What problem does it solve? Hard bugs and performance regressions resist casual debugging: staring at code rarely finds the cause. This Skill enforces a disciplined six-phase diagnosis loop that builds a tight, red-capable feedback signal first, then reproduces, minimises, hypothesises, instruments, fixes, and cleans up. ## Core Features & Use Cases - Feedback loop construction: Ten ranked strategies for building a pass/fail signal, from failing tests and curl scripts to replayed traces, fuzz loops, bisection harnesses, and human-in-the-loop bash scripts. - Structured hypothesis testing: Generates 3-5 ranked, falsifiable hypotheses before testing, then instruments one variable at a time with tagged debug logs for easy cleanup. - Regression locking: Turns the minimised repro into a failing regression test at a correct seam before applying the fix, with a mandatory cleanup checklist. - Use Case: A user reports an intermittent production error. The Skill guides building a high-reproduction-rate loop, minimising the failing scenario, ranking hypotheses, and landing a fix with a regression test. ## Quick Start Ask the assistant to diagnose the bug where the export button throws an intermittent error, following the phased diagnosis loop.
