skills.rest
SAZO-KR
SAZO-KROFFICIAL
Explore all skills by this author →
WebsiteGitHub

review

Launch five parallel fresh-context code review agents until all pass.

Updated Jan 2, 2026
Search Tags:#code-review#multi-perspective#ci#pull-request#parallel-processing#review-agents
One-click install
npx skills add https://github.com/SAZO-KR/sazo-toolkit --skill review-sazo-kr
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/SAZO-KR/sazo-toolkit/tree/main/packages/ai-harness/skills/review
Command: npx skills add https://github.com/SAZO-KR/sazo-toolkit --skill review-sazo-kr

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates the post-CI review process by orchestrating independent, fresh-context code reviews, ensuring every cycle begins without leaked history and all feedback is re-evaluated before merging.

Core Features & Use Cases

  • Launches five parallel review agents, each in a new session, to evaluate changes from distinct perspectives.
  • Reconciles results by requiring all agents to PASS before proceeding; supports iterative fixes and re-runs of CI.
  • Provides deterministic, auditable review workflows that reduce bias and improve review quality.

Quick Start

Initiate the review workflow using the current diffs to spin up five fresh-review agents and start the cycle.

Frequently Asked Questions about review

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

FAQPage Schema
How do I automate multi-perspective code reviews after CI passes?▼

Automate post-CI code review by launching five parallel review agents with fresh contexts to evaluate pull-request diffs. Each agent independently assesses changes from distinct perspectives, and all must pass before merging, ensuring unbiased critique and reducing bias.

Why use fresh contexts for parallel review agents in pull-request workflows?▼

Fresh contexts for parallel review agents ensure every review cycle begins without leaked history. This deterministic orchestration re-evaluates all feedback independently, preventing bias carry-over and improving overall code review quality across diverse codebases.

Does multi-agent code review work with iterative fixes and re-runs?▼

Multi-agent code review supports iterative fixes and re-runs by applying a gating condition. If any of the five review agents find issues, the workflow requires fixes and re-runs of CI until all independent reviewers pass, ensuring auditable review workflows.

Can I use parallel review agents across diverse codebases for unbiased critique?▼

Parallel review agents apply to pull-request workflows across diverse codebases where unbiased critique is needed. The deterministic orchestration manages independent sessions for each agent, aggregating results to provide auditable and objective code assessments.

What's the best way to gate pull-request merges using independent review agents?▼

Gate pull-request merges by requiring all five independent review agents to PASS before proceeding. This deterministic workflow aggregates multi-perspective results, enforcing iterative fixes and re-runs if any issues are found, ensuring high review quality.

Related Skills

Explore More Software Engineering Skills→
edobryedobry
6

review-pr

Analyze pull requests and post structured GitHub PR reviews.

Community
Advanced
supersuit-techsupersuit-tech
4

fix-ci

Trigger GitHub Actions CI and audit workflows, collect failure logs, and iterate until both pass.

Official
Intermediate
dalagerdalager
1

github-workflow-automation

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

Community
Advanced
jamesjlundinjamesjlundin
32

pr-review

Analyze pull requests and generate structured review reports.

Community
Intermediate