Skip to main content

code-review-expert

Rigorous, severity-ranked review of a diff, PR, or file. Use when you want a thorough check of correctness, security, performance, design, readability, and test coverage with actionable feedback.

v1.0.0New
0

Signing

SignedSLSA L2
Signed by
skills-hub.ai distributor
Method
Distributor-signed by skills-hub.aiCryptographically signed by the skills-hub.ai distributor key at publish time.
Signed

Install this skill

Run this command in your terminal. No account required — it auto-detects your AI tool and installs the skill file.

npx @skills-hub-ai/cli install code-review-expert
Or download directly:
Browse all CLI commands →

Setup by platform

Claude Code

~/.claude/skills/<skill>/SKILL.md

Setup guide →

Cursor

~/.cursor/skills/<skill>/SKILL.md

Setup guide →

Windsurf

~/.windsurf/skills/<skill>/SKILL.md, or add to .windsurfrules in your project

Setup guide →

GitHub Copilot

.github/copilot-instructions.md (project-level), paste skill content into instructions

Setup guide →

Cline

~/.cline/skills/<skill>/SKILL.md, or add to .clinerules in your project

Setup guide →

Codex CLI

~/.codex/skills/<skill>/SKILL.md, or reference via codex.md instructions file

Setup guide →

Gemini CLI

GEMINI.md (project-level) or ~/.gemini/skills/<skill>/SKILL.md

Setup guide →

Install

One-click setup for your editor

Run in your project root

npx @skills-hub-ai/cli install code-review-expert --target claude-code

Examples

Prompt

Please review the new user authentication function in auth.py. It handles token validation and session management.

Output

[Approve-with-comments] The implementation correctly validates tokens and manages sessions, but there are some security concerns.

[CRITICAL] auth.py:L27 — No rate limiting on token validation endpoint. Why it matters: potential for abuse or DoS attacks. Fix: add rate limiting or throttling.
[HIGH] auth.py:L45 — Password hashing uses a weak algorithm (MD5). Why it matters: compromises user credentials. Fix: switch to bcrypt or Argon2.
[LOW] auth.py:L60 — Logging includes full tokens in logs. Why it matters: PII exposure. Fix: mask tokens in logs.

What's good: Clear separation of concerns, thorough validation logic, and good use of existing libraries.
Open questions: Are there plans to implement multi-factor authentication? Are there existing rate limits elsewhere?

Prompt

Review the recent database schema migration in db/migrations/2024_04_01_add_indexes.sql. It adds indexes on user_id and created_at columns.

Output

[Approve] The migration improves query performance by adding relevant indexes. The changes are straightforward and safe.

[MEDIUM] db/migrations/2024_04_01_add_indexes.sql: Line 3 — Creating index on user_id. Why it matters: improves lookup speed for user-specific queries. No issues.
[MEDIUM] db/migrations/2024_04_01_add_indexes.sql: Line 4 — Creating index on created_at. Why it matters: speeds up recent data retrieval. Consider adding a composite index if queries filter by both columns.

What's good: Clear, well-documented migration, and indexes target common query patterns.
Open questions: Are there any existing slow queries that prompted these indexes? Should we analyze index usage post-deployment?

Instructions

This skill doesn’t include stateful context yet, instructions only. Learn about stateful skills.

Security

Loading security scan...

Reviews (0)

Frequently asked questions about code-review-expert

What does the code-review-expert skill do?

Rigorous, severity-ranked review of a diff, PR, or file. Use when you want a thorough check of correctness, security, performance, design, readability, and test coverage with actionable feedback. It's a reusable SKILL.md instruction set that loads into your AI coding assistant on demand, no prompt engineering, no copy-pasting every session.

How do I install the code-review-expert skill?

Run `npx @skills-hub-ai/cli install code-review-expert` from your terminal. The CLI writes the SKILL.md to the correct location for your AI tool (e.g. ~/.claude/skills/code-review-expert/ for Claude Code or ~/.cursor/skills/ for Cursor with --target cursor) and adds it to your project's .skills.json lockfile.

Which AI tools does code-review-expert work with?

code-review-expert runs in Claude Code, Cursor, Windsurf, GitHub Copilot, Cline, Codex CLI, Gemini CLI. It follows the open Agent Skills standard (SKILL.md), so the same skill works in every supported tool without modification.

Is the code-review-expert skill free?

Yes. Every skill on skills-hub.ai is free and open-source. There are no premium tiers, paywalls, or usage limits. You only pay for whatever AI assistant you're already using.

How do I use code-review-expert after installing it?

In Claude Code, type `/code-review-expert` (or whatever slash command the skill registers) and the AI follows the skill's instructions immediately. You can also reference it by name in natural language, your AI loads the skill into context when relevant.

Can I share the code-review-expert skill with my team?

Yes. Commit your project's .skills.json lockfile and teammates run `npx @skills-hub-ai/cli install` (no args) to install every skill at the exact version you pinned. Organization-scoped installs work via skills-hub.ai organizations.