What problem does it solve? Hard bugs and flaky performance regressions resist casual code reading; without a reproducible red signal, debugging devolves into guessing. This Skill enforces a disciplined diagnosis loop that builds a tight pass/fail feedback signal before any hypothesis is tested. ## Core Features & Use Cases - Feedback Loop Construction: Ten ranked techniques for building a red-capable repro, from failing tests and curl scripts to bisection harnesses, differential loops, and property-based fuzzing. - Structured Six-Phase Process: Build a loop, reproduce and minimise, generate 3-5 falsifiable ranked hypotheses, instrument with tagged debug logs, fix with a regression test, then clean up and post-mortem. - Non-Deterministic Bug Handling: Strategies to raise reproduction rates via looped triggers, parallelisation, and stress so flaky bugs become debuggable. - Use Case: A user reports an intermittent export failure. The Skill guides building a CLI replay harness from a captured request, minimising the failing input, ranking hypotheses, and landing a fix with a regression test. ## Quick Start Ask the assistant to diagnose the bug where the export endpoint intermittently returns empty files, following the diagnosing-bugs workflow.
