investigate

Guide root-cause debugging through four investigation phases before proposing fixes.

9|3|Updated Jan 29, 2022
One-click install
npx skills add https://github.com/I194/PMTools_2.0 --skill investigate-i194
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: investigate
Source: https://github.com/I194/PMTools_2.0/tree/main/.claude/skills/gstack/investigate
Command: npx skills add https://github.com/I194/PMTools_2.0 --skill investigate-i194

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Systematic debugging with root cause investigation to avoid masking symptoms. The Iron Law: no fixes without root cause. Proactively invoke this skill when the user encounters errors, 500s, stack traces, or unexpected behavior.

Core Features & Use Cases

  • Four phases: investigate, analyze, hypothesize, implement.
  • Proactive invocation when troubleshooting is needed.
  • Works with Bash, Read, Write, Edit, Grep, Glob, AskUserQuestion, WebSearch to guide root-cause analysis.

Quick Start

Ask Claude to start the investigate cycle to identify the root cause before proposing fixes.

Frequently Asked Questions about investigate

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

FAQPage Schema
How do I find the root cause of an error instead of just fixing the symptoms?

Root-cause debugging enforces an Iron Law: no fixes until the actual cause is identified. It guides you through a four-phase investigation cycle to gather symptoms and propose evidence-based fixes rather than masking underlying problems.

What is the best way to debug unexpected crashes and 500 errors across a codebase?

Debugging unexpected crashes and 500 errors requires a systematic investigation applying Bash, Grep, and Glob to gather symptoms. You reproduce the issue, analyze the evidence, hypothesize the root cause, and only then implement an evidence-based fix.

How do I start a systematic investigation workflow for troubleshooting stack traces?

To start a systematic investigation workflow for troubleshooting stack traces, invoke the investigate cycle. This initiates a structured four-phase process—investigate, analyze, hypothesize, implement—to analyze errors before applying any code fixes.

Can I use this root-cause analysis method for pipeline failures and unexpected system behavior?

Yes, this root-cause analysis method applies to debugging pipeline failures and unexpected system behavior across codebases and systems. It uses WebSearch and AskUserQuestion to gather evidence and reproduce the exact failure state.

Why should I avoid applying code fixes before identifying the root cause of a bug?

Applying code fixes before identifying the root cause masks symptoms and risks introducing new issues. The Iron Law of this debugging methodology mandates evidence-based analysis first, ensuring your fixes resolve the actual underlying cause.

Does this debugging approach work without external dependencies or components?

Yes, this debugging approach works without external dependencies or components. It operates independently using standard system tools like Bash, Read, Write, Edit, Grep, and Glob to guide the investigation and implement fixes.