investigate

Identify root causes of bugs by gathering symptoms, reading code, and testing hypotheses.

Updated Jul 3, 2025
One-click install
npx skills add https://github.com/andrew-t-james/dotfiles --skill investigate-andrew-t-james
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: investigate
Source: https://github.com/andrew-t-james/dotfiles/tree/main/dot_claude/skills/investigate
Command: npx skills add https://github.com/andrew-t-james/dotfiles --skill investigate-andrew-t-james

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Gather symptoms, read code, and test hypotheses.

Core Features & Use Cases

  • Structured root-cause workflow spanning symptoms collection, code reading, hypothesis testing, and verification.
  • Guided debugging across codebases and multi-stage fixes.
  • Reproducible, testable steps that help you confirm root cause before shipping changes.

Quick Start

Initiate a root-cause investigation by collecting symptoms, reading the relevant code, and outlining a plan.

Frequently Asked Questions about investigate

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

FAQPage Schema
How do I identify the root cause of a bug in my codebase?

To find a root cause, you collect symptoms, read the relevant code, and test hypotheses systematically. This structured workflow spans five phases from initial symptom collection through code reading to final verification, ensuring you confirm the actual failure before applying fixes.

What is the best way to structure a debugging workflow for complex code?

A structured debugging workflow spans five phases: symptom collection, code reading, hypothesis testing, reproduction, and verification. Following these distinct phases ensures you methodically narrow down failures and confirm the root cause across complex codebases before committing changes.

How do I test debugging hypotheses without guessing the fix?

Testing debugging hypotheses requires reading code to outline a plan and executing reproducible, testable steps. By validating each hypothesis against actual symptoms, you confirm the root cause through evidence rather than guessing before you ship any code changes.

Can I use a structured root-cause workflow across different debugging tasks?

Yes, a structured root-cause workflow applies across diverse codebases and multi-stage debugging tasks. By standardizing on symptom collection, code reading, and hypothesis testing, you can reproduce failures and guide fixes consistently regardless of the specific bug context.

Why should I verify the root cause before shipping code changes?

Verifying the root cause before shipping changes ensures you are fixing the actual failure rather than a secondary symptom. The workflow's final phase confirms that your tested hypotheses and code reading accurately reproduce the bug, preventing incomplete or incorrect fixes.