code-review-preferences
Use when reviewing code, PRs, or discussing code quality standards. Applies team coding standards and review methodology.
Best use case
code-review-preferences is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Use when reviewing code, PRs, or discussing code quality standards. Applies team coding standards and review methodology.
Teams using code-review-preferences should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/code-review-preferences/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How code-review-preferences Compares
| Feature / Agent | code-review-preferences | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Use when reviewing code, PRs, or discussing code quality standards. Applies team coding standards and review methodology.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Cursor vs Codex for AI Workflows
Compare Cursor and Codex for AI coding workflows, repository assistance, debugging, refactoring, and reusable developer skills.
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
SKILL.md Source
<essential_principles> ## Code Review Philosophy Reviews exist to: 1. **Catch bugs** before production 2. **Share knowledge** across the team 3. **Maintain consistency** in the codebase Reviews do NOT exist to: - Show off knowledge - Enforce personal style preferences - Block progress unnecessarily ## The 3-Pass Method ### Pass 1: Understand (don't comment yet) - What is this change trying to do? - What files are affected? - What's the scope? ### Pass 2: Correctness - Are there bugs? - Are edge cases handled? - Are there security issues? ### Pass 3: Improvements (max 5 comments) - Is it readable? - Is it maintainable? - Are there better patterns? ## Review Standards ### Must Check - [ ] Tests pass - [ ] No obvious bugs - [ ] Edge cases from PR description handled - [ ] No security vulnerabilities - [ ] No secrets in code ### Should Check - [ ] Code is readable - [ ] Functions are reasonably sized (<50 lines) - [ ] Names are clear and descriptive - [ ] Error messages are helpful ### Nice to Check - [ ] Performance considerations - [ ] Documentation updated - [ ] Consistent with existing patterns ## Feedback Style **DO:** - Ask questions: "What happens if X is null?" - Be specific: "Line 42: Consider using a guard clause" - Acknowledge good work: "Nice refactor here" - Limit comments: Max 5 per review **DON'T:** - Dictate: "You must do X" - Be vague: "This could be better" - Nitpick style: "I prefer single quotes" - Pile on: 20 comments is overwhelming </essential_principles> <intake> What would you like me to review? 1. **Format** - Paste the code/diff here - Reference a file with @filename - Describe the PR and I'll ask questions 2. **Context** - Bug fix - New feature - Refactor - Performance optimization - Other: ___ 3. **Specific concerns?** (Security, performance, breaking changes, etc.) **I'll wait for your answers before starting the review.** </intake>
Related Skills
Medical Imaging AI Literature Review Skill
Write comprehensive literature reviews following a systematic 7-phase workflow.
performing-security-code-review
Execute this skill enables AI assistant to conduct a security-focused code review using the security-agent plugin. it analyzes code for potential vulnerabilities like sql injection, xss, authentication flaws, and insecure dependencies. AI assistant uses this skill wh... Use when assessing security or running audits. Trigger with phrases like 'security scan', 'audit', or 'vulnerability'.
iam-policy-reviewer
Iam Policy Reviewer - Auto-activating skill for Security Advanced. Triggers on: iam policy reviewer, iam policy reviewer Part of the Security Advanced skill category.
reviewing-cli-command
Provides checklist for reviewing Typer CLI command implementations. Covers structure, Annotated syntax, error handling, exit codes, display module usage, destructive action patterns, and help text conventions. Use when user asks to review/check/verify a CLI command, wants feedback on implementation, or asks if a command follows best practices.
Paper Summary & Review Skill
## 功能描述
recipe-review-overdue-tasks
Find Google Tasks that are past due and need attention.
recipe-review-meet-participants
Review who attended a Google Meet conference and for how long.
web-design-reviewer
This skill enables visual inspection of websites running locally or remotely to identify and fix design issues. Triggers on requests like "review website design", "check the UI", "fix the layout", "find design problems". Detects issues with responsive design, accessibility, visual consistency, and layout breakage, then performs fixes at the source code level.
sql-code-review
Universal SQL code review assistant that performs comprehensive security, maintainability, and code quality analysis across all SQL databases (MySQL, PostgreSQL, SQL Server, Oracle). Focuses on SQL injection prevention, access control, code standards, and anti-pattern detection. Complements SQL optimization prompt for complete development coverage.
reviewing-oracle-to-postgres-migration
Identifies Oracle-to-PostgreSQL migration risks by cross-referencing code against known behavioral differences (empty strings, refcursors, type coercion, sorting, timestamps, concurrent transactions, etc.). Use when planning a database migration, reviewing migration artifacts, or validating that integration tests cover Oracle/PostgreSQL differences.
review-and-refactor
Review and refactor code in your project according to defined instructions
power-bi-model-design-review
Comprehensive Power BI data model design review prompt for evaluating model architecture, relationships, and optimization opportunities.