diagnose

Reproduce, minimize, hypothesize, instrument, fix, and regression-test hard bugs.

Updated May 15, 2026
One-click install
npx skills add https://github.com/az9713/engineer-skills-tutorial --skill diagnose-az9713
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: diagnose
Source: https://github.com/az9713/engineer-skills-tutorial/tree/main/skills/engineering/diagnose
Command: npx skills add https://github.com/az9713/engineer-skills-tutorial --skill diagnose-az9713

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Diagnose and triage hard bugs and performance regressions using a disciplined, multi-phase loop: reproduce → minimise → hypothesise → instrument → fix → regression-test.

Core Features & Use Cases

  • Phase-driven debugging workflow from reproduction to verification.
  • Instrumentation and hypothesis testing to isolate root causes.
  • Useful for engineering teams tackling flaky or high-impact issues across systems.

Quick Start

Initiate the diagnosis loop by stating the bug and following the six-phase workflow outlined.

Frequently Asked Questions about diagnose

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

FAQPage Schema
How do I systematically debug a hard to reproduce bug across my codebase?

Systematic bug diagnosis requires a disciplined, six-phase loop: reproduce, minimise, hypothesise, instrument, fix, and regression-test. This workflow isolates root causes by using deterministic feedback signals and targeted instrumentation to verify fixes across codebases and integrations.

What is the best way to diagnose a performance regression in a software service?

Diagnosing a performance regression involves running a phased diagnosis loop to reproduce the slowdown, form hypotheses, and add instrumentation. By testing specific hypotheses against deterministic feedback signals, you can isolate the root cause and apply a verified fix.

How do I isolate root causes of flaky bugs using instrumentation?

Isolating flaky bugs through instrumentation requires forming clear hypotheses about the unexpected behavior and adding targeted tests to capture deterministic feedback signals. This disciplined approach guides the debugging loop from reproduction through regression testing.

When should I use a phased debugging workflow instead of ad hoc troubleshooting?

A phased debugging workflow is necessary for hard bugs or performance regressions where ad hoc troubleshooting fails. It enforces a disciplined sequence from reproduction to regression testing, ensuring root cause isolation through clear hypotheses and deterministic feedback signals.

Can I use this systematic diagnosis loop for crashes and unexpected behavior in integrations?

Yes, the systematic diagnosis loop is applicable to user reports of crashes, slowdowns, or unexpected behavior across codebases, services, and integrations. It relies on deterministic feedback signals, instrumentation, and clear hypotheses to guide the fix and verification phases.