skills.rest
bosmadev
bosmadevCOMMUNITY
Explore all skills by this author →
GitHub

review

Coordinate multi-agent code reviews for security, design, and quality issues.

Updated Aug 23, 2026
Search Tags:#security#a11y#multi-agent#code-review#serena#pull-request
One-click install
npx skills add https://github.com/bosmadev/claude --skill review-bosmadev
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/bosmadev/claude/tree/main/skills/review
Command: npx skills add https://github.com/bosmadev/claude --skill review-bosmadev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Unified, multi-aspect code reviews that integrate security and accessibility checks to catch issues early.

Core Features & Use Cases

  • Code quality and bug detection across large codebases
  • Security and design reviews (OWASP and WCAG AAA) by default
  • Parallel agent orchestration with configurable scope and models
  • Pre-review quality context (Biome/Knip/TypeScript) to guide evaluation

Quick Start

Invoke /review to start a full, parallel review with default settings.

Frequently Asked Questions about review

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

FAQPage Schema
How do I automate a multi-agent code review for security and design?▼

Automate a multi-agent code review by invoking the review workflow to coordinate parallel agents that surface security, design, and quality issues across your repository. It orchestrates multiple configurable models to evaluate code in parallel.

What does a comprehensive code review check for by default?▼

A comprehensive code review checks for code quality and bugs, alongside security and design issues. By default, it evaluates repositories against OWASP security standards and WCAG AAA accessibility guidelines.

Can I run a code review on a specific Git branch or pull request?▼

Yes, you can run a code review on a specific Git branch or pull request. The review workflow supports configurable scopes including working, impact, branch, staged, path, and pr targets.

How does semantic code analysis work during a repository review?▼

Semantic code analysis during a repository review uses Serena to inject automated context and perform deep semantic evaluations. This process guides the agents by providing pre-review quality checks from tools like Biome, Knip, or TypeScript.

Do I need to configure agent counts and models for a parallel code review?▼

No, you do not need to configure agent counts and models to start a parallel code review. Default settings automatically initiate a full parallel review, though these parameters remain configurable for custom scopes.

Related Skills

Explore More Software Engineering Skills→
uxnameuxname
30

check

Run TypeScript quality checks with Prisma, Biome, and Knip.

Community
Advanced
iani-kuliiani-kuli

iterate-pr

Automate CI failure fixes and code review feedback on GitHub pull requests.

Community
Advanced
eventua11yeventua11y
1

fixing-accessibility-issues

Automates remediation of accessibility defects in UI code from linting tools.

Official
Advanced
umairinayatumairinayat
5

parallel-agents

Coordinate multiple specialized agents in parallel and sequential orchestration sessions.

Community
Advanced