incident-investigator

Orchestrate logs-fetcher, root-cause-analysis, and context-fetcher to investigate incidents.

9|10|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/redhat-et/rhdp-rca-plugin --skill incident-investigator-redhat-et
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: incident-investigator
Source: https://github.com/redhat-et/rhdp-rca-plugin/tree/main/experiments/skill_chaining_exp/incident-investigator
Command: npx skills add https://github.com/redhat-et/rhdp-rca-plugin --skill incident-investigator-redhat-et

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides an integrated workflow to investigate incidents by fetching remote logs, correlating telemetry, and performing root cause analysis so operators do not need to manually gather evidence across multiple systems.

Core Features & Use Cases

  • End-to-end orchestration: sequentially runs logs-fetcher, root-cause-analysis, and context-fetcher to deliver consolidated diagnostic findings.
  • Multi-source correlation: fetches logs via SSH, correlates events with Splunk and GitHub/Ansible context, and surfaces likely causes.
  • Use Case: Troubleshoot a failed infrastructure or CI job by automatically retrieving logs, correlating Splunk traces, and pulling repository or Confluence context to identify configuration or code changes.

Quick Start

Invoke the incident-investigator skill to fetch logs via SSH, run root-cause-analysis with Splunk correlation, and gather additional context for job 123456.

Frequently Asked Questions about incident-investigator

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

FAQPage Schema
How do I automate root cause analysis for CI job failures using fetched logs?

Automated root cause analysis for CI job failures is performed by fetching logs via SSH, correlating Splunk telemetry, and retrieving GitHub context to output consolidated diagnostic findings. This eliminates manual evidence gathering across multiple systems.

Can I correlate Splunk logs with Ansible and GitHub context during incident response?

Yes, incident response can correlate Splunk logs with Ansible and GitHub context. The investigation orchestrates context-fetcher to pull repository configuration details and surface likely causes alongside telemetry traces.

What is the best way to troubleshoot infrastructure incidents without manually gathering remote logs?

Troubleshooting infrastructure incidents without manual log gathering requires an orchestration workflow that sequentially runs logs-fetcher, root-cause-analysis, and context-fetcher to deliver consolidated diagnostic findings automatically.

How does SSH log retrieval work for end-to-end incident investigation?

SSH log retrieval for incident investigation works by invoking logs-fetcher to pull remote logs, then passing them to root-cause-analysis with Splunk correlation to identify configuration or code changes causing failures.

Do I need any dependencies to run a unified log-to-root-cause investigation?

No external dependencies are required to run a unified log-to-root-cause investigation. The workflow orchestrates logs-fetcher, root-cause-analysis, and context-fetcher internally to perform end-to-end incident investigation.

Why does my CI job failure investigation require correlating multiple log sources?

CI job failure investigation requires correlating multiple log sources because infrastructure failures often stem from code or configuration changes. Correlating Splunk traces with GitHub and Ansible context surfaces likely causes that isolated logs miss.