diagnose

Guide a phase-driven root-cause analysis loop for bugs and performance regressions.

1|Updated Apr 24, 2026
One-click install
npx skills add https://github.com/laozhong86/gxpm --skill diagnose-laozhong86
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: diagnose
Source: https://github.com/laozhong86/gxpm/tree/main/skills/gxpm-diagnose
Command: npx skills add https://github.com/laozhong86/gxpm --skill diagnose-laozhong86

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Disciplined diagnosis loop for hard bugs and performance regressions. Use when user says 'diagnose this', reports a hard bug, describes a performance regression, or asks why something fails.

Core Features & Use Cases

  • Phase-driven diagnosis workflow: Reproduce, Explore, Hypothesise, Instrument, Fix, Cleanup.
  • Maintains auditable evidence and supports iterative testing and regression checks.
  • Suitable for bug investigations that require structured hypotheses and reproducible proofs.

Quick Start

Load the gxpm-diagnose skill and start the diagnose loop from Phase 2 to Phase 7 as described in the workflow notes.

Frequently Asked Questions about diagnose

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

FAQPage Schema
How do I structure root-cause analysis for a hard bug?

Root-cause analysis for hard bugs requires a phase-driven workflow: Reproduce, Explore, Hypothesise, Instrument, Fix, and Cleanup. This enforces disciplined evidence collection and maintains an auditable, append-only record of the investigation.

What is the best way to diagnose a performance regression in my codebase?

Diagnose performance regressions by applying a structured hypothesis testing loop. You reproduce the symptom, explore the codebase, formulate hypotheses, and use prescribed instrumentation to gather evidence before applying a fix.

How do I maintain an auditable evidence trail during debugging?

Maintain an auditable evidence trail during debugging by using an append-only record of the investigation. This structured approach captures proofs and instrumentation data iteratively across each diagnostic phase.

Can I use structured hypothesis testing for exploratory debugging?

Structured hypothesis testing supports both exploratory debugging and formal root-cause analysis. It guides iterative testing and regression checks across codebases, refactors, or integration work when symptoms or stack traces are observed.

When do I need phase-driven instrumentation for bug investigations?

You need phase-driven instrumentation when diagnosing hard bugs or performance drops that require reproducible proofs. It enforces disciplined evidence collection rather than ad-hoc troubleshooting when symptoms or stack traces are observed.