Code Reviewer logo

Code Reviewer

Community
zhaono1
code-reviewer

Reviews pull requests and code changes for quality, security, and best practices. Use when user asks for code review, PR review, or mentions reviewing changes.

Overview

Publisherzhaono1
Repositoryagent-playbook
Skill namecode-reviewer
Stars
79
Forks
12
Bundled files
4
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by zhaono1 on GitHub. Read the source before you install it.

Installation

Install the Code Reviewer AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zhaono1/agent-playbook.git /tmp/agent-playbook
mkdir -p .claude/skills
cp -r /tmp/agent-playbook/skills/code-reviewer .claude/skills/code-reviewer
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Code Reviewer in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Code Reviewer on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Code Reviewer is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Code Reviewer

A comprehensive code review skill that analyzes pull requests and code changes for quality, security, maintainability, and best practices.

When This Skill Activates

This skill activates when you:

  • Ask for a code review
  • Request a PR review
  • Mention reviewing changes
  • Say "review this" or "check this code"

Review Process

Phase 1: Context Gathering

  1. Get changed files

    bash
    git diff main...HEAD --name-only
    git log main...HEAD --oneline
  2. Get the diff

    bash
    git diff main...HEAD
  3. Understand project context

    • Read relevant documentation
    • Check existing patterns in similar files
    • Identify project-specific conventions

Phase 2: Analysis Categories

1. Correctness
  • Logic is sound and matches requirements
  • Edge cases are handled
  • Error handling is appropriate
  • No obvious bugs or typos
2. Security
  • No hardcoded secrets or credentials
  • Input validation and sanitization
  • SQL injection prevention
  • XSS prevention (for frontend)
  • Authentication/authorization checks
  • Safe handling of user data
3. Performance
  • No N+1 queries
  • Appropriate caching
  • Efficient algorithms
  • No unnecessary computations
  • Memory efficiency
4. Code Quality
  • Follows DRY principle
  • Follows KISS principle
  • Appropriate abstractions
  • Clear naming conventions
  • Proper typing (if TypeScript)
  • No commented-out code
5. Testing
  • Tests cover new functionality
  • Tests cover edge cases
  • Test assertions are meaningful
  • No brittle tests
6. Documentation
  • Complex logic is explained
  • Public APIs have documentation
  • JSDoc/TSDoc for functions
  • README updated if needed
7. Maintainability
  • Code is readable
  • Consistent style
  • Modular design
  • Separation of concerns

Phase 3: Output Format

Use this structured format for review feedback:

markdown
# Code Review

## Summary
Brief overview of the changes (2-3 sentences).

## Issues by Severity

### Critical
Must fix before merge.

- [ ] **Issue Title**: Description with file:line reference

### High
Should fix before merge unless there's a good reason.

- [ ] **Issue Title**: Description with file:line reference

### Medium
Consider fixing, can be done in follow-up.

- [ ] **Issue Title**: Description with file:line reference

### Low
Nice to have improvements.

- [ ] **Issue Title**: Description with file:line reference

## Positive Highlights
What was done well in this PR.

## Suggestions
Optional improvements that don't require immediate action.

## Approval Status
- [ ] Approved
- [ ] Approved with suggestions
- [ ] Request changes

Common Issues to Check

Security Issues

IssuePatternRecommendation
Hardcoded secretsconst API_KEY = "sk-"Use environment variables
SQL injection\"SELECT * FROM...\" + user_inputUse parameterized queries
XSS vulnerabilityinnerHTML = user_inputSanitize or use textContent
Missing auth checkNew endpoint without @RequireAuthAdd authentication middleware

Performance Issues

IssuePatternRecommendation
N+1 queryLoop with database callUse eager loading or batch queries
Unnecessary re-renderMissing dependencies in useEffectFix dependency array
Memory leakEvent listener not removedAdd cleanup in useEffect return
Inefficient loopNested loops O(n²)Consider hash map or different algorithm

Code Quality Issues

IssuePatternRecommendation
Duplicate codeSimilar blocks repeatedExtract to function
Magic numberif (status === 5)Use named constant
Long functionFunction >50 linesSplit into smaller functions
Complex condition`a && b

Testing Issues

IssuePatternRecommendation
No testsNew feature without test fileAdd unit tests
Untested edge caseTest only covers happy pathAdd edge case tests
Brittle testTest relies on implementation detailsTest behavior, not implementation
Missing assertionTest doesn't assert anythingAdd proper assertions

Language-Specific Guidelines

TypeScript

  • Use unknown instead of any for untyped values
  • Prefer interface for public APIs, type for unions
  • Use strict mode settings
  • Avoid as assertions when possible

React

  • Follow Hooks rules
  • Use useCallback/useMemo appropriately (not prematurely)
  • Prefer function components
  • Use proper key props in lists
  • Avoid prop drilling with Context

Python

  • Follow PEP 8 style guide
  • Use type hints
  • Use f-strings for formatting
  • Prefer list comprehensions over map/filter
  • Use context managers for resources

Go

  • Handle errors explicitly
  • Use named returns for clarity
  • Keep goroutines simple
  • Use channels for communication
  • Avoid package-level state

Before Approving

Confirm the following:

  • All critical issues are addressed
  • Tests pass locally
  • No merge conflicts
  • Commit messages are clear
  • Documentation is updated
  • Breaking changes are documented

Scripts

Run the review checklist script:

bash
python3 scripts/review_checklist.py --base main --output review-checklist.md

References

  • references/checklist.md - Complete review checklist
  • references/security.md - Security review guidelines
  • references/patterns.md - Common patterns and anti-patterns

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Code Reviewer AI skill do?

Reviews pull requests and code changes for quality, security, and best practices. Use when user asks for code review, PR review, or mentions reviewing changes.

Why use Code Reviewer on TypingMind?

Because you install it once and use it with any model. Code Reviewer is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Code Reviewer in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zhaono1/agent-playbook/tree/main/skills/code-reviewer. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Code Reviewer?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Code Reviewer?

As many as you like. As long as a model supports skills, you can use Code Reviewer with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Code Reviewer AI skill free?

Yes. It is published on GitHub by zhaono1 under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇