skills.rest
6BNBN
6BNBNCOMMUNITY
Explore all skills by this author →
GitHub

code-review

Automate pull request and code diff reviews with a structured multi-pass AI workflow.

134|12|Updated Feb 20, 2026
Search Tags:#diff analysis#developer tools#code review#pull request#AI assistant#github
One-click install
npx skills add https://github.com/6BNBN/FlowPilot --skill code-review-6bnbn
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: code-review
Source: https://github.com/6BNBN/FlowPilot/tree/main/%E5%85%BC%E5%AE%B9codex%40cursor%E4%B8%80%E9%94%AE%E5%AE%89%E8%A3%85%E6%8A%80%E8%83%BD/codex%E4%B8%80%E9%94%AE%E5%AE%89%E8%A3%85%E6%8A%80%E8%83%BD/.codex-home-claude-parity/skills/code-review
Command: npx skills add https://github.com/6BNBN/FlowPilot --skill code-review-6bnbn

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the process of reviewing pull requests and code diffs, ensuring high-signal, actionable feedback and adherence to project standards.

Core Features & Use Cases

  • Structured Review Workflow: Guides the AI through a systematic review process, from eligibility checks to confidence-tested findings.
  • Parallel Review Passes: Employs multiple AI agents with different review lenses (conventions, correctness, history) for comprehensive analysis.
  • Actionable Feedback Filtering: Filters out noise, focusing only on critical issues relevant to a senior engineer.
  • Use Case: When a developer submits a pull request, this Skill can automatically analyze the changes, identify potential bugs or style violations, and provide concise, actionable feedback directly in the PR comments or session.

Quick Start

Use the code-review skill to review the current pull request, focusing on correctness and adherence to project conventions.

Frequently Asked Questions about code-review

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

FAQPage Schema
How do I automate pull request reviews for my code diffs?▼

Automating pull request reviews involves using a multi-pass AI workflow to analyze code diffs for correctness and conventions. The system filters out noise to deliver concise, actionable feedback directly in your PR comments.

Do I need GitHub CLI installed to review pull requests with AI?▼

Yes, you need the GitHub CLI (gh) installed for direct interaction when automating pull request reviews. The Skill uses gh to fetch code diffs and adhere to defined review rules for actionable findings.

How does AI code review handle large pull requests with multiple file changes?▼

AI code review uses parallel review passes with different lenses like conventions, correctness, and history to handle large pull requests. This multi-agent approach systematically analyzes diffs to filter noise and focus on critical issues.

What's the best way to ensure AI-generated code review feedback is actionable?▼

Ensure actionable AI code review feedback by enforcing confidence-tested findings and defined project review rules. The workflow filters out noise, focusing only on critical issues relevant to a senior engineer.

Can I use automated diff analysis for checking code correctness and project conventions?▼

Yes, you can use automated diff analysis to check code correctness and project conventions. The AI assistant applies multiple parallel review lenses to ensure high-signal findings and strict adherence to project standards.

Related Skills

Explore More Software Engineering Skills→
x402agentx402agent

review-github-pr

Summarizes GitHub pull requests by distilling diffs and highlighting design decisions.

Community
Intermediate
mmartinsolivmmartinsoliv

pr-review-pending

Create pending GitHub pull request review comments from code review findings.

Community
Advanced
moberghrmoberghr
6

pre-commit-review

Review staged git changes for security and compliance issues.

Official
Advanced
samChang72samChang72
1

code-review

Automates code reviews to detect bugs, style violations, and performance issues in submissions via static analysis tools.

Community
Intermediate