kramme:review-pr:team

Orchestrate a team of AI reviewers to cross-validate PR findings.

2|2|Updated Jan 15, 2026
One-click install
npx skills add https://github.com/Abildtoft/kramme-cc-workflow --skill kramme-review-pr-team
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kramme:review-pr:team
Source: https://github.com/Abildtoft/kramme-cc-workflow/tree/main/skills/kramme%3Areview-pr%3Ateam
Command: npx skills add https://github.com/Abildtoft/kramme-cc-workflow --skill kramme-review-pr-team

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill streamlines and enhances PR reviews by coordinating a team of AI reviewers that cross-validate findings, surface issues faster, and reduce bias or missed edge cases.

Core Features & Use Cases

  • Team orchestration: Spawn a named review team and assign specialized AI reviewers based on PR components.
  • Cross-review & aggregation: Collect findings from all teammates and synthesize an integrated REVIEW_OVERVIEW.md.
  • Conditional deployment: Dynamically spawn reviewers based on PR changes (code, tests, docs) to optimize cost.

Quick Start

Run the team-based PR review workflow: /kramme:review-pr:team /kramme:review-pr:team code errors tests

Frequently Asked Questions about kramme:review-pr:team

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

FAQPage Schema
How do I run an AI agent team-based PR review?

To run a team-based PR review, execute the /kramme:review-pr:team command. This orchestrates specialized AI reviewers to cross-validate findings across code, tests, documentation, and design notes.

How does conditional agent deployment work for PR reviews?

Conditional agent deployment dynamically spawns specialized reviewer agents based on PR diffs. By analyzing changes in code, tests, or docs, it optimizes costs by only deploying necessary agents.

Can I use multiple AI agents to review complex pull requests?

Yes, you can use multiple AI agents to review complex pull requests. The team orchestration feature spawns a named review team and assigns specialized reviewers to provide multiple perspectives.

What is the best way to aggregate AI code review findings?

The best way to aggregate AI code review findings is through cross-review and aggregation. This collects findings from all teammates and synthesizes an integrated REVIEW_OVERVIEW.md file.

When should I use a team-based AI review instead of a single agent?

You should use a team-based AI review for large or complex PRs where multiple perspectives are beneficial. It helps surface issues faster and reduces bias or missed edge cases compared to single-agent reviews.

Do I need to specify review areas when starting the AI agent team?

No, you do not need to specify review areas, but you can. Running /kramme:review-pr:team works alone, or you can append arguments like code errors tests to target specific review aspects.