My core question is why would I use this instead of duckdb and writing SQL as God intended[2]?

---

[1] A clear indication of AI generation

[2] This is a joke.

I don't like how the "times" symbol floats off the line -- it's a visual thing for me (again, irrational).

I recognize that the former is the multiplication symbol, but I don't think it should be used that way.

There are a lot of operational needs that exist downstream from dbt models that combine data from the various source systems.

"""

Totally fair. You can build the first 10-minute demo with an LLM now.

The hard part is usually what comes after. You need editable state, templates, and email-safe HTML. Then come export pipelines, custom blocks, permissions, and all the rendering edge cases that show up with real usage.

AI makes structure more important, not less. That’s why we launched Unlayer Elements. Instead of having an LLM generate a static blob of HTML, it can target structured components that map back into an editable email, web page, or document.

So I'd use AI to prototype it. I'd use Unlayer when that content layer becomes production infrastructure you don't want to maintain yourself.

"""

I made a deslopper[1] tool based on a new skill[2] I saw on twitter earlier. It's still a little smelly imo, but better.

---

[1] https://deslop.btst.workers.dev

[2] https://github.com/petergyang/no-ai-slop

It might be overkill features-wise, but there's a free tier and it likely won't be left for dead anytime soon.

Re: README -- I can't recall a specific repo with one off the top of my head so took a stab at editing yours[1] instead of hunting around. It's not perfect -- I'd want to trim the bullet lists further, for example -- but is much more scannable in my opinion.

---

[1] https://gist.github.com/thedatadavis/fbbe556348eb43731659456...

In a time where people are reading less and less code, introducing a new surface area -- that you don't have a good feel for -- to handle orchestration feels risky.

---

[1] https://github.com/dbt-labs/dbt-core

[2] https://github.com/pdthq/pdt

What about skillscript is unique that couldn't be done with bash or python as a permissioned tool? (Trying to understand where you see the difference.)

---

My original impression from the repo was that the language/toolkit is overengineered, but then I saw on the website that the intention is for the agents to write their own tools. That helps explain some of the complexity.

I think the rest of the perceived complexity is the over-explaining in the README.

I don't think anyone's going to really engage with all of that so you might have better luck chopping it down 80% to only highlight the stuff that matters.

Source: https://chatgpt.com/share/6a42dd8a-4e28-83e8-9ef7-6ba56d665c...

I'm not sure I understand why the second or third compile would work, but not the first.

Are the scores here normalized such that each point difference is equidistant?