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 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: Ten ordered strategies for building a red-capable test signal, from failing tests and curl scripts to Playwright traces, fuzz loops, and git bisect harnesses. - 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 and cleanup discipline: Writes regression tests at correct seams before fixing, removes all tagged instrumentation, and records the confirmed root cause in the commit message. - Use Case: A user reports an intermittent export failure in production. The Skill guides building a replay harness from a captured request, minimizing the repro, 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 reproducible feedback loop before proposing any fix.
