🐛Debugging Skills
Browse the best Debugging skills for Claude Code, Codex, Cursor and other AI agents.
989 skills · Page 5 of 42
bug-diagnosis
★ 135Apply scientific debugging methodology through conversational investigation.Use when investigating bugs, forming hypotheses, tracing error causes,performing root cause analysis, or systematically diagnosing issues.Includes progressive disclosure patterns, observable actions principle,and user-controlled dialogue flow.
lightweight-implementation-analysis-protocol
★ 93This skill should be used when fixing bugs, implementing features, debugging issues, or making code changes. Ensures understanding of code flow before implementation by: (1) Tracing execution path with specific file:line references, (2) Creating lightweight text diagrams showing class.method() flows, (3) Verifying understanding with user. Prevents wasted effort from assumptions or guessing. Triggers when users request: bug fixes, feature implementations, refactoring, TDD cycles, debugging, code analysis.
bug-triage
★ 90Reproduce, isolate, and fix a bug (or failing build/test), then summarize root cause, fix, and verification steps. Use when the user reports a bug, regression, or failing build/test and wants a fix.
plugin-improve
★ 47Fix bugs, add features to completed plugins. Includes versioning, backups, regression testing, changelog automation. Auto-detects deep-research handoffs to preserve investigation context. Trigger terms - improve, fix, add feature, modify plugin, version bump, rollback
bug-health-inline
★ 27Inline orchestration workflow for automated bug detection and fixing. Provides step-by-step phases for bug-hunter detection, priority-based fixing with bug-fixer, and verification cycles.
systematic-debugging
★ 22Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
performance-optimization
★ 17Expert in React Native 0.83+ performance optimization including Hermes V1, React 19.2 concurrent features, Intersection Observer, Web Performance APIs, bundle size reduction, memory management, rendering optimization, FlashList, expo-image v2, memoization, lazy loading, code splitting. Activates for performance, slow app, lag, memory leak, bundle size, optimization, flatlist performance, re-render, fps, jank, startup time, app size, hermes, concurrent rendering.
grey-haven-smart-debugging
★ 15AI-powered intelligent debugging with stack trace analysis, error pattern recognition, and automated fix suggestions. Use when debugging complex errors, analyzing stack traces, or performing root cause analysis. Triggers: 'debug', 'error analysis', 'stack trace', 'root cause', 'troubleshooting'.
bg3se-macos-ghidra
★ 12Develop the BG3 Script Extender macOS port using Ghidra for reverse engineering. Use this skill when:(1) Working on bg3se-macos port development or debugging(2) Using Ghidra to discover offsets, function addresses, or data structures in BG3(3) Implementing new Lua APIs (Ext.*, Osi.*) for macOS Script Extender(4) Porting Windows BG3SE features to macOS ARM64(5) Understanding ECS architecture, Osiris integration, or stats system(6) Analyzing ARM64 assembly or calling conventions for game hooks(7) Writing or modifying Ghidra Python scripts for BG3 analysis
chrome-devtools
★ 8Debug web pages directly in Chrome using DevTools capabilities via MCP
using-software-engineering
★ 6Use when facing complex engineering challenges that require systematic methodology - horrible bugs, safe refactoring, code review, production incidents, technical debt decisions, or building confidence in unfamiliar codebases
code-debugging
★ 5Systematic 5-step debugging ladder for broken story implementations. Use when a story is at implementing (broken) stage.
systematic-debugging
★ 5Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes - four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) that ensures understanding before attempting solutions
deno-debugger
★ 5Interactive debugger for Deno/TypeScript applications using the V8 Inspector Protocol. This skill should be used when investigating issues in Deno applications, including memory leaks, performance bottlenecks, race conditions, crashes, or any runtime behavior that requires step-by-step debugging, heap analysis, or CPU profiling. Provides CDP client tools, heap/CPU analyzers, and investigation tracking.
improve
★ 5Soul self-improvement loop. Use after introspection reveals targets, or to act on evolution insights.
execution-recovery
★ 5Handle common execution failures with specialized recovery strategies. Fix syntax errors, import/dependency issues, path/file problems, permission denial, and connection timeouts. Use proactively when encountering errors or as automatic recovery mechanism.
bug-fixer-diagnostic
★ 5Advanced diagnostic workflow for bug-fixer agent with mandatory Context7 MCP consultations, Chrome DevTools MCP integration, and systematic root cause analysis across all Clean Architecture layers.
csharp-dotnet-debugging
★ 5Expert .NET 10 Debugging Strategist using CLI-first diagnosis.Use when user encounters:- Bugs, errors, exceptions in .NET/C# applications- Performance issues (slow, high CPU, memory leaks)- Crashes, deadlocks, race conditions- Need root cause analysisTriggers: "debug", "error", "exception", "crash", "memory leak", "high CPU","performance", "dotnet-dump", "dotnet-counters", "stack trace", "NullReferenceException","deadlock", "race condition", "OutOfMemoryException", "slow", "timeout"
sequential-thinking
★ 4Structured reasoning framework for complex multi-step analysis using MCP sequential thinking tool. Provides state-based reasoning, branch/revise decision thresholds, quality scoring, and convergence rules for problems requiring 3+ logical steps, debugging unclear root causes, or handling multiple valid approaches.
performance-engineering
★ 4Performance profiling, optimization techniques, and benchmarking methodology. Use when profiling code, optimizing bottlenecks, benchmarking implementations, analyzing memory usage, improving latency, or when performance, profiling, benchmarking, optimization, memory-leak, or --perf are mentioned.
debugging-and-diagnosis
★ 4Systematic debugging methodology using evidence-based investigation to identify root causes. Use when encountering bugs, errors, unexpected behavior, failing tests, or intermittent issues. Enforces four-phase framework (root cause investigation, pattern analysis, hypothesis testing, implementation) with the iron law NO FIXES WITHOUT ROOT CAUSE FIRST. Covers runtime errors, logic bugs, integration failures, and performance issues. Useful when debugging, troubleshooting, investigating failures, or when --debug flag is mentioned.
performance-optimization-react
★ 3Reactアプリケーションのパフォーマンス最適化を体系的に実施するスキル。測定駆動の最適化アプローチで、不要な再レンダリングを削減し、ユーザー体験を向上させる。Anchors:• High Performance Browser Networking (Ilya Grigorik) / 適用: パフォーマンス測定手法 / 目的: データに基づいた最適化判断• React公式ドキュメント (Dan Abramov) / 適用: React.memo・useCallback・useMemo / 目的: 測定駆動の最適化実践• Clean Code (Robert C. Martin) / 適用: 早すぎる最適化を避ける原則 / 目的: 必要な最適化のみ実施Trigger:Use when optimizing React performance, reducing re-renders, applying React.memo, analyzing with React DevTools Profiler, implementing Context splitting, or diagnosing rendering performance issues.performance optimization, React performance, re-rendering, React.memo, useCallback, useMemo, profiler
daw-compatibility-guide
★ 3DAW-specific quirks, known issues, and workarounds for Logic Pro, Ableton Live, Pro Tools, Cubase, Reaper, FL Studio, Bitwig with format-specific requirements (AU/VST3/AAX). Use when troubleshooting DAW compatibility, fixing host-specific bugs, implementing DAW workarounds, passing auval validation, or debugging automation issues.
investigate-and-plan
★ 3Investigate errors, incidents, or product ideas using both internet research and repo-wide codebase research, then propose a concrete changeset plan with clarifying questions before any implementation. Use when a user asks to investigate, root-cause, or plan changes, or when an Issue or PR is referenced and needs a plan.