audit

Review pending git diffs for correctness, security, and style issues.

Updated Jul 8, 2026
One-click install
npx skills add https://github.com/missdeer/skills --skill audit-missdeer
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: audit
Source: https://github.com/missdeer/skills/tree/main/audit
Command: npx skills add https://github.com/missdeer/skills --skill audit-missdeer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill automates the initial pass of code reviews, identifying potential bugs, security vulnerabilities, and style violations in pending changes before a human reviewer even looks at the code.

Core Features & Use Cases

  • Automated Diff Analysis: Automatically detects and reviews pending changes or branch-vs-master differences.
  • Structured Reporting: Categorizes findings into must-fix, should-fix, and nit, ensuring clear actionable feedback.
  • Use Case: Use this before submitting a pull request to catch common errors like nil dereferences, SQL injection risks, or deviations from project coding standards.

Quick Start

Ask the assistant to audit the current changes in the repository to identify potential issues and coding standard violations.

Frequently Asked Questions about audit

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

FAQPage Schema
How do I automate code review for pending git diffs?

Automating code review for pending git diffs involves running a structured analysis that uses read-only git commands to check for correctness, security, and style issues. It automatically detects pending changes and categorizes findings into must-fix, should-fix, and nit.

What kind of security and style issues can automated static analysis catch in a git diff?

Automated static analysis on a git diff can catch common errors such as nil dereferences, SQL injection risks, and deviations from project coding standards. It analyzes the diff output against defined rules to flag these potential bugs before submission.

Do I need a specific environment to run automated static analysis on my repository changes?

Yes, performing automated code review requires a configured Codex CLI environment to process the git diff and generate feedback. The tool operates within this setup by executing read-only git commands to analyze your pending changes.

When should I run an automated code review on my branch?

You should run an automated code review on your branch before submitting a pull request. This catches potential bugs, security vulnerabilities, and style violations early, ensuring common errors are resolved before a human reviewer looks at the code.

How does automated diff analysis categorize code review findings?

Automated diff analysis categorizes code review findings into three levels: must-fix, should-fix, and nit. This structured reporting ensures clear, actionable feedback by prioritizing security vulnerabilities and correctness issues over minor style deviations.