correlating

Identify cross-PMR patterns and generate structured correlation reports in Markdown with four sections and a YAML-like schema.

Updated Feb 23, 2026

Search Tags:#metrics #root-cause #hardening #blast-radius #correlation #incident-analysis #pmr

Ready to run

npx skills add https://github.com/0xHoneyJar/construct-hardening --skill correlating

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: correlating
Source: https://github.com/0xHoneyJar/construct-hardening/tree/main/skills/correlating
Command: npx skills add https://github.com/0xHoneyJar/construct-hardening --skill correlating

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Cross-PMR correlation identifies recurring root causes, common blast-radius patterns, and persistent signal gaps to prevent repeat incidents.

Core Features & Use Cases

Detect cross-incident patterns across PMRs to surface systemic vulnerabilities.
Generate structured correlation reports including hot spots, root-cause trends, persistent gaps, and fix-introduced patterns.
Useful for postmortems, regression analysis, and sprint planning to close gaps before recurrence.

Quick Start

Input an array of PMR metadata to generate a cross-incident correlation report.

Frequently Asked Questions about correlating

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

FAQPage Schema

What is cross-incident correlation for root-cause analysis?▼

Cross-incident correlation for root-cause analysis identifies recurring patterns across multiple postmortem reports to surface systemic vulnerabilities, persistent signal gaps, and common blast-radius trends. It processes PMR metadata to reveal root-cause trends and prevent repeat incidents.

How do I generate a cross-incident correlation report from PMR metadata?▼

To generate a cross-incident correlation report, input an array of PMR metadata objects representing incidents and regression data. The analysis outputs a structured markdown report containing hot spots, root-cause trends, persistent gaps, and fix-introduced patterns.

Can I use incident metrics to find fix-introduced regression patterns?▼

Yes, you can use incident metrics to find fix-introduced regression patterns by analyzing cross-PMR metadata. This reveals systemic vulnerabilities and communication gaps across time, ensuring that hot spots reference at least two PMRs to confirm recurrence.

What's the best way to analyze blast-radius patterns across postmortems?▼

The best way to analyze blast-radius patterns across postmortems is to correlate a set of PMR metadata objects. This surfaces hot spots and persistent gaps, generating a structured markdown report with a YAML-like schema for sprint planning and hardening.

Does cross-PMR correlation work for sprint planning and regression analysis?▼

Yes, cross-PMR correlation works for sprint planning and regression analysis by identifying persistent signal gaps and fix-introduced patterns. It processes incident metadata to reveal systemic vulnerabilities, helping close gaps before recurrence during development cycles.

What format is required for PMR metadata inputs to detect incident hot spots?▼

PMR metadata inputs must be provided as an array of metadata objects representing incidents and regression data. All PMR IDs in the resulting correlation report must originate from this input, and detected hot spots must reference at least two PMRs.