autoresearch:debug

Systematic debugging with falsifiable hypotheses is a scientific method for bug hunting that structures investigations into a loop: observing, hypothesizing, designing tests, running tests, and updating active hypothesis sets to isolate root causes.

To find a root cause, form falsifiable hypotheses, design specific tests to challenge them, run the tests, and update your hypothesis sets. This Skill orchestrates the investigation loop and logs active and eliminated hypotheses in a structured debug directory.

Yes, scientific bug hunting using this Skill requires Python for scripting and various command-line tools to design tests, run investigations, and validate falsifiable hypotheses during the debugging process.

The best way to track eliminated hypotheses is to use a structured output directory. This Skill automatically generates a debug folder with files specifically logging active hypotheses, eliminated hypotheses, and findings.

A limitation of scientific debugging is that it requires Python and command-line tool proficiency. Users must methodically form and test falsifiable hypotheses rather than relying on ad-hoc inspection to resolve complex bugs.