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 command (failing test, curl script, headless browser, replayed trace, bisection harness, or fuzz loop) that catches the exact reported symptom before any hypothesis work begins. - 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 test and cleanup discipline: Writes the regression test before the fix at a correct seam, removes all tagged instrumentation, and documents the confirmed root cause. - Use Case: A user reports an intermittent export failure in production. The Skill replays a captured request through the code path, raises the reproduction rate with stress loops, minimizes the failing scenario, tests ranked hypotheses, and lands a fix with a regression test. ## Quick Start Ask the agent to diagnose the bug you are experiencing and describe the exact symptom, error message, or slowdown you observed.
