systematic-debugging or diagnosing-bugs for finding the cause?
Both stop the agent from guessing at fixes, but they enter the problem from different ends. systematic-debugging holds a process until the cause is proven. diagnosing-bugs is closer to a working investigation of the failure in front of you.
The systematic-debugging skill in superpowers runs a four phase root cause analysis instead of trying fixes until the error stops appearing. Use it on bugs that already survived a first attempt, and on anything intermittent, where guess and patch is not just slow but actively misleading.
Best for
Intermittent failures, heisenbugs, and defects that came back after a fix.
Skip if
The cause is obvious from the stack trace and the fix is one line.
Which one to install
Choose systematic-debugging when the failing behaviour is intermittent or nobody can reliably reproduce it, because the value is in refusing to accept an unproven cause. This is the one that stops a session ending in a plausible fix that was never verified.
The diagnosing-bugs skill separates diagnosis from repair: understand what is actually happening, prove it, and only then change code. It directly targets the most common expensive failure in agent assisted debugging, which is a confident patch on a symptom that hides the real defect.
Best for
Bugs that have already survived one attempted fix, and anything intermittent.
Skip if
The failure is obvious and local, where the ceremony costs more than it saves.
Which one to install
Choose diagnosing-bugs when there is a concrete failure you can trigger and you want the investigation moved along rather than formalised. It is the lighter option for the ordinary case where the bug is right there.
These two overlap enough to compete on the same task, so keeping both usually means one of them never fires. If you want both available, narrow one description until it names the situation it is for rather than the activity.