Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot

code-review · agno-agi — Claude Code skill: style and quality checks

Automated code inspection for style violations, bugs, and best-practice gaps. The skill runs linting, identifies issues, and delivers structured feedback with severity levels.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add agno-agi/agno --skill code-review -a claude-code
Open on GitHub

What code-review does

The skill works in three stages: checks code against a style guide, runs the automated linter via check_style.py, then manually scans for bugs, performance problems, and security gaps. Feedback is categorized by severity—Critical (block merge), Important (should fix), and Suggestion (nice to have).

The checklist verifies naming conventions, absence of hardcoded secrets, proper error handling, functions under 50 lines, no obvious vulnerabilities, and test coverage for new code. The skill keeps code quality consistent and catches issues before they reach production.

What it helps with

  • detect style guide violations across your codebase
  • spot bugs and security vulnerabilities before merge
  • identify performance bottlenecks and inefficiencies
  • confirm code is documented and tested
  • standardize review feedback with severity labels

Example prompts for the agent

  • Review this code for style and best practices
  • Run a full review of my pull request
  • Find security issues in this function

How to install code-review

1Skills CLI (Vercel)

npx skills add agno-agi/agno --skill code-review -a claude-code

2Manually: put the files in place

~/.claude/skills/code-review/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/code-review/

From the same set3

The whole set →

Other versions of code-review

Similar

cpp-pro https://github.com/Jeffallan Writes, optimizes, and debugs C++ with concepts, ranges, coroutines, SIMD, and template metaprogramming. Built for C++20/23 projects where performance and type safety matter. Claude Code CX Codex Cursor +1 5,300installs simplify-code Hermes Agent (inspired by Claude Code /simplify) Reviews recent code changes through four parallel subagents and applies justified cleanup fixes. Use it after edits to simplify code that already works. Claude Code CX Codex Cursor +1 345installs plan-devex-review garrytan An interactive read of a plan from the developer's side: it flags where someone opening the project for the first time will stumble, and asks before editing. Claude Code CX Codex Cursor +1 347installs pr-workflow tursodatabase Enforces rules for atomic commits, clean PRs, dependency licensing, and secret hygiene. Useful for agents pushing code or running inside CI workflows. Claude Code CX Codex Cursor +1 1,200installs golang-refactoring samber A skill for behavior-preserving restructuring of Go code at scale. Uses gopls, gofmt, and tools like gopatch to break down large functions, rename types across a project, and reorganize packages without breakage. Claude Code CX Codex Cursor +1 11,200installs secure-workflow-guide trailofbits Guides smart contracts through Trail of Bits' 5-step security audit on check-in or before deployment. It runs static analysis, generates visual charts, and prepares fuzzing tests. Claude Code CX Codex Cursor +1 7,400installs improve-codebase-architecture Matt Pocock This skill scans a codebase for architectural friction, then builds a visual HTML report with refactoring candidates. Use it before a deeper architecture review. Claude Code 1,163,035installs tdd Matt Pocock Guides the red-green TDD loop: ensures tests are written first, keep them at public interfaces, and avoid coupling to implementation details. Claude Code 1,141,062installs

Questions about code-review

How do I install code-review for Claude Code?

Run npx skills add agno-agi/agno --skill code-review -a claude-code, then find the skill in ~/.claude/skills/code-review/SKILL.md.

What does code-review do?

It checks code for style violations, runs a linter, and scans for bugs and security issues. Output is labeled by severity: Critical (must fix), Important (should fix), and Suggestion (optional).

Does code-review support multiple programming languages?

The skill reviews logic and structure independently of language, but the automated linter via check_style.py adapts to your project's language and conventions.

Source text

SKILL.md · Apache-2.0
---
name: code-review
description: Code review assistance with linting, style checking, and best practices
license: Apache-2.0
metadata:
  version: "1.0.0"
  author: agno-team
  tags: ["quality", "review", "linting"]
---
# Code Review Skill

You are a code review assistant. When reviewing code, follow these steps:

## Review Process
1. **Check Style**: Reference the style guide using `get_skill_reference("code-review", "style-guide.md")`
2. **Run Style Check**: Use `get_skill_script("code-review", "check_style.py")` for automated style checking
3. **Look for Issues**: Identify potential bugs, security issues, and performance problems
4. **Provide Feedback**: Give structured feedback with severity levels

## Feedback Format
- **Critical**: Must fix before merge (security vulnerabilities, bugs that cause crashes)
- **Important**: Should fix, but not blocking (performance issues, code smells)
- **Suggestion**: Nice to have improvements (naming, documentation, minor refactoring)

## Review Checklist
- [ ] Code follows naming conventions
- [ ] No hardcoded secrets or credentials
- [ ] Error handling is appropriate
- [ ] Functions are not too long (< 50 lines)
- [ ] No obvious security vulnerabilities
- [ ] Tests are included for new functionality

© agno-team · Apache-2.0 · agno-agi/agno

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor