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 browsers, trace replay, fuzz loops, or bisection harnesses. - Ranked Hypothesis Testing: Generates 3-5 falsifiable hypotheses with explicit predictions, then instruments with tagged debug logs or debugger breakpoints, changing one variable at a time. - Regression Test Discipline: Writes the regression test before the fix at a correct seam, verifies the original repro no longer fails, and removes all tagged instrumentation during cleanup. - Use Case: A user reports that an export endpoint intermittently throws a 500 error. The Skill guides building a curl-based loop that reproduces the failure, minimizing the input payload, testing ranked hypotheses, and landing a fix with a regression test. ## Quick Start Ask the agent to diagnose the bug where the export button throws an error, and have it build a reproduction loop before proposing any fix.
