rca

Automate root cause analysis by triaging CI logs, Kind, or HyperShift diagnostics.

292|103|Updated Mar 27, 2025
One-click install
npx skills add https://github.com/kagenti/kagenti --skill rca
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rca
Source: https://github.com/kagenti/kagenti/tree/main/.claude/skills/rca
Command: npx skills add https://github.com/kagenti/kagenti --skill rca

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the systematic investigation of failures, helping to quickly identify the root cause of issues in CI/CD pipelines or live environments.

Core Features & Use Cases

  • Automated Failure Triage: Intelligently selects the appropriate diagnostic sub-skill based on the failure source and available cluster access (CI logs, Kind, or HyperShift).
  • Context-Safe Logging: Ensures diagnostic output is isolated to prevent context pollution in the main conversation.
  • CVE Awareness: Integrates CVE scanning and responsible disclosure protocols for dependency-related issues.
  • Use Case: When a CI pipeline fails, this skill can automatically analyze logs, attempt to reproduce the issue locally with Kind, or perform deep dives on a HyperShift cluster to pinpoint the exact cause.

Quick Start

Use the rca skill to investigate the latest CI pipeline failure.

Frequently Asked Questions about rca

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

FAQPage Schema
How do I automate root cause analysis for CI/CD pipeline failures?

Root cause analysis for CI/CD failures is automated by intelligently routing diagnostic tasks based on failure origin and environment access. The skill systematically investigates CI logs, attempts local reproduction using Kind, or performs deep cluster analysis on HyperShift environments to pinpoint exact causes.

Can I reproduce Kubernetes failures locally when diagnosing system issues?

Yes, you can reproduce Kubernetes failures locally when diagnosing system issues by using Kind. The skill attempts local reproduction of failures using Kind to safely identify root causes before applying fixes to live cluster environments.

Does this troubleshooting approach work with HyperShift environments?

Yes, this troubleshooting approach works with HyperShift environments by performing deep cluster analysis. When failures originate in HyperShift, the skill conducts thorough diagnostic investigations directly on the cluster to resolve complex system issues securely.

How are dependency-related failures and CVEs handled during failure triage?

Dependency-related failures and CVEs are handled during failure triage by integrating CVE scanning and enforcing responsible disclosure protocols. This ensures dependency-related issues are identified securely while maintaining efficient and safe failure resolution.

What is the best way to prevent context pollution when analyzing CI logs?

The best way to prevent context pollution when analyzing CI logs is to enforce context-safe logging. This skill isolates diagnostic output to prevent context pollution in the main conversation, ensuring clean and efficient failure analysis without disrupting active workflows.