What problem does it solve? Random fixes and guess-and-check patching waste hours and introduce new bugs. This Skill enforces a disciplined four-phase debugging process that finds the root cause before any fix is attempted, preventing symptom-only patches and repeated failed fix attempts. ## Core Features & Use Cases - Four-Phase Process: Root cause investigation, pattern analysis, hypothesis testing, and implementation, each with explicit completion checklists. - Tight Feedback Loops: Build fast, deterministic reproduction commands (failing tests, curl scripts, CLI invocations, headless browser checks) that go red on the exact symptom and green when fixed. - Rule of Three: After three failed fixes, stop and question the architecture instead of attempting a fourth patch. - Use Case: A production API intermittently returns wrong data. Instead of guessing, you build a high-repetition repro loop, trace data flow across the API-service-database boundary, form ranked hypotheses, and fix the actual root cause with a regression test. ## Quick Start Ask the agent to debug a failing test or bug using the systematic-debugging process, starting with root cause investigation before proposing any fix.
