What problem does it solve? Hard bugs and flaky performance regressions resist casual code reading; without a reproducible signal, debugging devolves into guessing. This Skill enforces a disciplined diagnosis loop that builds a tight, red-capable feedback signal before any hypothesis is tested. ## Core Features & Use Cases - Feedback Loop Construction: Ten ranked strategies for building a pass/fail signal, from failing tests and curl scripts to Playwright traces, fuzz loops, and git bisect harnesses. - Structured Six-Phase Process: Build a loop, reproduce and minimise, generate ranked falsifiable hypotheses, instrument with tagged debug logs, fix with a regression test, then clean up and post-mortem. - Non-Deterministic Bug Handling: Techniques to raise reproduction rates via repetition, parallelisation, and stress so flaky bugs become debuggable. - Use Case: A user reports an intermittent export failure in production. The Skill guides you to build a replay harness from a captured request, minimise the failing scenario, rank hypotheses, and land a fix with a regression test. ## Quick Start Ask the agent to diagnose the bug where the export button throws an error, following the diagnosing-bugs workflow.
