us how little thinking it required.

I can picture this comment at the 50th percentile on the midwit meme

On either side it says "I just ask the model why it did that"

Good advice. After seeing the capability of the skills for frontend design by impeccable crew ( https://impeccable.style ) i am tempted to make my own `/blog-polish` skill or similar

realistically, though, i quite like writing. The other article i've posted ( https://www.dardar.co/articles/your-data-agent-is-wrong ) is 100% me, but as a consequence it feels kinda preachy and verbose in places haha

I saw a good yt video on this the other day, investigating baking soda and athletics. https://youtu.be/Y_aTfQmqc5o

The creator certainly got pretty crook from ingesting baking soda

I was stubbornly of the same mindset, but had friends and colleagues that raved about skills, i thought it was hype cycle context management - i'm happy to be proven wrong

haha interesting - the article is 99% written by me, but i had gemini review it and sharpen up the send off because it felt weak.

I guess this goes to show that even a subtle touch of an LLM can undermine authenticity.

edit: i've removed that line. I don't like to edit articles after publish (call me old fashioned, but i try to be honest and transparent), in this case though the line adds nothing and your call-out has taught me a good lesson: shit human writing is better than "good" AI writing.

Author here,

> It looks like someone just pointed a LLM at the codebase and asked it to write an article.

Not entirely true. I pointed an LLM at the codebase to get me to the right files for understanding skills, and to map out the dependencies and lifecycles - Then I spent quite a bit of time reading the code myself and writing about it.

An AI review at the end of the writing (to "sharpen" the language) unfortunately brought in a couple of AI fingerprints (note the "mic drop" comment above)

edit: write -> right (its 8am)

A technical breakdown of how agent skills are parsed, rendered, injected, and refreshed in your Claude Code working session.

You lost me at "these are formed using radio signals rather than light"

An excellent read.

I mourn and i celebrate. I can't think of another craft for which the implicit goal was to make itself obsolete, but we've just about done it!

and that is something to celebrate

Not really that insane, hunting is a much faster reward cycle than farming. On the surface, it makes sense that tools for hunting are produced earlier than tools for farming

If yes to all of the above, I will use windowsill

Can it farm a ber rune for me?

No point, old mate just can't deal with anything but perfection. No energy source is clean, so let's not bother.

Now now, there are words that you can say to make your point that don't make you seem deranged.

This is ever so clever! When is your IPO?

I got a score of 25 for "What if everything was spiders?"

I enjoyed the unordered but ranked priority list on the GitHub page

I'm broadly aware that the product is free so "I am the product" with gmail

I don't really care though. None of what you've mentioned, even if true, would stop me from using the product, mostly because of the convenience and extremely high switching-cost.

Excellent idea. I found the UX after clicking send too tedious, so instead i went to gmail and hit schedule send for 2029

Feedback: I opened your page, eager to read, saw the "subscribe to my substack" email popup and just left.

Not salty, just broke my interest. So now I will go about my day without reading your article. p.s. I'm sure it's very good though

Consider saving that popup until I've read some of the article

This looks great! I'm building www.monca.app Maybe we can share notes, I'm far more data than engineer :)

"skip tutorial" was like that onetime i bought mod privilege on twitch using channel points.

first few minutes : yeah this is cool this is what i wanted

not very long later : this is awful, please take it back

People have said "tulips and crypto" when bitcoin was at $800, $5000, $20000, and now at $50000.

I wonder when (if) it will stop?

I also wonder if crypto valuations are a reflection of truly "free market" economics. Where there is little-to-no barrier to entry as a creator or an investor, and there is complete impossibility of counterfeiting assets.

Unfortunately, though this is an excellent story, this is just an example of a bias known as "frequency illusion". It happens with a lot of things, like seeing the clock at 11:11 more than you do at 11:09. Or seeing lots of your make/model car but being blind to the hundred of other variants on the road.

How many times have you opened up your laptop and not seen a Facebook add for something you just did, or something you discussed? You'll never notice those occasions.