6 months ago a few people [https://news.ycombinator.com/item?id=44940089] agreed that LLMs are very good at translating Pseudo-code to real code. I agree. Also, writing pseudo code somewhat makes me feel a similar state of flow. Maybe even more, because no compiler/interpreter annoys me about syntax issues. Now, I built this:
https://github.com/HalfEmptyDrum/Pseudo-Code-Flow
It is basically a Claude Code skill. You can call it on a .pseudo text file with /translate. It will obviously translate the pseudo code into your specified language. This would be nice and all, but I included another subtle but useful feature:
*This is probably the most useful feature and fundamentally changed my coding*:
The LLM will suggest changes (design, architecture, functionality, ...) to your code, but will roughly use your pseudo code style.
I think of pseudo code as the semantic body that is closest to how the code/algorithm is represented in my head. When Claude then answers in my language instead of Python/C++/... (which has lots of boilerplate to make it work), it resonates much easier with me.
Let me know what you think!
> The LLM will suggest changes (design, architecture, functionality, ...) to your code, but will roughly use your pseudo code style.
So it will change your architecture, but keep your line-by-line logic? Is this like a self-driving car that takes you to the wrong destination, but accurately follows traffic laws on the way?
Give me the opposite - something that builds exactly what I designed, but has the freedom to get there in better ways than I suggest.
It won't keep the logic. It is encouraged to change the line-by-line as well as the overall logic!
Btw, I got inspired by this: https://www.williamjbowman.com/blog/2026/03/05/against-vibes...
Really useful read!
Great point on the flow state with pseudo code. The gap I keep running into is what comes after – once the translated code ships to production, knowing quickly whether it actually behaves as intended is still mostly manual. Curious if others have thoughts on that part of the loop.
I feel like that this is fundamentally impossible to solve for. Approximately the effort = planning + checking correctness seems to be constant.
Why would that be any more manual than it has been before? You still write or have Claude to write unit and integration tests thst you review
LLMs work perfectly well without a pseudocode skill. It natively understands pseudocode just as well as it understands Indonesian.
That's not the point of the skill.
feedback: your psuedo code example is just product requirements and not actual psuedo code. and I think if you wrote psuedo code it would just work as is without a skill
True (will fix) - but then still, Claude will still not change my pseudo code, but directly translate. I liked that part particularly.
https://github.com/HalfEmptyDrum/Pseudo-Code-Flow
the link again
[flagged]
I agree - in the end we have some fuzzy turing machine when writing in pseudo code. I think it is inherently hard to get this right. I also think that these decisions about control flow etc should stay with the developer given I find it very rewarding and LLMs are not very good at it yet (even though they have promised us the improvements for the past 5 years lol).