skills.rest
adamfeldman
adamfeldmanCOMMUNITY
Explore all skills by this author →
Website𝕏@adamfeldmanGitHub

do:review

Performs AI-assisted code reviews on GitHub pull requests and branches, generating categorized todo files and summary reports.

Updated Aug 27, 2026
Search Tags:#code quality#automation#developer tools#code review#pull request#ai agents
One-click install
npx skills add https://github.com/adamfeldman/compound-workflows --skill do-review
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: do:review
Source: https://github.com/adamfeldman/compound-workflows/tree/main/plugins/compound-workflows/skills/do-review
Command: npx skills add https://github.com/adamfeldman/compound-workflows --skill do-review

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

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.

Frequently Asked Questions about do:review

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

FAQPage Schema
How do I automate pull request code reviews using AI agents?▼

Automated multi-agent code review uses specialized AI agents to analyze GitHub pull requests in parallel, categorizing findings by severity and generating actionable todo files. This ensures comprehensive analysis without manual effort.

How does multi-agent code review prevent context exhaustion in large pull requests?▼

Multi-agent code review prevents context exhaustion by persisting all agent findings directly to disk. This context-lean operation ensures review data and traceability persist even if the session is compacted during the pull request analysis.

Can I use automated code review to categorize pull request issues by severity?▼

Automated code review categorizes pull request issues into structured findings like security and performance, assigning severity levels such as P1, P2, and P3 to help developers prioritize code quality improvements.

What is the best way to generate actionable todo files from pull request findings?▼

Generating actionable todo files from pull request findings is achieved by synthesizing AI agent reports and writing individual tasks to disk. This creates long-term traceability and facilitates immediate issue tracking for developers.

Does automated code review work with branches or only submitted pull requests?▼

Automated code review works with both submitted GitHub pull requests and direct branches. Specialized AI agents analyze code changes across various dimensions and synthesize a summary report for either target.

Related Skills

Explore More Software Engineering Skills→
nanocoainanocoai
30.5k

add-github

Configure GitHub webhooks and API keys for automated pull request and issue comments.

Official
Intermediate
beratcelik1beratcelik1
1

review-code

Review Python and TypeScript code changes with parallel agents and P1/P2/P3 severity findings.

Community
Advanced
VoDaiLoczVoDaiLocz
24

lint-and-validate

Automate linting and static analysis of code in CI pipelines.

Community
Intermediate
fabioc-alohafabioc-aloha

lint-clean-markdown

Reduce Markdown lint errors by enforcing formatting rules during authoring.

Community
Basic