What problem does it solve? Hard bugs and performance regressions resist casual debugging: staring at code rarely finds the cause, and untested hypotheses waste hours. This Skill enforces a disciplined six-phase diagnosis loop that builds a tight, red-capable feedback signal before any hypothesis is tested. ## Core Features & Use Cases - Feedback loop construction: Builds a fast, deterministic, agent-runnable repro command using failing tests, curl scripts, headless browsers, trace replay, fuzz loops, or bisection harnesses. - Ranked hypothesis testing: Generates 3-5 falsifiable hypotheses, then instruments with tagged debug logs or debugger breakpoints, changing one variable at a time. - Regression test and cleanup: Converts the minimized repro into a failing regression test at a correct seam, verifies the fix, and removes all tagged instrumentation. - Use Case: A user reports that an export endpoint intermittently returns stale data. The Skill builds a curl-based loop that reproduces the failure, minimizes the scenario, tests ranked hypotheses, and lands a fix with a regression test. ## Quick Start Ask the agent to diagnose the bug where the export endpoint intermittently returns stale data and follow the diagnosis loop.
