skills.rest
jscott3201
jscott3201COMMUNITY
Explore all skills by this author →
GitHub

debug

Diagnose bugs by testing ranked hypotheses and verifying fixes.

2|Updated Apr 3, 2026
Search Tags:#testing#debugging#regression#root-cause#hypothesis-driven#git-bisect#selenedb
One-click install
npx skills add https://github.com/jscott3201/ai-agent-skills --skill debug-jscott3201
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: debug
Source: https://github.com/jscott3201/ai-agent-skills/tree/main/skills/debug
Command: npx skills add https://github.com/jscott3201/ai-agent-skills --skill debug-jscott3201

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Systematic debugging prevents wasted effort on blind fixes by guiding reproducible investigation, hypothesis testing, and verified remediation so bugs are resolved at their root rather than as temporary patches.

Core Features & Use Cases

  • Hypothesis-driven isolation: Proposes ranked hypotheses, predicts observations, and runs tests one at a time with user approval to narrow the fault domain.
  • Regression and root-cause tooling: Uses git bisect for regressions and a 5 Whys workflow to produce systemic root-cause chains and actionable fixes.
  • Persistence and learning: Optionally records hypotheses, eliminated theories, and root-cause chains to SeleneDB so future sessions recall prior investigations and avoid redundant tests.

Quick Start

Provide a failing test name or bug description and ask the skill to reproduce the failure, propose ranked hypotheses, and run the first hypothesis test.

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 regression using git bisect?▼

To find a regression's root cause, provide a failing test and reproducible steps. The skill uses git bisect alongside hypothesis-driven debugging to isolate the faulty commit and verify the fix.

What is hypothesis-driven debugging and how does it isolate faults?▼

Hypothesis-driven debugging is a systematic method that proposes ranked theories, predicts observations, and runs tests one at a time. This isolates the fault domain by eliminating incorrect theories until the root cause is found.

Can I use this to fix intermittent runtime or concurrency bugs?▼

Yes, you can diagnose intermittent runtime or concurrency bugs. You must provide reproducible reproduction steps and test execution capability so the skill can systematically narrow the fault domain.

Do I need a database to persist debugging hypotheses and root-cause chains?▼

No, database integration is optional. The skill can optionally integrate with SeleneDB to persist hypotheses, eliminated theories, root-cause chains, and session summaries for future recall.

How do I start debugging a failing unit test?▼

To debug a failing unit test, provide the test name or bug description. Ask the skill to reproduce the failure, propose ranked hypotheses, and run the first hypothesis test for approval.

What are the limitations of using a 5 Whys workflow for systemic root-cause analysis?▼

The 5 Whys workflow produces systemic root-cause chains and actionable fixes, but it requires reproducible reproduction steps and test execution capability to function accurately across codebases.

Related Skills

Explore More Software Engineering Skills→
korchasakorchasa
3

flow-skill-fix-tests

Diagnoses and fixes failing tests through a guided, step-by-step workflow.

Community
Intermediate
aist-ai-sastaist-ai-sast

mcp-regression-fix

Diagnose MCP regression failures and implement durable fixes across test suites.

Official
Advanced
jscott3201jscott3201
2

perf-profile

Profile Rust, Python, and JavaScript code to resolve performance regressions.

Community
Advanced
act70255act70255

code-reviewer

Automate code reviews with static analysis and AI vulnerability detection.

Community
Advanced