What problem does it solve? Hard bugs and performance regressions stall when developers stare at code without a reliable reproduction signal. This Skill enforces a disciplined six-phase loop — build a feedback loop, reproduce, hypothesise, instrument, fix with regression test, and clean up — so debugging converges on the real root cause instead of guesses. ## Core Features & Use Cases - Feedback-loop construction: Ten ranked strategies for building a deterministic pass/fail signal, from failing tests and curl scripts to headless browser runs, trace replay, fuzz loops, and git bisect harnesses. - Ranked falsifiable hypotheses: Generates 3–5 hypotheses with explicit predictions before testing, and tags all debug instrumentation with unique prefixes for one-grep cleanup. - Regression testing and post-mortem: Writes the regression test before the fix at a correct seam, verifies the original repro no longer fails, and records the confirmed root cause in the commit message. - Use Case: A user reports that an export endpoint intermittently returns corrupted data. The Skill builds a loop that replays the failing request 100 times, ranks hypotheses, instruments the boundary between serialization and transport, and lands a fix guarded by a regression test. ## Quick Start Ask the agent to diagnose the bug where the export endpoint intermittently returns corrupted data and follow the structured diagnosis loop.
