PR Review Subagent Catalog FAQs

Question 1

How does this skill handle overlapping review concerns?

Accepted Answer

The skill defines strict scope boundaries. For example, it distinguishes between 'Types' (logic/states) and 'Consistency' (naming/patterns) to ensure unique and relevant feedback.

Question 2

How are different AI models allocated for reviews?

Accepted Answer

Models are assigned based on 'Reasoning Demand'. High-reasoning tasks like architectural implications use Claude 3 Opus, while pattern-matching tasks like documentation checks use Sonnet.

Question 3

What are the priority tiers in this catalog?

Accepted Answer

Agents are ranked by criticality. Tier 1 includes security (IAM) and architecture because misses in these areas cause irreversible debt or incidents, whereas Tier 3 covers recoverable issues like missing tests.

Question 4

What is the PR Review Subagent Catalog?

Accepted Answer

It is a structured directory of specialized AI agents designed to review specific aspects of code, such as security, architecture, and frontend patterns, ensuring each area gets expert-level attention.

Question 5

Is this skill meant to be invoked directly by users?

Accepted Answer

No, this is a system-level skill (user-invocable: false) designed to guide orchestrator agents in dispatching the correct subagents during a PR review process.

PR Review Subagent Catalog

主要功能

使用场景

PR Review Subagent Catalog

主要功能

使用场景