skills.rest
Ankurjain1121
Ankurjain1121COMMUNITY
Explore all skills by this author →
WebsiteGitHub

brutal-review

Orchestrate five code-review agents and output a structured final report.

1|Updated Jan 15, 2026
Search Tags:#architecture#security#MCP#multi-agent#code-review#weighted-scores#brutal-review
One-click install
npx skills add https://github.com/Ankurjain1121/dev-workflow-skills --skill brutal-review-ankurjain1121
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: brutal-review
Source: https://github.com/Ankurjain1121/dev-workflow-skills/tree/main/plugins/brutal-review/skills/brutal-review
Command: npx skills add https://github.com/Ankurjain1121/dev-workflow-skills --skill brutal-review-ankurjain1121

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill enables a zero-tolerance, multi-agent code-review workflow that orchestrates five specialized reviewers (Security, Architecture, Quality, Performance, Style) using MCP integration to enforce rigorous quality and security thresholds.

Core Features & Use Cases

  • Multi-agent orchestration: Spawns five dedicated agents to assess code quality, security, architecture, performance, and style in parallel.
  • Weighted scoring & zero-tolerance: Applies mode-based weights and strict thresholds to determine pass/fail outcomes.
  • Comprehensive reporting: Aggregates results into a final report detailing all findings and required remediations.

Quick Start

  • Use the /brutal-review command to initiate a FULL review on the target repository or changeset.

Frequently Asked Questions about brutal-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 architecture?▼

Automate multi-agent code review by orchestrating five specialized agents to assess security, architecture, quality, performance, and style in parallel, using MCP tools for best-practice alignment and weighted scoring.

Can I run a code review focused only on security vulnerabilities?▼

Yes, you can run a code review focused only on security vulnerabilities by selecting the SECURITY mode, which targets specific threat vectors while excluding broader architecture or performance checks.

What is a zero-tolerance code review and how does weighted scoring work?▼

A zero-tolerance code review enforces strict quality thresholds where any failing grade results in a fail outcome. Weighted scoring applies mode-based weights to five specialized agents to determine the final pass/fail result.

Does the multi-agent code review work with different programming stacks?▼

Yes, the multi-agent code review applies to software projects across all stacks. It uses MCP tools like context7 and exa to align with language-agnostic best practices during the assessment.

What's the best way to compare code quality between two different versions?▼

The best way to compare code quality between versions is to use the COMPARE mode, which evaluates differences across dedicated agents and aggregates the results into a structured final report.

Do I need MCP tools to run a comprehensive code review?▼

Yes, MCP tools are required for best results. The workflow relies on context7, exa, grep, and sequential-thinking MCP tools to align with best practices and compute weighted scores accurately.

Related Skills

Explore More Software Engineering Skills→
langchain-ailangchain-ai
27.5k

web-research

Orchestrate multi-source web research with parallel subagents and cited reports.

Official
Advanced
blake-goodwynblake-goodwyn

pr-review

Automate pull request code review with confidence-scored issues.

Community
Advanced
softmgsoftmg

github-workflow-automation

Automate GitHub Actions workflow generation and CI/CD pipeline management.

Official
Advanced
PriyanshKuniyalPriyanshKuniyal

sast-configuration

Configures and manages SAST tools for automated vulnerability detection in CI/CD pipelines.

Community
Advanced