aiox-qa

Reviews code and stories with quality gates, risk assessment, and test strategy analysis.

Updated May 13, 2026
One-click install
npx skills add https://github.com/MarcoBolsa/motor-cotacoes --skill aiox-qa-marcobolsa
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: aiox-qa
Source: https://github.com/MarcoBolsa/motor-cotacoes/tree/main/.claude/skills/AIOX/agents/qa
Command: npx skills add https://github.com/MarcoBolsa/motor-cotacoes --skill aiox-qa-marcobolsa

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? It provides a structured QA review workflow for development teams, ensuring stories meet acceptance criteria, security standards, and non-functional requirements before merge through advisory quality gates. ## Core Features & Use Cases - Story Review & Quality Gates: Run comprehensive story reviews with PASS/CONCERNS/FAIL/WAIVED gate decisions, requirements traceability via Given-When-Then mapping, and risk-based test prioritization. - Automated Code Review Integration: Leverages CodeRabbit CLI (via WSL) for pre-review scanning with a self-healing loop that iterates up to 3 times on CRITICAL/HIGH issues. - Enhanced Validation Suite: Includes 8-point security scans, database migration validation, library validation via Context7, browser console checks, and false-positive detection for bug fixes. - Use Case: After a developer marks a story "Ready for Review", activate Quinn and run *review {story-id} to get a full quality analysis, then *gate {story-id} to record the merge decision. ## Quick Start Ask the agent to review a completed story by saying: run a comprehensive QA review and quality gate decision on story 3.2.

Frequently Asked Questions about aiox-qa

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

FAQPage Schema
How do I run a QA review on a completed story?▼

Use the *review command with the story identifier, for example *review 3.2. The agent runs an automated CodeRabbit scan first, then performs manual analysis of acceptance criteria and test coverage before issuing a gate decision.

What quality gate decisions can the QA agent make?▼

The agent issues four gate outcomes: PASS, CONCERNS, FAIL, or WAIVED, each documented with rationale in a gate file. Decisions are advisory only, meaning teams choose their own quality bar rather than being blocked arbitrarily.

Does the QA agent work with CodeRabbit for automated code review?▼

Yes, CodeRabbit CLI runs via WSL before manual review to detect security vulnerabilities, code quality issues, and performance anti-patterns. A self-healing loop iterates up to 3 times requesting fixes for CRITICAL and HIGH severity issues.

Can the QA agent modify story files during review?▼

The agent is only authorized to update the QA Results section of story files. It cannot modify Status, Acceptance Criteria, Tasks, Dev Notes, or any other sections, and it cannot commit or push code.

Why does the CodeRabbit review command fail with command not found?▼

CodeRabbit is installed in WSL, not Windows, so commands must use the wsl bash -c wrapper with the full binary path ~/.local/bin/coderabbit. Verify the installation path and run coderabbit auth status inside WSL if authentication errors occur.