swarm-pr-review

Automate graph-guided pull request reviews with parallel exploration and reviewer validation.

Updated Jun 19, 2026
One-click install
npx skills add https://github.com/refernandes/toktrim --skill swarm-pr-review-refernandes
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: swarm-pr-review
Source: https://github.com/refernandes/toktrim/tree/main/.opencode/skills/swarm-pr-review
Command: npx skills add https://github.com/refernandes/toktrim --skill swarm-pr-review-refernandes

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Swarm PR Review addresses the challenge of conducting comprehensive and accurate pull request reviews, minimizing false positives while maximizing recall.

Core Features & Use Cases

  • Structured Review Workflow: Automates a multi-phase process for review, encompassing scope detection, obligation extraction, signal ingestion, and parallel exploration.
  • Parallel Exploration: Leverages parallel lanes for exploring code and dependencies, enhancing efficiency and coverage.
  • Independent Reviewer Validation: Ensures objectivity in the review process by validating findings through independent reviewer validation.
  • Metrics & Knowledge Writeback: Integrates feedback into a knowledge base for future reference and continuous improvement.
  • Use Case: Ideal for engineering teams looking to streamline pull request reviews, enhance code quality, and maintain a secure development environment.

Quick Start

Run the swarm-pr-review skill on your PR to initiate a structured review.

Frequently Asked Questions about swarm-pr-review

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

FAQPage Schema
How do I automate a pull request review to reduce false positives and maximize recall?

Automated pull request review reduces false positives and maximizes recall by using a graph-guided, tool-augmented Swarm process. It executes multi-phase scope detection, obligation extraction, and signal ingestion to ensure comprehensive code analysis.

What is the benefit of using parallel exploration for code analysis during a pull request review?

Parallel exploration during code analysis leverages multiple lanes to investigate code and dependencies simultaneously. This approach significantly enhances review efficiency and coverage compared to sequential processing, ensuring thorough validation.

How does independent reviewer validation work in automated pull request workflows?

Independent reviewer validation ensures objectivity in the pull request workflow by cross-checking findings from parallel exploration. This validation step minimizes false positives and guarantees that detected code issues are accurately verified.

Can I track metrics and write back knowledge from automated code analysis to improve future reviews?

Metrics tracking and knowledge writeback integrate validated code analysis feedback into a centralized knowledge base. This continuous improvement loop captures review signals and obligations, enhancing the accuracy of future pull request assessments.

Does the parallel processing pull request review workflow require external dependencies?

The parallel processing pull request review workflow operates without external dependencies, relying solely on internal scripts. This standalone configuration allows immediate execution of the structured review process within your existing environment.

When should I use a graph-guided Swarm review process instead of standard code analysis tools?

A graph-guided Swarm review process is ideal for engineering teams needing deep pull request reviews with low false-positive tolerance and high recall. It replaces standard tools when comprehensive scope detection and parallel validation are required.