What specifically do the review agents focus on?

The skill launches five distinct agents focusing on general code quality, silent failures/exception handling, test coverage gaps, documentation accuracy, and type design invariants.

Does this skill post comments to GitHub automatically?

No. The skill is designed with a strict approval workflow. It will show you all proposed inline comments and the review body first, allowing you to edit or reject them before posting.

How does it avoid 'AI-style' robotic feedback?

The skill is instructed to use a casual, professional tone (like a senior colleague) and is strictly limited to 5-7 high-impact comments per review to avoid noise.

Can it review PRs in any programming language?

Yes. While it has specific logic for detecting Python and TypeScript files, its core tools like Grep and Read allow it to analyze any text-based source code.

Do I need any external tools to use this skill?

Yes, this skill requires the GitHub CLI (gh) to be installed and authenticated to your repository to read PR data and post comments.

Professional PR Reviewer

Name: Professional PR Reviewer
Author: AI-Builder-Team

byAI-Builder-Team

•

协作工具

Performs deep, multi-agent code reviews on GitHub pull requests with human-like inline comments and manual approval workflows.

The Professional PR Reviewer skill orchestrates specialized AI agents to conduct thorough, senior-level code reviews on GitHub pull requests. It simultaneously analyzes code quality, error handling, test coverage, and documentation accuracy to identify subtle bugs and architectural flaws that standard linters miss. To maintain high credibility, the skill automatically validates every agent finding against the actual source code, filtering out false positives. It drafts concise, conversational inline comments and a structured review summary, presenting everything for your approval before posting to GitHub via the official CLI.

主要功能

01False-Positive Validation: Automatically verifies every finding against the source code to ensure technical accuracy before reporting.

02Human-in-the-Loop Workflow: Requires explicit user approval for all inline comments and review summaries before any data is posted to GitHub.

03Seamless GitHub Integration: Uses the GitHub CLI to detect PR context, analyze diffs, and post-batch reviews with a single command.

042 GitHub stars

05Conversational Inline Feedback: Generates concise, senior-engineer style comments rather than robotic linter-like warnings.

06Parallel Multi-Agent Analysis: Runs specialized agents for code quality, silent failures, test coverage, and type design simultaneously.

使用场景

01Catching silent failures and edge-case exceptions that unit tests and linters frequently overlook.

02Automating deep technical peer reviews for complex feature branches and refactors.

03Ensuring architectural consistency and documentation accuracy across large team repositories.

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add ai-builder-team/ai-builder-plugin-marketplace review-pr

For use in Claude.ai and ChatGPT

Download Skill