investigator-agent

Diagnose problems by gathering evidence and identifying likely causes.

Updated Mar 30, 2026
One-click install
npx skills add https://github.com/harkers/forge-email-server --skill investigator-agent
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: investigator-agent
Source: https://github.com/harkers/forge-email-server/tree/main/skills/investigator-agent
Command: npx skills add https://github.com/harkers/forge-email-server --skill investigator-agent

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

The Investigator Agent helps teams diagnose problems by systematically gathering evidence, attempting reproductions, reducing uncertainty, and pinpointing likely causes to guide timely fixes and preventive actions.

Core Features & Use Cases

  • Evidence gathering from logs, symptoms, and environment
  • Reproducing or narrowing issues to move from hypothesis to testable steps
  • Identifying likely causes and distinguishing facts from speculation
  • Defining the next best diagnostic or remediation step to minimize blast radius
  • Suitable for debugging, incident triage, root-cause analysis, post-mortems, and learning what is happening before implementing fixes

Quick Start

Describe the issue and available evidence, and instruct the agent to begin evidence gathering.

Frequently Asked Questions about investigator-agent

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

FAQPage Schema
How do I perform root-cause analysis using gathered evidence?

Root-cause analysis is performed by gathering evidence from logs and symptoms, reproducing the issue, and distinguishing facts from speculation to pinpoint likely causes. This structured approach reduces uncertainty and guides timely fixes.

What is the best way to troubleshoot an incident before implementing a fix?

The best way to troubleshoot an incident is to systematically gather evidence, narrow the issue scope, and define the next best diagnostic step to minimize blast radius. This prevents premature fixes and ensures the actual problem is addressed.

How do I structure my debugging findings for a post-mortem report?

Debugging findings are structured by including a findings summary, gathered evidence, confidence level, likely causes, unresolved questions, and next actions. This format satisfies post-mortem requirements and clearly communicates diagnostic results.

Can I use evidence-based diagnosis for active incident triage?

Evidence-based diagnosis is suitable for incident triage because it moves from hypothesis to testable steps, minimizing blast radius. It helps teams quickly identify likely causes and define remediation steps during active incidents.

What should I provide to start an evidence-based problem diagnosis?

To start evidence-based problem diagnosis, you should describe the issue and any available evidence from your logs, symptoms, or environment. Instruct the agent to begin gathering evidence to start narrowing down the likely causes.