quality-test

Automate conversational UAT with session persistence and auto-diagnosis.

511|63|Updated Mar 17, 2026
One-click install
npx skills add https://github.com/catlog22/Maestro-Flow --skill quality-test
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: quality-test
Source: https://github.com/catlog22/Maestro-Flow/tree/main/.codex/skills/quality-test
Command: npx skills add https://github.com/catlog22/Maestro-Flow --skill quality-test

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Conversational UAT with session persistence, auto-diagnosis, and gap-plan closure loop to ensure quality-assured software in multi-agent environments.

Core Features & Use Cases

  • Conversational UAT with persistent sessions across resets and resumed analyses.
  • Parallel debug agent diagnosis for rapid gap identification and suggested fixes.
  • Gap-closure loop that plans and executes fixes in iterative cycles.
  • Supports phase-based workflows and session resumption via --session.

Quick Start

Invoke quality-test with a phase number to start testing, for example quality-test "3" or quality-test "3 --auto-fix".

Frequently Asked Questions about quality-test

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

FAQPage Schema
How do I automate conversational UAT with session persistence?

Automating conversational UAT with session persistence is achieved by invoking phase-based testing commands that maintain state across resets, allowing resumed analyses and reproducible outcomes in multi-agent environments.

What is a gap-closure loop in software quality assurance?

A gap-closure loop in software quality assurance is an iterative cycle that plans and executes fixes for identified testing gaps, running parallel diagnostic agents to suggest and apply corrections until quality targets are met.

How do I resume a UAT session after an environment reset?

To resume a UAT session after an environment reset, invoke the testing command with the --session flag and the target phase number, which restores the previous test state and continues the interactive workflow.

Does multi-agent UAT support parallel auto-diagnosis for test failures?

Multi-agent UAT supports parallel auto-diagnosis by deploying debug agents alongside the testing workflow to rapidly identify root causes of failures and generate suggested fixes for interactive presentation.

Can I enable auto-fix loops for end-to-end testing workflows?

You can enable auto-fix loops for end-to-end testing workflows by appending the --auto-fix flag to your phase invocation, which triggers iterative gap-plan execution and automated correction cycles.

When should I use phase-based targets in user acceptance testing?

Phase-based targets in user acceptance testing should be used when validating end-to-end workflows across multi-agent environments, ensuring strict phase and target validation before progressing to subsequent testing stages.