Verified:GitHub

investigate

Debug software issues by enforcing root cause investigation before fixes.

Updated Feb 24, 2026

Search Tags:#debugging #root cause #troubleshooting #error analysis #bug investigation #systematic debugging #stack traces

Ready to run

npx skills add https://github.com/Jia-Hong-Peng/jolike.com --skill investigate-jia-hong-peng

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: investigate
Source: https://github.com/Jia-Hong-Peng/jolike.com/tree/main/.claude/skills/gstack/investigate
Command: npx skills add https://github.com/Jia-Hong-Peng/jolike.com --skill investigate-jia-hong-peng

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the guesswork and recurring bugs that come from whack-a-mole debugging. It enforces a strict Iron Law: no fixes ship without first identifying the true root cause, saving teams from repeated incidents and hidden technical debt.

Core Features & Use Cases

Four-Phase Workflow: Guides users through investigate, analyze, hypothesize, and implement stages to ensure every fix addresses the underlying issue.
Proactive Triggering: Automatically activates when users report errors, stack traces, 500 errors, or unexpected behavior, catching problems early.
Context Recovery: Restores recent project artifacts, checkpoints, and session history after context compaction so debugging continuity survives long sessions.

Quick Start

Use the investigate skill to find the root cause of the reported error before applying any fix.

Frequently Asked Questions about investigate

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

FAQPage Schema

What is systematic debugging and how does it prevent recurring bugs?▼

Systematic debugging enforces root cause investigation before applying fixes, eliminating whack-a-mole debugging and preventing recurring incidents. It requires reading code paths, checking recent changes, and reproducing bugs deterministically.

How do I find the root cause of a 500 error or stack trace?▼

To find the root cause of a 500 error or stack trace, follow a four-phase workflow: investigate, analyze, hypothesize, and implement. This requires reading code paths and validating hypotheses before shipping any fixes.

How do I debug production incidents without guessing at solutions?▼

Debug production incidents without guessing by enforcing an Iron Law: no fixes ship without identifying the true root cause. This involves reproducing bugs deterministically and validating hypotheses through systematic error analysis.

What is the best way to troubleshoot regressions where code previously worked?▼

The best way to troubleshoot regressions where code previously worked is checking recent code changes and reading execution paths. This structured approach ensures you identify the true root cause rather than applying superficial patches.

Does root cause investigation work for long debugging sessions that lose context?▼

Root cause investigation supports long debugging sessions through context recovery. It restores recent project artifacts, checkpoints, and session history after context compaction, ensuring debugging continuity survives throughout extended troubleshooting.