AI coding agents see an error and immediately edit code. They guess at fixes, get it wrong, and spiral. This skill enforces a strict 5-phase protocol where you CANNOT edit source code until the root cause is identified and confirmed.
Based on claude-debug (full plugin with PreToolUse hook enforcement).
Use this skill when:
Run the failing command/test. Capture the exact error. Run 2-3 times for consistency.
Read code. Add diagnostic logging marked // DEBUG. Re-run with diagnostics. Binary search to narrow down.
// DEBUG marked logging is allowedAnalyze WHY at the isolated location. Use "5 Whys" technique. Remove debug logging.
State: "This is my root cause analysis: [explanation]. Do you agree, or should I investigate further?"
WAIT for user confirmation. Do NOT proceed without it.
Remove all // DEBUG lines. Apply minimal change addressing confirmed root cause.
Run original failing test — must pass. Run related tests. For intermittent bugs, run 5+ times. If verification fails: root cause was wrong, go back to Phase 2.
| Type | Technique |
|---|---|
| Crash/Panic | Stack trace backward — trace the bad value to its source |
| Wrong Output | Binary search — log midpoint, halve search space each iteration |
| Intermittent | Compare passing vs failing run logs — find ordering divergence |
| Regression | git bisect — find the offending commit |
| Performance | Timing at stage boundaries — find the bottleneck |
// DEBUG in phase 2)