| name | debug-helper |
| description | Debug assistant for error analysis, log interpretation, and performance profiling. Use when user encounters errors, crashes, or performance issues. |
Debug Helper
Systematic debugging workflow.
Error Analysis
- Read the error — Full stack trace and error message
- Locate — Find the source file and line
grep -rn "ErrorClass\|error_function" src/
- Context — Read surrounding code (±30 lines)
- Reproduce — Identify minimal reproduction steps
- Root cause — Trace the data flow to find where it goes wrong
- Fix — Minimal change that addresses the root cause
- Verify — Run the failing case to confirm the fix
Log Analysis
- Read the log file or output
- Identify patterns: timestamps, error levels, request IDs
- Correlate events across log lines
- Summarize: what happened, when, and why
Performance Profiling
- Measure — Get baseline numbers first
time <command>
- Profile — Use language-appropriate tools:
- Node.js:
--prof, clinic.js
- Python:
cProfile, py-spy
- Go:
pprof
- Identify — Find the hotspot (usually 1-2 functions)
- Optimize — Fix the bottleneck
- Verify — Measure again, compare with baseline