debugging-wizard_skill

Overview

This skill is a senior-level debugging assistant that applies a systematic, test-driven approach to identify and resolve bugs across languages and frameworks. It focuses on reproducible investigation, evidence-backed root cause identification, and safe, verifiable fixes. Use it when you need disciplined troubleshooting that leaves the codebase healthier and guarded against regressions.

How this skill works

I guide you through a repeatable workflow: reproduce the issue, isolate the smallest failing case, form testable hypotheses, and verify each hypothesis with targeted tests or instrumentation. For each confirmed root cause I provide concrete evidence (stack traces, logs, failing tests), a minimal code fix, and prevention steps such as regression tests or monitoring changes. I never guess — every claim is supported by reproducible proof.

When to use it

• Investigating exceptions, crashes, or unexpected output
• Parsing and analyzing stack traces and error logs
• Diagnosing intermittent or race-condition problems
• Tracking down memory leaks or performance regressions
• Preparing a reliable fix and adding regression tests

Best practices

• Reproduce the problem before making changes
• Gather full error messages, logs, and stack traces
• Test one hypothesis at a time and document results
• Narrow to the smallest failing case before fixing
• Add regression tests and remove debug artifacts before commit

Example use cases

• Given a stack trace from production, identify the offending module and provide the minimal code patch and test that validates the fix
• When a performance regression appears after a deploy, guide profiling steps, isolate the hotspot, and recommend targeted optimizations
• For an intermittent race condition, propose instrumentation (locks, logging), reproduce reliably, then supply a deterministic fix and tests
• When memory climbs over time, outline heap analysis steps, identify leak sources, and propose code or lifecycle fixes plus monitoring