EmptyDrum

That's not the point of the skill.

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).

I feel like that this is fundamentally impossible to solve for. Approximately the effort = planning + checking correctness seems to be constant.

Spam

True (will fix) - but then still, Claude will still not change my pseudo code, but directly translate. I liked that part particularly.

I kept mashing 1 to accept changes in Claude Code, so I automated it. It spawns your command in a PTY and pipes "1" into stdin on a loop.

  npm install -g press-one
  press-one --delay 3000 claude "fix all the bugs"                                                                                                                                                                                                                                        
                  
  Known "features": a slow stream of 11111 appears while the model is thinking, and you can't type because stdin belongs to the machine now. Zero dependencies (just Node + Python for PTY allocation). MIT licensed.

Yes, I partially used their approach which I found very smart. Added a few improvements which you can find on the GitHub.

fyi - this was built inspired by how OpenClaw manages llm-keys. I liked their idea and improved on it. Feedback is welcome.