# Debugging Strategies > Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance iss... Use when this capability is needed. - Skill: `tomevault-io/debugging-strategies-3` (Agent Skill, multi-file: 2 files) - Install (CLI): `npx skillmds@latest add tomevault-io/debugging-strategies-3` - Raw SKILL.md: https://api.skillmd.com/api/skills/tomevault-io/debugging-strategies-3/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: AI & ML - Author: tomevault-io (https://skillmd.com/u/tomevault-io) - Updated: 2026-09-17 - Page: https://skillmd.com/skills/tomevault-io/debugging-strategies-3 --- # Debugging Strategies Transform debugging from frustrating guesswork into systematic problem-solving with proven strategies, powerful tools, and methodical approaches. ## Use this skill when - Tracking down elusive bugs - Investigating performance issues - Debugging production incidents - Analyzing crash dumps or stack traces - Debugging distributed systems ## Do not use this skill when - There is no reproducible issue or observable symptom - The task is purely feature development - You cannot access logs, traces, or runtime signals ## Instructions - Reproduce the issue and capture logs, traces, and environment details. - Form hypotheses and design controlled experiments. - Narrow scope with binary search and targeted instrumentation. - Document findings and verify the fix. - If detailed playbooks are required, open `resources/implementation-playbook.md`. ## Resources - `resources/implementation-playbook.md` for detailed debugging patterns and checklists. --- ## AGI Framework Integration > **Adapted for [@techwavedev/agi-agent-kit](https://www.npmjs.com/package/@techwavedev/agi-agent-kit)** > Original source: [antigravity-awesome-skills](https://github.com/sickn33/antigravity-awesome-skills) ### Memory-First Protocol Retrieve prior error resolutions and debugging strategies. The hybrid search excels here — BM25 finds exact error codes/stack traces while vectors find semantically similar past issues. ```bash # Check for prior debugging/diagnostics context before starting python3 execution/memory_manager.py auto --query "error patterns and debugging solutions for Debugging Strategies" ``` ### Storing Results After completing work, store debugging/diagnostics decisions for future sessions: ```bash python3 execution/memory_manager.py store \ --content "Root cause: memory leak from unclosed DB connections in pool — fixed with context manager" \ --type error --project \ --tags debugging-strategies debugging ``` ### Multi-Agent Collaboration Store error resolutions so any agent encountering the same issue retrieves the fix instantly instead of re-debugging. ```bash python3 execution/cross_agent_context.py store \ --agent "" \ --action "Debugged and resolved critical issue — root cause documented for future reference" \ --project ``` ### Self-Annealing Loop When this skill resolves an error, store the fix in memory AND update the relevant directive. The system gets stronger with each resolved issue. ### BM25 Exact Match Error codes, stack traces, and log messages are best found via BM25 keyword search. The hybrid system automatically uses exact matching for these patterns. --- > Converted and distributed by [TomeVault](https://tomevault.io/claim/techwavedev) — claim your Tome and manage your conversions.