debug

Diagnose code or test failures using an 8-step structured investigation loop.

Updated Mar 12, 2026
One-click install
npx skills add https://github.com/Nerfherder16/BrickLayer --skill debug-nerfherder16
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: debug
Source: https://github.com/Nerfherder16/BrickLayer/tree/main/.claude/skills/debug
Command: npx skills add https://github.com/Nerfherder16/BrickLayer --skill debug-nerfherder16

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Diagnose broken code or failing tests using an 8-step structured investigation loop. Each technique is tried in order until root cause is found or all 8 are exhausted.

Core Features & Use Cases

  • Stepwise debugging methodology: Binary Search, Differential Analysis, Minimal Reproduction, Forward Trace, Pattern Search, Backward Trace, Rubber Duck, and Hypothesis Log.
  • Provides a repeatable process to identify root causes in CI failures, flaky tests, and runtime errors.
  • Use case: When a failure lacks a clear trigger, apply the loop to isolate the root cause and document the investigation.

Quick Start

Initiate the diagnostic loop by providing an error description, failing test, or file path for analysis.

Frequently Asked Questions about debug

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

FAQPage Schema
How do I find the root cause of a failing test when the trigger is unclear?

To find the root cause of a failing test, apply an 8-step structured investigation loop using techniques like minimal reproduction and pattern search. It systematically isolates undocumented failure triggers through disciplined execution.

What is the best way to troubleshoot intermittent CI failures?

Troubleshooting intermittent CI failures involves applying a stepwise debugging methodology like differential analysis and backward tracing. This structured loop identifies flaky test patterns and isolates underlying software defects.

How do I debug a runtime error without an obvious trigger?

Debugging a runtime error without an obvious trigger requires techniques like binary search and forward tracing. The structured loop isolates variables and narrows down the execution path to pinpoint the exact failure.

Does this structured debugging methodology work for large software projects?

Yes, this structured debugging methodology works for large software projects by applying the 8-step investigation loop. It scales by systematically attempting techniques from binary search to hypothesis logging until the root cause is found.

What should I do if all 8 debugging steps are exhausted without finding the root cause?

If all 8 debugging steps are exhausted, the loop requires structured documentation of the findings gathered during the investigation. This documented state sharing from each step guides subsequent remediation efforts.