agentic-review

Automate multi-agent code review of a branch against main.

92|9|Updated Mar 14, 2026
One-click install
npx skills add https://github.com/Ovid/paad --skill agentic-review-ovid
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agentic-review
Source: https://github.com/Ovid/paad/tree/main/plugins/paad/skills/agentic-review
Command: npx skills add https://github.com/Ovid/paad --skill agentic-review-ovid

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates a rigorous, multi-agent review of the current branch against the main branch to surface defects, verify plan alignment, and reduce the risk of regressions before merging.

Core Features & Use Cases

  • Parallel specialist agents inspect changed code paths (Logic & Correctness, Error Handling, Contract & Integration, Concurrency & State, Security) and aggregate findings.
  • Phase-driven workflow enforces reconnaissance, specialist review, verification, and a formal report to guide human reviewers.
  • Comprehensive artifacts include a manifest, steering caveats, and a final write-up to support pre-merge discussions and audits.

Quick Start

Ask PAAD to run agentic-review on your current branch against main to identify and report bugs before pushing.

Frequently Asked Questions about agentic-review

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

FAQPage Schema
How does multi-agent code review work for bug hunting before a merge?

Multi-agent code review deploys parallel specialist agents to inspect changed code paths for logic, error handling, and security risks. It aggregates findings across changed files to produce a structured report, surfacing defects before merging.

How do I automate branch review against main to check plan alignment?

Automate branch review by running a staged workflow that analyzes the current branch against main. This protocol enforces reconnaissance, specialist review, and verification phases to assess plan alignment and reduce regression risks.

Can I use multi-agent code review for diff analysis on specific areas like concurrency?

Yes, multi-agent code review supports diff analysis by assigning parallel specialist agents to specific areas. Agents inspect changed code paths for concurrency, state management, contract integration, and security vulnerabilities.

What is the best way to generate a structured pre-merge risk assessment report?

The best way to generate a structured pre-merge risk assessment is using a phase-driven workflow. It enforces reconnaissance and specialist review phases, producing a formal write-up and manifest to guide human reviewers and support audits.

Do I need any specific dependencies to run an automated agentic code review?

No specific dependencies are required to run an automated agentic code review. The workflow orchestrates tasks and deliverables internally using a staged review protocol, agent roles, and a manifest, requiring no external tool installations.