What problem does it solve? Random fixes and quick patches waste time, mask underlying issues, and introduce new bugs. This Skill enforces a disciplined debugging methodology that finds the actual root cause before any fix is attempted, even under time pressure or social pressure to take shortcuts. ## Core Features & Use Cases - Four-Phase Process: Structured workflow covering Root Cause Investigation, Pattern Analysis, Hypothesis Testing, and Implementation, with explicit gates between phases. - Pressure-Resistant Rules: Anti-patterns, red flags, and rationalization tables that catch shortcut behavior like "just one quick fix" or shotgun debugging. - Supporting Techniques: Includes root-cause tracing through call stacks, defense-in-depth validation at multiple layers, condition-based waiting to replace flaky timeouts, and a test-polluter bisection script. - Use Case: A test fails intermittently in CI. Instead of adding arbitrary sleep delays, follow Phase 1 to reproduce and gather evidence, trace the bad value to its source, form a single hypothesis, and verify the fix with a failing test case. ## Quick Start Ask the AI to debug a failing test or production bug using the systematic-debugging skill and require root cause investigation before any fix is proposed.
