investigate

Automate structured cross-domain investigations of MCU hard faults, boot/kernel issues, and WPF crashes.

2|1|Updated Mar 22, 2026
One-click install
npx skills add https://github.com/solitasroh/rkit --skill investigate-solitasroh
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: investigate
Source: https://github.com/solitasroh/rkit/tree/main/skills/investigate
Command: npx skills add https://github.com/solitasroh/rkit --skill investigate-solitasroh

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Systematic protocol for diagnosing MCU HardFaults, MPU boot/kernel issues, and WPF crashes across MCU/MPU/WPF projects.

Core Features & Use Cases

  • Domain auto-detection and symptom collection
  • Phase-based root-cause classification with evidence capture
  • Investigation reporting and ADR creation
  • Cross-domain templates and best practices for repeatable analysis

Quick Start

Trigger the investigate workflow on the affected MCU/MPU/WPF project to collect symptoms and generate a structured report.

Frequently Asked Questions about investigate

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

FAQPage Schema
How do I systematically debug MCU hard faults and find the root cause?

A systematic hard fault investigation protocol automates domain auto-detection, collects crash symptoms, classifies root causes, captures evidence, and generates a structured investigation report with an ADR for your WPF or MCU project.

What is the best way to diagnose WPF crashes across different application domains?

Diagnosing WPF crashes requires a cross-domain investigation protocol that auto-detects the affected domain, captures crash evidence, performs root-cause classification, and generates a structured investigation report for repeatable analysis.

Can I use a single debugging workflow for both MCU hard faults and MPU boot issues?

A cross-domain debugging workflow supports both MCU hard faults and MPU boot or kernel issues by applying domain auto-detection, phase-based root-cause classification, and standardized evidence capture templates across multiple project types.

How do I document root-cause analysis for an embedded kernel issue?

Documenting root-cause analysis for a kernel issue involves generating an Architecture Decision Record that captures the investigation report, fault classification, and evidence collected during the boot failure analysis.

Does this systematic fault analysis approach work without specific debugging hardware dependencies?

This fault analysis approach operates without specific dependencies, using domain auto-detection and symptom collection to drive the investigation workflow and generate reports directly within the affected MCU or WPF project.

Why do I need an ADR when investigating a system crash or hard fault?

Creating an ADR during a crash investigation records the root-cause classification, captured evidence, and reasoning behind the fault analysis, ensuring repeatable and structured debugging across MCU, MPU, and WPF projects.