do:review

Community

Automated multi-agent code review.

Authoradamfeldman
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill automates the process of conducting thorough code reviews by leveraging multiple specialized AI agents, ensuring comprehensive analysis and identifying potential issues across various aspects of the codebase.

Core Features & Use Cases

  • Parallel Agent Analysis: Runs multiple AI agents concurrently (e.g., TypeScript reviewer, security auditor, performance analyst) to cover different review dimensions.
  • Disk-Persisted Outputs: All agent findings are written to disk, preventing context exhaustion and ensuring that review data persists even if the session is compacted.
  • Structured Findings: Organizes review feedback into categories like security, performance, and architecture, assigning severity levels (P1, P2, P3).
  • Todo File Generation: Automatically creates actionable todo files for each identified finding, facilitating issue tracking and resolution.
  • Use Case: When a pull request is submitted, this Skill can be dispatched to perform an in-depth, multi-faceted review, generating a report and creating specific tasks for developers to address before merging.

Quick Start

Use the do:review skill to analyze the current branch for code review.

Dependency Matrix

Required Modules

None required

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: do:review
Download link: https://github.com/adamfeldman/compound-workflows/archive/main.zip#do-review

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.