Which aspects of the code are analyzed during a review?

The review covers six specialized areas: security vulnerabilities, logic bugs, general code quality, API/contract design, test coverage, and historical git context.

What is the 'Quality Gate' feature?

The Quality Gate provides a clear 'READY TO COMMIT' or 'NEEDS FIXES' status based on the severity and quantity of issues found during the audit.

Does it review the entire codebase every time?

No, it is optimized to focus specifically on local uncommitted changes (git diff) to provide fast, relevant feedback on your current work.

Can it follow my specific project guidelines?

Yes, it automatically scans for AGENTS.md, README.md, and constitution.md files to ensure the review adheres to your specific coding standards and instructions.

How does this skill handle false positives?

The skill uses a secondary validation phase where a Haiku agent scores every identified issue. Only issues with a confidence score of 80 or higher are included in the final report.

Local Changes Code Reviewer

Name: Local Changes Code Reviewer
Author: Gamezar

byGamezar

0•

安全与测试

Conducts deep, multi-agent audits of uncommitted local code changes to catch bugs and security risks before they reach the repository.

This skill automates the pre-commit review process by deploying a swarm of specialized AI agents to analyze local git diffs. It systematically evaluates code for security vulnerabilities, logic bugs, maintainability, and architectural consistency while filtering results through a confidence scoring mechanism to minimize noise. Ideal for developers wanting to ensure high-quality commits, it provides a structured report that categorizes issues by impact, provides file-specific citations, and offers actionable improvement suggestions to maintain high development standards.

主要功能

01Multi-agent analysis covering security, bug hunting, quality, and contracts

02Historical context analysis using git history and blame data

03Confidence scoring system that filters out false positives and trivial nitpicks

04Automated 'Ready to Commit' quality gate assessment

050 GitHub stars

06Adherence to project-specific guidelines from AGENTS.md and README files

使用场景

01Ensuring code changes align with existing project architecture and guidelines

02Identifying security vulnerabilities in new code modifications before commit

03Performing a final audit on a feature branch before opening a pull request

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add gamezar/opencode-cek code-review-review-local-changes

For use in Claude.ai and ChatGPT

主要功能

01Multi-agent analysis covering security, bug hunting, quality, and contracts

02Historical context analysis using git history and blame data

03Confidence scoring system that filters out false positives and trivial nitpicks

04Automated 'Ready to Commit' quality gate assessment

050 GitHub stars

06Adherence to project-specific guidelines from AGENTS.md and README files

使用场景

01Ensuring code changes align with existing project architecture and guidelines

02Identifying security vulnerabilities in new code modifications before commit

03Performing a final audit on a feature branch before opening a pull request

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add gamezar/opencode-cek code-review-review-local-changes

For use in Claude.ai and ChatGPT