deep-debugger

Guide structured root-cause investigations across multi-file codebases and pipelines.

Updated Apr 19, 2026

Search Tags:#debugging #analysis #evidence #diagnosis #traceability #root-cause

Ready to run

npx skills add https://github.com/mgsystemsdev/POD --skill deep-debugger

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: deep-debugger
Source: https://github.com/mgsystemsdev/POD/tree/main/agent-system-base/.claude/skills/deep-debugger
Command: npx skills add https://github.com/mgsystemsdev/POD --skill deep-debugger

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This diagnostic skill helps engineers perform thorough, evidence-based root-cause analysis of complex system problems before making code changes.

Core Features & Use Cases

Phase-driven diagnosis: read-before-you-think, build an evidence map, produce a precise root-cause, and propose minimal fixes.
Works across multi-file codebases and pipelines; useful for deep-dives when logs, traces, and prompts indicate multiple interacting components.
Generates traceable outputs with file paths and line references to support debugging reviews.

Quick Start

Follow the Phase 1 instructions to begin a diagnostic investigation on a detailed problem prompt.

Frequently Asked Questions about deep-debugger

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I perform root-cause analysis on a multi-file codebase with distributed symptoms?▼

Root-cause analysis on multi-file codebases requires a phase-driven approach: read existing evidence first, build an evidence map across modules, and produce a precise diagnosis before proposing fixes. This ensures traceable debugging across distributed components.

What is evidence-based debugging and when do I need it for integration failures?▼

Evidence-based debugging is a structured investigation method that maps symptoms to root-causes using traceable proof rather than assumptions. You need it for integration failures where symptoms are distributed across multiple interacting components or pipeline stages.

How do I debug complex pipeline failures across multiple interacting components?▼

Debug pipeline failures by following a structured diagnostic process: gather logs and traces, construct an evidence map of interacting components, and propose minimal remediation steps with explicit file paths and line references for safe resolution.

What's the best way to ensure traceability when diagnosing distributed system problems?▼

Traceability in distributed system diagnosis requires generating outputs with explicit file paths and line references throughout the investigation. This approach supports debugging reviews by mapping each piece of evidence back to specific locations in the codebase.

Does deep-debugger work with multi-file codebases that have integration failures across modules?▼

Yes, it works across multi-file codebases and pipelines specifically designed for deep-dives when logs, traces, and prompts indicate multiple interacting components. It handles integration failures where symptoms are distributed across modules.

When should I not use a phase-driven evidence map approach for debugging?▼

Phase-driven evidence mapping may be excessive for single-file bugs with obvious causes where immediate code changes suffice. It is designed for complex, multi-file codebases and pipeline failures requiring thorough root-cause investigation before remediation.