Code Reviewer

VerifiedSafe

Perform structured code reviews that identify bugs, security issues, performance problems, and maintainability concerns. Provides prioritized, actionable feedback with specific fix suggestions.

Sby Skills Guide Bot
DevelopmentIntermediate
6/2/2026
Claude Code
#code-review#quality#bugs#security#best-practices

Recommended for

Automated summary

Performs structured code reviews that identify bugs, security issues, performance problems, and maintainability concerns with prioritized, actionable feedback.

Strengths

  • Comprehensive coverage across correctness, security, performance, reliability, readability, and testing
  • Prioritized feedback by severity with specific fix suggestions
  • Works with any programming language and can review full files or diffs

Limitations

  • Requires the code to be provided in the prompt or as a file; cannot directly access pull requests on third-party platforms
  • Review quality depends on the clarity of the user's request and the amount of context provided
  • May not catch project-specific or business logic nuances without additional context
When to use it

Use when you need a thorough code review to catch bugs, security vulnerabilities, or improve code quality before merging or deploying.

When not to use it

Do not use for high-level architecture discussions or when only a quick formatting check is needed.

Security analysis

Safe
Quality score90/100

The skill provides only code review guidelines and examples. It does not instruct or require the AI to execute any commands, access external resources, or perform destructive actions. No tools are declared, and the content is purely instructional.

No concerns found

How this analysis is made

Examples

Review an Express route handler
Review this Express route handler:

app.post('/users', async (req, res) => {
  const { name, email, role } = req.body;
  const user = await db.query(
    `INSERT INTO users (name, email, role) VALUES ('${name}', '${email}', '${role}')`
  );
  res.json(user);
});
Find bugs in a Python function
Check this code for bugs:

def calculate_discount(price, discount_code):
    if discount_code == 'SUMMER':
        return price * 0.9
    elif discount_code == 'WINTER':
        return price * 0.8
    else:
        return price
Review a pull request diff
Review this diff:

@@ -1,5 +1,10 @@
 function greet(name) {
-    console.log('Hello, ' + name);
+    if (!name) {
+        throw new Error('Name is required');
+    }
+    console.log(`Hello, ${name}`);
 }
+ 
+ module.exports = greet;

name: code-reviewer description: >- Perform thorough code reviews with actionable, prioritized feedback. Use when a user asks to review code, check code quality, find bugs, review a pull request, audit code for issues, or get feedback on implementation. Covers correctness, security, performance, readability, and best practices across languages. license: Apache-2.0 compatibility: "Works with any programming language" metadata: author: terminal-skills version: "1.0.0" category: development tags: ["code-review", "quality", "bugs", "security", "best-practices"]

Code Reviewer

Overview

Perform structured code reviews that identify bugs, security issues, performance problems, and maintainability concerns. Provides prioritized, actionable feedback with specific fix suggestions.

Instructions

When a user asks you to review code, a file, a diff, or a pull request, follow this process:

Step 1: Understand the context

Before reviewing, determine:

  • What does this code do? (feature, bugfix, refactor)
  • What language and framework is it using?
  • Are there tests included?
  • Is this a full file or a diff/patch?

Read surrounding files if needed to understand the broader codebase context.

Step 2: Review using this checklist

Evaluate the code against each category in order of severity:

Correctness (Critical)

  • Logic errors, off-by-one mistakes, wrong conditions
  • Unhandled null/undefined/empty cases
  • Race conditions or concurrency issues
  • Incorrect error handling (swallowed exceptions, wrong error types)
  • Missing input validation

Security (Critical)

  • SQL injection, XSS, command injection
  • Hardcoded secrets, API keys, passwords
  • Improper authentication/authorization checks
  • Unsafe deserialization, path traversal
  • Missing rate limiting on public endpoints

Performance (High)

  • N+1 queries in database loops
  • Unnecessary re-renders in UI components
  • Missing indexes for frequent queries
  • Unbounded memory growth (loading entire datasets)
  • Blocking operations on the main thread

Reliability (High)

  • Missing error handling for external calls (network, file I/O)
  • No retry logic for transient failures
  • Missing timeouts on HTTP requests
  • Resource leaks (unclosed connections, file handles)

Readability (Medium)

  • Unclear variable or function names
  • Functions doing too many things (> 30 lines is a smell)
  • Deeply nested conditionals (> 3 levels)
  • Missing or misleading comments
  • Inconsistent naming conventions

Testing (Medium)

  • Missing tests for new logic
  • Tests that do not assert meaningful behavior
  • Missing edge case coverage
  • Brittle tests coupled to implementation details

Step 3: Format the review

Organize findings by severity. For each issue:

### [SEVERITY] Category: Brief title

**File:** `path/to/file.ext` line XX-YY

**Issue:** What is wrong and why it matters.

**Suggestion:**
\`\`\`language
// Suggested fix
\`\`\`

Severity levels: CRITICAL, HIGH, MEDIUM, LOW

Step 4: Provide a summary

End with:

  • Overall assessment (approve, request changes, or needs discussion)
  • Count of issues by severity
  • Top 3 things to fix before merging

Examples

Example 1: Review a Node.js API endpoint

User request: "Review this Express route handler"

Code submitted:

app.post('/users', async (req, res) => {
  const { name, email, role } = req.body;
  const user = await db.query(
    `INSERT INTO users (name, email, role) VALUES ('${name}', '${email}', '${role}')`
  );
  res.json(user);
});

Review output:

### CRITICAL Security: SQL Injection vulnerability

**File:** routes/users.js line 2-5

**Issue:** User input is interpolated directly into the SQL query string.
An attacker can inject arbitrary SQL via the name, email, or role fields.

**Suggestion:**
    const user = await db.query(
      'INSERT INTO users (name, email, role) VALUES ($1, $2, $3)',
      [name, email, role]
    );

### CRITICAL Security: No input validation

**File:** routes/users.js line 2

**Issue:** Request body fields are used without validation. Missing or
malformed data will cause database errors or store invalid records.

**Suggestion:**
    if (!name || !email || !email.includes('@')) {
      return res.status(400).json({ error: 'Name and valid email required' });
    }
    const allowedRoles = ['user', 'admin', 'editor'];
    if (!allowedRoles.includes(role)) {
      return res.status(400).json({ error: 'Invalid role' });
    }

### HIGH Reliability: No error handling

**File:** routes/users.js line 3-5

**Issue:** If the database query fails, the error propagates as an
unhandled promise rejection, crashing the process or returning a 500
with a stack trace.

**Suggestion:**
    try {
      const user = await db.query(...);
      res.status(201).json(user);
    } catch (err) {
      console.error('Failed to create user:', err);
      res.status(500).json({ error: 'Failed to create user' });
    }

Summary: REQUEST CHANGES
- Critical: 2, High: 1, Medium: 0
- Fix SQL injection and add input validation before merging

Example 2: Review a React component

User request: "Review this component for any issues"

Code submitted:

function UserList({ users }) {
  const [search, setSearch] = useState('');

  const filtered = users.filter(u =>
    u.name.toLowerCase().includes(search.toLowerCase())
  );

  return (
    <div>
      <input onChange={e => setSearch(e.target.value)} />
      {filtered.map(user => (
        <div>{user.name} - {user.email}</div>
      ))}
    </div>
  );
}

Review output:

### MEDIUM Performance: Filtering runs on every render

**Issue:** The filter operation recalculates on every render, even when
unrelated state changes. For large lists this causes jank.

**Suggestion:**
    const filtered = useMemo(() =>
      users.filter(u =>
        u.name.toLowerCase().includes(search.toLowerCase())
      ), [users, search]);

### MEDIUM Readability: Missing key prop on list items

**Issue:** React requires a unique key prop on list items for efficient
reconciliation. Missing keys cause incorrect re-renders and warnings.

**Suggestion:**
    {filtered.map(user => (
      <div key={user.id}>{user.name} - {user.email}</div>
    ))}

### LOW Readability: Missing input label and placeholder

**Issue:** The search input has no label or placeholder, making it
unclear what the input is for and inaccessible to screen readers.

**Suggestion:**
    <label htmlFor="user-search">Search users</label>
    <input
      id="user-search"
      placeholder="Search by name..."
      onChange={e => setSearch(e.target.value)}
    />

Summary: APPROVE with suggestions
- Critical: 0, High: 0, Medium: 2, Low: 1
- Add key prop and useMemo before merging

Guidelines

  • Focus on issues that matter. Do not nitpick formatting if there is a linter configured.
  • Always explain WHY something is a problem, not just what to change.
  • Provide concrete fix suggestions, not just "this could be improved."
  • Acknowledge what the code does well. Reviews should not be exclusively negative.
  • When reviewing diffs, focus on changed lines but check context for integration issues.
  • For large PRs (500+ lines), start with an architectural overview before line-by-line review.
  • If you are unsure about a finding, say so. Do not present uncertain issues as definitive.
  • Prioritize: fix all CRITICALs, fix HIGH before merge, MEDIUM/LOW can be follow-up tasks.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/code-reviewer-mmk3niby/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/code-reviewer-mmk3niby' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/code-reviewer-mmk3niby/download' --output '.skill-downloads/code-reviewer-mmk3niby/SKILL.md.part' && mv '.skill-downloads/code-reviewer-mmk3niby/SKILL.md.part' '.skill-downloads/code-reviewer-mmk3niby/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Environment declared by the author: Works with any programming language

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/code-reviewer-mmk3niby/SKILL.md' && test -s '.skill-downloads/code-reviewer-mmk3niby/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/code-reviewer' && cp -R '.skill-downloads/code-reviewer-mmk3niby' '.claude/skills/code-reviewer'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/code-reviewer-mmk3niby'

openskills read 'code-reviewer-mmk3niby'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/code-reviewer-mmk3niby/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills