What problem does it solve? Hard bugs and performance regressions resist casual code reading; without a reproducible signal, debugging devolves into guessing. This Skill enforces a disciplined six-phase diagnosis loop that builds a tight pass/fail feedback signal first, then reproduces, minimizes, hypothesizes, instruments, fixes, and cleans up. ## Core Features & Use Cases - Feedback loop construction: Builds a red-capable, deterministic, fast reproduction command using failing tests, curl scripts, CLI fixtures, headless browser scripts, trace replay, fuzz loops, or bisection harnesses. - Structured hypothesis testing: Generates 3-5 ranked falsifiable hypotheses, then instruments with tagged debug logs or debugger breakpoints, changing one variable at a time. - Regression testing and cleanup: Writes the regression test before the fix at a correct seam, verifies the original repro no longer fails, and removes all tagged instrumentation. - Use Case: A user reports an export button throwing an error in production. The Skill drives creation of a curl-based repro loop, minimizes the failing scenario, tests ranked hypotheses, applies the fix, and leaves a regression test behind. ## Quick Start Ask the assistant to diagnose the bug where the export button throws an error, following the diagnosing-bugs workflow to build a reproduction loop first.
