When experiment code fails or gives wrong results, a clear step-by-step method can save time. This approach helps you categorize errors by type and severity. Then you apply targeted fixes with smart retry logic.
After fixing, you reflect on what went wrong. This helps you avoid the same mistakes in the future. The method limits how many times you retry before changing your whole approach.
It works for common issues like syntax errors, import problems, runtime crashes, and logic mistakes. You get clear instructions for each step, from reading the error to verifying your fix.
Global
mkdir -p ~/.claude/skills/code-debuggingProject
mkdir -p .claude/skills/code-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
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