code-reviewer
Use when reviewing code, conducting code reviews, analyzing pull requests, or when the user mentions "code review", "PR review", "code quality", or "static…
Skill by ntk148v
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/ntk148v-code-reviewer
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/code-reviewer
What's inside
- Skill name
code-reviewer- Description
- Use when reviewing code, conducting code reviews, analyzing pull requests, or when the user mentions "code review", "PR review", "code quality", or "static analysis".
- License
- MIT
- Instructions
- 411 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Code Reviewer
## Overview
Code Reviewer provides a systematic approach to conducting thorough code reviews. It helps identify code quality issues, potential bugs, security vulnerabilities, performance problems, and ensures adherence to best practices and coding standards before merging changes.
## When to Use
Use this skill when:
- Reviewing pull requests or merge requests
- Conducting code reviews
- The user mentions "code review", "PR review", or "review this code"
- Analyzing code quality
- Checking for bugs or security issues
- Validating adherence to coding standards
- Pre-merging code changes
## Review Process
### Phase 1: Understand the Change
Before diving into details, understand the scope and purpose:
1. **Read the PR description**
- What is the purpose of this change?
- What problem does it solve?
- Are there any related issues or tickets?
2. **Identify the scope**
- What files were changed?
- How large is the change?
- Is this a breaking change?
3. **Check the baseline**
- Review existing code in affected areas
- Understand the context and architecture
- Identify any related code that might be affected
### Phase 2: Security Review
Check for security vulnerabilities first:
#### Input Validation
```javascript
// ❌ BAD: Unvalidated input
function queryDatabase(userInput) {
return db.query(`SELECT * FROM users WHERE id = ${userInput}`);
}
// ✅ GOOD: Parameterized query
function queryDatabase(userId) {
return db.query("SELECT * FROM users WHERE id = ?", [userId]);
}
```
#### Authentication & Authorization
- Verify user is authenticated before sensitive operations
- Check that authorization checks are properly enforced
- Look for privilege escalation possibilities
#### Data Exposure
- Ensure sensitive data is not logged or exposed
- Check for proper encryption of sensitive information
- Verify secure storage of credentials and secrets
#### Common Security Issues
| Issue | What to Check | Fix |
| -------------- | ------------------------------------------- | --------------------------- |
| SQL Injection | String concatenation in queries | Use parameterized queries |
| XSS | Unescaped user input in HTML | Sanitize and escape output |
| CSRF | Missing CSRF tokens on forms | Add anti-CSRF tokens |
| SSRF | User-provided URLs fetched server-side | Validate and sanitize URLs |
| IDOR | Direct object references without auth check | Verify authorization |
| Path Traversal | File paths constructed from user input | Validate and sanitize paths |
### Phase 3: Code Quality Review
#### Code Structure
- **Single Responsibility**: Does each function/class do one thing?
- **DRY (Don't Repeat Yourself)**: Is there code duplication?
- **Clean abstractions**: Are interfaces clean and focused?
- **Modularity**: Is code properly organized into modules?
```python
# ❌ BAD: God function doing multiple things
def process_user(user_data):
validate(user_data)
save_to_db(user_data)
send_email(user_data)
update_analytics(user_data)
log_action(user_data)
# ✅ GOOD: Separated concerns
def process_user(user_data):
validate(user_data)
save_to_db(user_data)
notify_user(user_data)
track_action(user_data)
```
#### Error Handling
- Are errors properly handled?
- Are error messages user-friendly?
- Are errors logged appropriately?
- Are resources cleaned up in finally blocks?
```javascript
// ❌ BAD: Swallowed error
try {
doSomething();
} catch (e) {
// Silently ignoredFrom ntk148v/skills, MIT.
More from ntk148v/skills
- 0.497score
skill-authoring
ntk148v
Use when creating, editing, auditing, or validating Agent Skills.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
repo-analyzer
ntk148v
Use when the user mentions "analyzing a project", "analyzing a repository", "analyzing GitHub", "project analysis", "source code analysis", "architecture…
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
caveman
ntk148v
Ultra-compressed communication mode.
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
grill
ntk148v
Interview the user relentlessly about a plan, design, or domain model until reaching shared understanding.
SkillCFreshness: C★ 1Claude Code +9 - 0.461score
handoff
ntk148v
Compact the current conversation into a handoff document for another agent to pick up.
SkillCFreshness: C★ 1Claude Code +9 - 0.432score
conventional-commits
ntk148v
Use when creating git commits, writing commit messages, or when the user mentions conventional commits, semantic versioning, or automated changelog generation.
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
deep-wiki
ntk148v
Use when generating comprehensive documentation for a codebase, creating wiki pages, documenting architecture, or when the user mentions "deep wiki"…
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
security-expert
ntk148v
Use when analyzing security vulnerabilities, conducting security reviews, checking for common vulnerabilities, or when the user mentions "security"…
SkillDFreshness: D★ 1Claude Code +9 - 0.423score
system-performance
ntk148v
Use when analyzing system performance, debugging performance issues, investigating bottlenecks, or when the user mentions "performance analysis", "USE…
SkillDFreshness: D★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Apr 3, 2026 (6 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/ntk148v/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ntk148v
- 0.497score
skill-authoring
ntk148v
Use when creating, editing, auditing, or validating Agent Skills.
SkillCFreshness: C★ 1Claude Code +9 - 0.493score
repo-analyzer
ntk148v
Use when the user mentions "analyzing a project", "analyzing a repository", "analyzing GitHub", "project analysis", "source code analysis", "architecture…
SkillCFreshness: C★ 1Claude Code +9 - 0.472score
caveman
ntk148v
Ultra-compressed communication mode.
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
grill
ntk148v
Interview the user relentlessly about a plan, design, or domain model until reaching shared understanding.
SkillCFreshness: C★ 1Claude Code +9 - 0.461score
handoff
ntk148v
Compact the current conversation into a handoff document for another agent to pick up.
SkillCFreshness: C★ 1Claude Code +9 - 0.432score
conventional-commits
ntk148v
Use when creating git commits, writing commit messages, or when the user mentions conventional commits, semantic versioning, or automated changelog generation.
SkillDFreshness: D★ 1Claude Code +9
Cite this page
code-reviewer skill. Agent Mart. https://agentmart.dev/skills/ntk148v-code-reviewer (last updated 2026-10-24)