team-reviewer

Official

Team-driven parallel PR reviews with scores

Authorparisgroup-ai
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Large or complex pull requests and local diffs are hard to review thoroughly by a single reviewer; this Skill orchestrates multiple specialized reviewer agents in parallel, consolidates their findings, and produces a prioritized, scored report to speed decision-making and reduce missed issues.

Core Features & Use Cases

  • Scatter-gather review: Spawn specialized agents (security, code-quality, type-design, test-coverage, commit-hygiene, silent-failure) to run in parallel against a PR or local diff.
  • Automated aggregation and scoring: Parse agent outputs, normalize severity-tagged findings, compute weighted dimension scores, and produce a final verdict (CLEAN, NEEDS_ATTENTION, SIGNIFICANT_ISSUES, BLOCK).
  • Integrations & fallbacks: Uses the gh CLI to fetch PR diffs or falls back to local git diffs, handles agent timeouts and unparseable outputs with conservative defaults.
  • Use case: Run a quick security-and-quality pass on a large feature branch before merge to surface critical issues and quantify overall readiness.

Quick Start

Ask the assistant to run the team-reviewer skill against the current branch or a specific PR number to produce a scored review report.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 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: team-reviewer
Download link: https://github.com/parisgroup-ai/imersao-ia-setup/archive/main.zip#team-reviewer

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 471,000+ vetted skills library on demand.