Fixing bugs can be messy without a clear process. This approach helps you avoid common mistakes by breaking the work into three steps. First you report the problem clearly. Then you analyze the root cause. Finally you fix it and check that it works. Each step creates a document so you never lose track.
Simple bugs can take a fast track. The AI reads the code and if the cause is obvious and the fix is small, it skips straight to fixing. But you still get a fix note for later reference. Complex bugs follow the full path with human checkpoints at every stage.
This method keeps your codebase healthy and your debugging history clear. No more guessing what changed or why a bug came back. Everything is written down.
Global
mkdir -p ~/.claude/skills/cs-issueProject
mkdir -p .claude/skills/cs-issueSource 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
Systematic Debuggingobra/superpowers
Find the root cause of every bug before attempting any fix to save time
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
Python Performance Optimizationwshobson/agents
Profile and optimize Python code to find and fix performance bottlenecks quickly