qa-scan

Classify code changes by category and risk to generate specialist routing manifests.

1|Updated Mar 3, 2026
One-click install
npx skills add https://github.com/dev-gios/agent-teams-qa --skill qa-scan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: qa-scan
Source: https://github.com/dev-gios/agent-teams-qa/tree/main/skills/qa-scan
Command: npx skills add https://github.com/dev-gios/agent-teams-qa --skill qa-scan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the initial triage of code changes, classifying them by category and assigning risk levels to determine which specialized AI agents should perform a detailed review.

Core Features & Use Cases

  • Code Classification: Analyzes file paths and content to categorize changes (e.g., 'auth', 'api', 'ui').
  • Risk Assessment: Assigns a risk level (low, medium, high, critical) based on the nature and volume of changes.
  • Specialist Routing: Generates a manifest indicating which QA specialists (e.g., 'qa-architect', 'qa-security') should be activated for review.
  • Use Case: When a developer commits changes to the authentication module, qa-scan identifies it as 'auth' and 'api', assigns a 'high' risk, and routes it to the 'qa-security' and 'qa-architect' specialists.

Quick Start

Use the qa-scan skill to analyze staged code changes and determine the appropriate review specialists.

Frequently Asked Questions about qa-scan

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

FAQPage Schema
How do I automate code review triage and route changes to specialist agents?

Code review triage is automated by ingesting code changes, classifying files by category using path and content patterns, and computing risk levels to generate a routing manifest for specialist agents.

How does risk assessment work when scanning code changes for QA review?

Risk assessment works by assigning a risk level (low, medium, high, critical) based on the nature and volume of the ingested code changes to determine which specialized AI agents should perform detailed reviews.

Can I scan staged changes and specific directories for code classification?

Yes, you can scan staged changes and specific directories because the skill handles various scope resolutions including git diffs, specific files, directories, and pull requests for code classification.

Does code classification integrate with artifact stores like Engram or OpenSpec?

Yes, code classification integrates with artifact stores like Engram or OpenSpec for persistence and feedback loading after computing risk levels and generating specialist routing manifests.

What is the best way to route authentication module changes to a security specialist?

The best way to route authentication module changes is to classify them as 'auth' and 'api', assign a 'high' risk level, and generate a routing manifest activating the 'qa-security' specialist for review.