What problem does it solve? Hard bugs and performance regressions stall when developers stare at code without a reproducible signal. This Skill enforces a disciplined six-phase diagnosis loop so the root cause is found, fixed, and locked down with a regression test instead of being patched by guesswork. ## Core Features & Use Cases - Feedback-loop construction: Builds a fast, deterministic pass/fail signal using failing tests, curl scripts, CLI fixtures, headless browsers (Playwright/Puppeteer), trace replay, fuzz loops, or git bisect harnesses. - Ranked falsifiable hypotheses: Generates 3-5 hypotheses with explicit predictions before testing, and instruments with tagged debug logs or baseline performance measurements. - Regression testing and post-mortem: Writes the regression test before the fix at a correct seam, cleans up all debug instrumentation, and hands architectural findings off for follow-up. - Use Case: A user reports that the export button intermittently throws an error. The Skill builds a reproduction loop, raises the flake rate until it is debuggable, isolates the cause one variable at a time, and ships a fix guarded by a failing-then-passing test. ## Quick Start Diagnose this bug: the export endpoint intermittently returns a 500 error, and help me reproduce it, find the root cause, and add a regression test.
