investigate

Investigate problems by forming hypotheses, gathering evidence, and testing empirically.

Updated Aug 23, 2026
One-click install
npx skills add https://github.com/olliecrow/codex --skill investigate-olliecrow
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: investigate
Source: https://github.com/olliecrow/codex/tree/main/skills/investigate
Command: npx skills add https://github.com/olliecrow/codex --skill investigate-olliecrow

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill tackles complex issues by systematically exploring hypotheses, gathering evidence, and conducting empirical tests to build high confidence in solutions or explanations.

Core Features & Use Cases

  • Hypothesis-driven analysis: Formulates and tests multiple explanations for a problem.
  • Empirical validation: Relies on real data and experiments over assumptions.
  • Iterative problem-solving: Continues investigation until root causes are understood or all avenues are exhausted.
  • Use Case: Debugging a subtle, intermittent bug in a large codebase by forming hypotheses about its cause, writing targeted tests to confirm or deny each one, and analyzing the results to pinpoint the exact issue.

Quick Start

Investigate the root cause of the recent performance degradation in the user authentication service.

Frequently Asked Questions about investigate

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

FAQPage Schema
How do I conduct root cause analysis for a subtle bug in a large codebase?

Root cause analysis for a subtle bug involves systematically formulating hypotheses about the issue, gathering empirical evidence, and testing each explanation iteratively until the exact root cause is pinpointed.

What is the best way to debug complex intermittent behavior?

Debugging complex intermittent behavior requires hypothesis-driven analysis, formulating multiple potential explanations and running targeted empirical tests to validate or refute each one based on real data.

When do I need hypothesis testing for software investigation?

Hypothesis testing for software investigation is needed when you must build high confidence in an explanation for a complex problem, relying on empirical validation rather than assumptions to thoroughly understand the codebase.

How do I research and understand a complex codebase thoroughly?

To understand a complex codebase thoroughly, you conduct a meticulous deep dive by iteratively gathering empirical evidence and testing hypotheses until all avenues are exhausted and the underlying root causes are clearly understood.

How to investigate performance degradation in a service?

Investigating performance degradation involves a deep dive into the service by formulating hypotheses about potential causes, gathering real data, and conducting empirical tests to build high confidence in the identified solution.