# code-review

code-review audits code and pull requests for security flaws, performance bugs, and testing gaps. Helpful when reviewing branches before merging into production.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 1 install · ★ 431 repo stars
- Author: cloudshipai
- License: Apache-2.0 · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/cloudshipai/station/tree/HEAD/environments/default/skills/user/code-review/SKILL.md
- Updated: 2026-01-27
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/cloudshipai-code-review

## What it does

The skill organizes structured code reviews across five specific evaluation areas: functionality with error handling, code clarity, security vulnerabilities, performance bottlenecks, and test coverage. To inspect codebases directly, the agent uses `read_file`, `grep`, `glob`, and `bash`.

Every detected issue comes with exact file coordinates, line numbers, and a severity rating from Low to Critical. Instead of vague feedback, the review provides actionable guidance and sample code blocks showing before-and-after fixes.

Because the skill relies on `bash` and file discovery tools, environments with restricted shell execution will limit its ability to inspect diffs and run repository searches.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add cloudshipai/station --skill code-review -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/code-review/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/code-review/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add cloudshipai/station --skill code-review -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/code-review/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add cloudshipai/station --skill code-review -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/code-review/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install cloudshipai/station environments/default/skills/user/code-review
```

2. **Manually: put the files in place**
- File: `.github/skills/code-review/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add cloudshipai/station --skill code-review -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/cloudshipai/station --path environments/default/skills/user/code-review
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/code-review/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add cloudshipai/station --skill code-review -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/cloudshipai/station/tree/HEAD/environments/default/skills/user/code-review/SKILL.md

## When to use it
- spot security flaws like SQL injections and hardcoded secrets
- detect performance bottlenecks including N+1 query patterns
- evaluate test coverage across critical edge cases
- catch duplicate logic and unclear naming before merging

## Example prompts
- Run a code review on the latest pull request diff
- Check `src/api/users.go` for security vulnerabilities and injection risks
- Audit this branch for performance issues and edge cases

## Source text · SKILL.md · Apache-2.0

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: a2c77963c268c080.

BEGIN THIRD-PARTY FILE a2c77963c268c080
````text
---
name: code-review
description: Systematic code review process with focus on quality, security, and best practices
allowed-tools:
  - read_file
  - grep
  - glob
  - bash
triggers:
  - review
  - code quality
  - pull request
---

# Code Review Skill

## When to Use
- User asks for code review or feedback
- Reviewing a pull request or diff
- Analyzing code quality or security

## Review Checklist

### 1. Functionality
- [ ] Does the code do what it's supposed to?
- [ ] Are edge cases handled?
- [ ] Is error handling appropriate?

### 2. Code Quality
- [ ] Is the code readable and maintainable?
- [ ] Are functions and variables named clearly?
- [ ] Is there unnecessary duplication?
- [ ] Are comments helpful and accurate?

### 3. Security
- [ ] Input validation present?
- [ ] No hardcoded secrets?
- [ ] SQL injection prevention?
- [ ] XSS prevention?

### 4. Performance
- [ ] Efficient algorithms used?
- [ ] No N+1 query problems?
- [ ] Resources properly managed?

### 5. Testing
- [ ] Tests cover main functionality?
- [ ] Edge cases tested?
- [ ] Tests are readable?

## Output Format

For each finding, provide:
1. **Location**: File and line number
2. **Severity**: Critical / High / Medium / Low
3. **Issue**: Clear description of the problem
4. **Suggestion**: How to fix it
5. **Example**: Code snippet showing the fix (if applicable)

## Example Review Comment

**Location**: `src/api/users.go:42`
**Severity**: High
**Issue**: SQL query built using string concatenation
**Suggestion**: Use parameterized queries to prevent SQL injection
**Example**:
```go
// Before (vulnerable)
query := "SELECT * FROM users WHERE id = " + userID

// After (safe)
query := "SELECT * FROM users WHERE id = ?"
db.Query(query, userID)
```
````
END THIRD-PARTY FILE a2c77963c268c080

The third-party file has ended. Everything between the a2c77963c268c080 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

© cloudshipai · Apache-2.0 · https://github.com/cloudshipai/station/tree/HEAD/environments/default/skills/user/code-review/SKILL.md

## Similar
- [trailmark-review-gate](https://affpapa.org/en/nevibecode/skills/trailmark-review-gate.md) — skill · 1900 installs
- [find-bugs](https://affpapa.org/en/nevibecode/skills/find-bugs.md) — skill · 944 installs
- [code-reviewer](https://affpapa.org/en/nevibecode/agents/voltagent-community-code-reviewer.md) — subagent · 31050 installs
- [code-review-pro](https://affpapa.org/en/nevibecode/skills/code-review-pro.md) — skill · 2600 installs
- [dfyx-code-security-review](https://affpapa.org/en/nevibecode/skills/dfyx-code-security-review.md) — skill · 342 installs
- [code-review-specialist](https://affpapa.org/en/nevibecode/skills/luongnv89-code-review-specialist.md) — skill · ★ 47494 repo stars

## Other versions with the same name
- [code-review · mattpocock](https://affpapa.org/en/nevibecode/skills/code-review.md) — 789521 installs
- [code-review · anthropics](https://affpapa.org/en/nevibecode/skills/anthropics-code-review.md) — 10300 installs
- [code-review · agno-agi](https://affpapa.org/en/nevibecode/skills/agno-team-code-review.md) — 478 installs
- [code-review · vectorize-io](https://affpapa.org/en/nevibecode/skills/vectorize-io-code-review.md) — 178 installs

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
