jr-debug

Plan evidence-based debugging workflows from vague reports to documented resolutions.

3|1|Updated Mar 28, 2026
One-click install
npx skills add https://github.com/rusi/junior --skill jr-debug
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: jr-debug
Source: https://github.com/rusi/junior/tree/main/agents/skills/jr-debug
Command: npx skills add https://github.com/rusi/junior --skill jr-debug

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Plan and drive evidence-based debugging investigations from hypothesis to verified resolution, with escalation to implementation when needed. This guide helps turn vague failure reports into structured investigation plans, ensuring each conclusion is supported by evidence and clearly documented.

Core Features & Use Cases

  • Systematic debugging workflow that transforms vague "something's broken" into structured investigation plans with clear hypotheses, evidence-based testing, and documented resolutions.
  • Supports rigorous hypothesis formation, test planning, and escalation to implementation when necessary.
  • Useful for complex software issues, log analysis, and configuration problems where root cause is not immediately obvious.

Quick Start

Describe the issue and generate the initial debugging plan with hypotheses and evidence-based tests.

Frequently Asked Questions about jr-debug

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

FAQPage Schema
What is evidence-based debugging and when should I use it?

Evidence-based debugging is a systematic approach that transforms vague issue reports into testable hypotheses supported by data. Use it for complex software issues, log analysis, and configuration problems where the root cause is not immediately obvious.

How do I turn a vague software failure report into a structured debugging plan?

To create a structured debugging plan, describe the issue to generate initial hypotheses and evidence-based tests. This workflow ensures each conclusion is supported by evidence and documented, progressing from vague failure reports to reproducible plans.

How do I investigate complex performance anomalies when the root cause is hidden?

Investigate performance anomalies by forming rigorous hypotheses and planning tests based on system evidence. This method applies structured steps to isolate root causes in logs and configurations, escalating to implementation only when verification requires it.

What is the best way to document software troubleshooting resolutions?

The best way to document troubleshooting resolutions is by recording each step of an evidence-based investigation. This ensures every hypothesis, test result, and conclusion is reproducible and clearly mapped from the initial issue report to the final fix.

Can I use this approach for configuration problems and log analysis?

Yes, this approach supports configuration problems and log analysis where root causes are not immediately evident. It guides you through rigorous hypothesis formation and test planning to verify issues across complex software systems.

When should I escalate from debugging investigation to actual implementation?

You should escalate from investigation to implementation after verifying your evidence-based hypotheses. The workflow supports escalation when necessary, ensuring you only implement fixes once the root cause is confirmed through structured, reproducible tests.