triage-issue

Diagnose bugs or regressions and produce a testable fix plan.

Updated Mar 18, 2026
One-click install
npx skills add https://github.com/Canepro/codex-skills --skill triage-issue-canepro
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: triage-issue
Source: https://github.com/Canepro/codex-skills/tree/main/skills/triage-issue
Command: npx skills add https://github.com/Canepro/codex-skills --skill triage-issue-canepro

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Diagnose bugs or regressions by isolating symptoms, identifying likely root causes, and producing a durable fix plan or issue-quality diagnosis.

Core Features & Use Cases

  • Structured problem capture: separates symptoms from causes and guides toward a diagnostic conclusion.
  • Root-cause analysis: outlines triggering conditions, the broken invariant, and minimal fix direction.
  • Output guidance: switches to an executor-grade plan when needed (e.g., generating an agent-plan-backlog entry) and provides testable criteria.

Quick Start

Diagnose the reported issue and draft a concise fix plan.

Frequently Asked Questions about triage-issue

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

FAQPage Schema
How do I diagnose a bug and find the root cause before writing code?

To diagnose a bug and find its root cause, you need structured root-cause analysis that separates symptoms from causes, identifies triggering conditions and broken invariants, and outlines a minimal fix direction.

What is the best way to create a testable fix plan for a software regression?

Creating a testable fix plan for a regression requires isolating symptoms, performing bug diagnosis to identify the broken invariant, and generating concise, executor-grade criteria that validate the fix.

Can I use this to triage issue quality and reproduce a broken behavior?

Yes, you can triage issue quality and reproduce broken behavior by applying structured problem capture, which guides diagnostic conclusions when regression reproduction is needed.

How do I structure a debugging workflow when behavior is broken but the cause is unclear?

Structuring a debugging workflow for broken behavior involves isolating symptoms, identifying likely root causes, and producing a durable fix plan or issue-quality diagnosis before implementation.

When do I need root-cause analysis instead of immediately patching a bug?

You need root-cause analysis instead of immediately patching when regression reproduction is required or when you want a durable fix plan and diagnosis before implementation begins.