review

Coordinate parallel specialist code reviews and aggregate findings into unified reports.

15|1|Updated Mar 29, 2026

Search Tags:#automation #reporting #swarm #quality-gate #code-review #specialists #parallel-review

Ready to run

npx skills add https://github.com/duronext/jig --skill review-duronext

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: review
Source: https://github.com/duronext/jig/tree/main/core/skills/review
Command: npx skills add https://github.com/duronext/jig --skill review-duronext

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Coordinating code reviews across multiple specialists can be slow and brittle; this Skill streamlines pre-PR and quality-gate reviews by dispatching a swarm of focused reviewers and aggregating their findings into a single report.

Core Features & Use Cases

Dispatches parallel specialist reviewers (security, correctness, performance, and more) to cover multiple concerns concurrently.
Integrates with code-review, team-dev, and /review invocations to enforce thorough, consistent reviews during PRs and gate checks.
Produces a unified swarm report with actionable findings, enabling faster decisions and clearer remediation guidance.

Quick Start

Invoke /review during a code review to start the swarm-driven evaluation.

Frequently Asked Questions about review

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

FAQPage Schema

How do I run parallel code reviews with a swarm of specialists?▼

Parallel code reviews with a swarm of specialists are dispatched by invoking /review during your pre-PR verification. The swarm concurrently evaluates security, correctness, and performance, then aggregates findings into a single unified report to guide remediation.

What is configuration-driven discovery for swarm specialist reviewers?▼

Configuration-driven discovery is the mechanism that automatically identifies and selects tier-based specialist reviewers for the code-review swarm. It enforces consistent participation across focused domains and outputs a unified set of actionable findings.

Can I integrate automated code review into team-dev quality gates?▼

Yes, automated code review integrates directly into team-dev quality gates and pre-PR checks. Invoking /review dispatches the specialist swarm to enforce thorough, consistent verification and produces a unified report for faster decisions.

Does parallel review work without external dependencies or components?▼

Yes, parallel review operates with zero external dependencies or components. It internally manages the configuration-driven discovery, tier-based participation, and automated aggregation required to dispatch the specialist swarm and report findings.

What is the best way to aggregate code review findings from multiple specialists?▼

The best way to aggregate code review findings is dispatching a parallel specialist swarm via /review. It automates the aggregation of security, correctness, and performance findings into a single unified report, accelerating pre-PR remediation decisions.

When should I not use a parallel swarm for pre-PR code review?▼

You should avoid a parallel swarm for pre-PR code review if your changes are trivial and do not warrant multi-specialist verification across security, correctness, and performance, as dispatching tier-based reviewers adds overhead for minimal remediation value.