diagnose

Guide Python debugging through reproduce, minimize, hypothesize, instrument, fix, and regression-test.

Updated Mar 9, 2026
One-click install
npx skills add https://github.com/sebc-dev/prosperity --skill diagnose-sebc-dev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: diagnose
Source: https://github.com/sebc-dev/prosperity/tree/main/.claude/skills/diagnose
Command: npx skills add https://github.com/sebc-dev/prosperity --skill diagnose-sebc-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill assists in efficiently diagnosing and resolving hard-to-find bugs and performance regressions in software systems.

Core Features & Use Cases

  • Disciplined Diagnostics: Provides a structured approach for reproducibility, minimization, hypothesis generation, and instrumentation.
  • Feedback Loop Construction: Offers various methods to construct a reliable feedback loop for identifying and verifying bugs.
  • Reproducible Bug Reproduction: Ensures the bug is consistently reproducible to accurately diagnose the root cause.
  • Hypothesis Testing: Generates falsifiable hypotheses and systematically tests them to identify the root cause of bugs.
  • Instrumentation: Instructs on effective debugging and logging strategies to isolate and understand the problem.
  • Regression Testing: Includes steps to ensure the fix does not reintroduce the issue.

Quick Start

Utilize the diagnose skill by following the structured bug diagnosis process for an unexplained software malfunction.

Frequently Asked Questions about diagnose

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

FAQPage Schema
What is the best way to diagnose a complex software bug that is hard to reproduce?

Diagnosing a complex software bug requires a disciplined loop: Reproduce, Minimize, Hypothesise, Instrument, Fix, and Regression-Test. This structured approach ensures consistent reproduction and systematic isolation of the root cause before applying a verified fix.

How do I build a reliable feedback loop for performance regression testing?

Building a reliable feedback loop for performance regression involves systematic instrumentation and hypothesis testing. By consistently reproducing the issue and minimizing the triggering conditions, you can generate falsifiable hypotheses to accurately identify the root cause.

How do you systematically test hypotheses during codebase debugging?

To systematically test hypotheses during codebase debugging, generate falsifiable assumptions about the malfunction and verify them through targeted instrumentation. This disciplined approach isolates variables and confirms the exact root cause before implementing a fix.

Do I need to understand the codebase architecture to isolate hard-to-find bugs?

Yes, understanding the codebase architecture is required to effectively isolate hard-to-find bugs. A disciplined diagnostic process relies on comprehending system structure to accurately minimize reproduction steps and generate valid hypotheses for instrumentation.

Why should I use a structured debugging process instead of ad-hoc logging?

A structured debugging process prevents reintroducing issues by enforcing regression testing after a fix. Unlike ad-hoc logging, it relies on reproducible bug reproduction and systematic hypothesis testing to accurately diagnose root causes without guesswork.

Can I use this systematic bug diagnosis approach for performance regressions in Python?

Yes, this systematic bug diagnosis approach targets performance regressions and complex bugs in Python environments. It requires utilizing Python debugging tools to construct a reliable feedback loop, instrument the code, and verify the regression test.