review-pr

Coordinate adversarial PR reviews by delegating checks to specialist subagents.

20|4|Updated Jan 7, 2026
One-click install
npx skills add https://github.com/nbramia/LifeOS --skill review-pr-nbramia
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: review-pr
Source: https://github.com/nbramia/LifeOS/tree/main/.agents/skills/review-pr
Command: npx skills add https://github.com/nbramia/LifeOS --skill review-pr-nbramia

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Adversarial PR reviews help ensure code changes meet intent, improve quality, and reduce risk by rigorously questioning assumptions and verifying evidence with multiple specialized reviewers.

Core Features & Use Cases

  • Context gathering: Collect PR metadata, diff, comments, and linked issues to frame the review.
  • Specialist review: Spawn and orchestrate multiple subagents to verify claims, test coverage, and alignment with spec.
  • Controlled verdicts: Aggregate findings with severity labels and provide actionable remediation steps.
  • Use Case: Before merging a complex PR, trigger an adversarial review to surface edge cases, missing tests, and potential design concerns.

Quick Start

Provide the PR diff to the skill and request an adversarial review using specialist agents.

Frequently Asked Questions about review-pr

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

FAQPage Schema
What is adversarial code review and how does it validate pull requests?

Adversarial code review rigorously questions assumptions and verifies evidence by delegating PR checks to specialist subagents. It validates scope, test evidence, and spec adherence across touched modules, architecture, and tests to reduce merging risks.

How do I run an adversarial PR review using specialist agents?

To run an adversarial PR review, provide the PR diff to the skill and request a review. It will gather context like metadata and comments, spawn subagents for independent verification, and aggregate findings with severity labels and remediation steps.

Can I use this for reviewing complex code changes before merging?

Yes, you can use this for reviewing complex code changes before merging. It is designed to surface edge cases, missing tests, and potential design concerns by orchestrating multiple specialized reviewers to ensure changes meet intent and improve quality.

What is the best way to automate quality assurance for pull requests?

The best way to automate quality assurance for pull requests is orchestrating adversarial reviews with specialist agents. This approach independently verifies test coverage, validates alignment with specifications, and aggregates structured findings with severity labels.

How are code review findings aggregated and reported?

Code review findings are aggregated with severity labels and actionable remediation steps. The specialist subagents independently verify claims and coverage, ensuring a structured aggregation of traceable context for the final controlled verdict.