home / skills / agno-agi / agno / code-review

code-review skill

safe

/cookbook/02_agents/skills/sample_skills/code-review

This skill helps you review Python code by applying style guides, detecting issues, and providing structured feedback to speed up safe, maintainable merges.

npx playbooks add skill agno-agi/agno --skill code-review

Review the files below or copy the command above to add this skill to your agents.

Files (3)

SKILL.md

1.2 KB

---
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

Overview

This skill provides code review assistance focused on linting, style checking, and best practices for Python projects. It combines automated style checks with manual inspection to identify bugs, security issues, and maintainability problems. Feedback is delivered in a structured format with clear severity levels to guide remediation.

How this skill works

The skill first validates code against a project style guide and runs automated style and lint checks to surface formatting and convention violations. It then inspects code for potential bugs, security vulnerabilities, error-handling gaps, performance traps, and test coverage omissions. Results are summarized with severity labels (Critical, Important, Suggestion) and actionable recommendations for each finding.

When to use it

Before opening a pull request to catch style and obvious issues early
When preparing a release or merging feature branches
During codebase audits for security and performance risks
When onboarding new contributors to enforce team conventions
To verify tests and error handling for newly added functionality

Best practices

Run the automated style check locally as part of pre-commit or CI to catch issues early
Prioritize Critical findings (security vulnerabilities and crash-causing bugs) before merging
Keep functions short and focused; flag functions longer than ~50 lines for refactor
Avoid hardcoded secrets; ensure credential handling follows secure patterns
Include or update tests for any new or changed behavior; flag missing tests

Example use cases

Automated pre-merge review that enforces project style and catches lint errors
Security-focused review to identify hardcoded credentials and input validation gaps
Performance review to find expensive operations and propose optimizations
Maintainability sweep to flag long functions, poor naming, and missing documentation
Test coverage check to ensure new features are accompanied by appropriate tests

FAQ

What do the severity labels mean?

Critical means fix before merge (security or crash bugs). Important should be addressed soon (performance or code smells). Suggestion is optional improvement (naming, docs).

Does the skill replace human reviewers?

No. It automates routine checks and finds common issues, but human reviewers are needed for design, architecture, and contextual decisions.