QA Auditor Skill

This skill provides the evaluation framework, data schema, and report generation tools for the /qa-audit command.

Quick Start

# Run a full audit with config
/qa-audit --config qa-audit.yaml

# Audit a single feature
/qa-audit --feature auth

# Auto-discovery mode (no config needed)
/qa-audit

Components

Evaluation Rubric

File: references/evaluation-rubric.md

Defines the 6 quality dimensions scored 1-5:

1. Functionality (25%) — Does it work?
2. Quality (20%) — How good is the output?
3. Edge Cases (15%) — What happens at boundaries?
4. Integration (15%) — Do parts work together?
5. UX/UI (15%) — Is it pleasant to use?
6. Performance (10%) — Is it fast enough?

Also defines issue severity levels: CRITICAL, HIGH, MEDIUM, LOW, INFO.

Report Schema

File: references/report-schema.md

JSON schema for audit-data.json — the structured data that feeds the HTML report. Sections: metadata, executive_summary, features, cross_cutting, issues, screenshots.

Report Generator

File: scripts/generate_report.py

Python script (stdlib only, no pip dependencies) that converts audit-data.json into a self-contained HTML report with embedded screenshots.

Usage:

python3 scripts/generate_report.py \
  --input qa-audit-results/audit-data.json \
  --output qa-audit-results/ \
  --open

HTML Template

File: assets/report-template.html

The HTML/CSS/JS template used by the report generator. Features:

• Executive summary with score ring and star rating
• SVG radar chart for dimension scores
• Feature cards with score bars and scenario results
• Filterable issues table by severity
• Screenshot gallery with lightbox
• Print-ready with @media print styles

Creating a Config

See examples/qa-audit.yaml for a complete reference. Minimum config:

project:
  name: "My App"
environment:
  base_url: "http://localhost:3000"
features:
  - id: homepage
    name: "Homepage"
    priority: high
    pages:
      - url: "/"
        name: "Home"