What problem does it solve? Hard bugs and flaky performance regressions resist casual code reading; without a reproducible signal, developers guess at causes and ship unverified fixes. This Skill enforces a disciplined diagnosis loop that builds a tight, red-capable reproduction before any hypothesis is tested. ## Core Features & Use Cases - Feedback Loop Construction: Builds a fast, deterministic pass/fail signal using failing tests, curl scripts, CLI fixtures, Playwright browser automation, trace replay, fuzz loops, or git bisect harnesses. - Structured Six-Phase Process: Guides reproduction and minimization, ranked falsifiable hypotheses, single-variable instrumentation with tagged debug logs, regression-test-first fixes, and cleanup with post-mortem. - Human-in-the-Loop Fallback: Ships a scripts/hitl-loop.template.sh bash template that drives a human through manual reproduction steps and captures observations as parseable KEY=VALUE output. - Use Case: A user reports the export button intermittently throws in production. The Skill builds a Playwright loop that reproduces the failure at a high rate, minimizes the scenario, tests ranked hypotheses one variable at a time, and lands a fix guarded by a regression test. ## Quick Start Ask the agent to diagnose the bug where the export button throws an error, and have it build a failing reproduction loop before proposing any fix.
