When you face a bug or a test failure, do not guess. Random fixes waste time and often create new problems. The core rule is simple. Find the root cause before you try any fix.
This process has four phases. First, investigate the root cause. Read error messages carefully. Reproduce the problem. Check recent changes. Trace data flow. Second, analyze patterns by comparing working and broken code. Third, apply the fix only after understanding the real source. Fourth, verify the fix works.
Follow each phase in order. Do not skip. Even simple bugs have root causes. This method saves time and prevents rework. It works for any technical issue from test failures to production bugs.
Global
mkdir -p ~/.claude/skills/systematic-debuggingProject
mkdir -p .claude/skills/systematic-debuggingSource Repository
Azure Diagnosticsmicrosoft/azure-skills
Debug Azure production issues with systematic diagnostics and AI-powered tools
Azure Messagingmicrosoft/azure-skills
Troubleshoot and fix Azure messaging SDK errors for Event Hubs and Service Bus
Use My Browserxixu-me/skills
Work inside your live browser session for real page inspection and debugging
Diagnosemattpocock/skills
A step-by-step debug loop for finding and fixing hard bugs
Diagnosing Bugsmattpocock/skills
Build a tight feedback loop to find any bug fast
Safe Debuglllllllama/rigorpilot-skills
Debug deep learning failures safely with conservative diagnosis and minimal patches
Firebase Crashlyticsfirebase/agent-skills
Set up crash reporting for your Android or iOS app with ease
Golang Troubleshootingsamber/cc-skills-golang
Find and fix Go bugs systematically using debugging tools and methods