code-review
A skill for conducting thorough code reviews, identifying issues, suggesting improvements, and ensuring code quality standards are met.
Packaged view
This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.
Install command
npx @skill-hub/cli install sheng-jie-maf-agentskills-code-review
Repository
Skill path: samples/Maf.AgentSkills.ConsoleDemo/.maf/skills/code-review
A skill for conducting thorough code reviews, identifying issues, suggesting improvements, and ensuring code quality standards are met.
Open repositoryBest for
Primary workflow: Ship Full Stack.
Technical facets: Full Stack.
Target audience: everyone.
License: MIT.
Original source
Catalog source: SkillHub Club.
Repository owner: sheng-jie.
This is still a mirrored public skill entry. Review the repository before installing into production workflows.
What it helps with
- Install code-review into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
- Review https://github.com/sheng-jie/Maf.AgentSkills before adding code-review to shared team environments
- Use code-review for development workflows
Works across
Favorites: 0.
Sub-skills: 0.
Aggregator: No.
Original source / Raw SKILL.md
--- name: code-review description: A skill for conducting thorough code reviews, identifying issues, suggesting improvements, and ensuring code quality standards are met. license: MIT compatibility: any allowed-tools: read_file list_directory grep_search metadata: author: Maf.AgentSkills version: 1.0.0 category: development --- # Code Review Skill This skill helps you conduct thorough and constructive code reviews. ## When to Use Use this skill when: - Reviewing pull requests or code changes - Auditing code quality in a project - Helping developers improve their code - Checking for security vulnerabilities or bugs ## Review Checklist Use the checklist in `templates/review-checklist.md` to ensure comprehensive coverage. ### Categories 1. **Correctness**: Does the code do what it's supposed to do? 2. **Security**: Are there any security vulnerabilities? 3. **Performance**: Are there performance concerns? 4. **Maintainability**: Is the code easy to understand and modify? 5. **Testing**: Is the code adequately tested? 6. **Documentation**: Is the code well-documented? ## Instructions ### 1. Understand Context Before reviewing: - Understand the purpose of the change - Read any related issue or ticket - Know the project's coding standards ### 2. Review Systematically Go through the code in this order: 1. **Architecture**: Does the overall approach make sense? 2. **Logic**: Is the logic correct and complete? 3. **Edge Cases**: Are edge cases handled? 4. **Error Handling**: Are errors handled appropriately? 5. **Style**: Does the code follow conventions? ### 3. Provide Constructive Feedback For each issue found: - Explain **what** the issue is - Explain **why** it's a problem - Suggest **how** to fix it - Categorize severity (blocker, major, minor, suggestion) ### 4. Output Format ```markdown # Code Review: [File/PR Name] ## Summary [Overall assessment: approve, request changes, or comment] ## Critical Issues π΄ [Issues that must be fixed before merge] ## Major Issues π [Important issues that should be addressed] ## Minor Issues π‘ [Nice-to-have improvements] ## Suggestions π‘ [Optional improvements for consideration] ## Positive Highlights β¨ [Things done well - always include some!] ``` ## Best Practices - Be respectful and constructive - Focus on the code, not the person - Ask questions when unclear - Acknowledge good patterns - Suggest alternatives, don't just criticize --- ## Referenced Files > The following files are referenced in this skill and included for context. ### templates/review-checklist.md ```markdown # Code Review Checklist Use this checklist during code reviews to ensure comprehensive coverage. ## β Correctness - [ ] Code implements the intended functionality - [ ] Logic is correct and handles all scenarios - [ ] Edge cases are handled properly - [ ] No off-by-one errors - [ ] Null/undefined values are handled ## π Security - [ ] No SQL injection vulnerabilities - [ ] No XSS vulnerabilities - [ ] Input validation is performed - [ ] Sensitive data is not logged - [ ] Authentication/authorization is correct - [ ] No hardcoded secrets or credentials ## β‘ Performance - [ ] No unnecessary database queries (N+1 problem) - [ ] Appropriate data structures used - [ ] No memory leaks - [ ] Caching used where appropriate - [ ] Large operations are async/background ## π§ Maintainability - [ ] Code is readable and self-documenting - [ ] Functions/methods are focused (single responsibility) - [ ] No code duplication (DRY) - [ ] Naming is clear and consistent - [ ] Complex logic has comments - [ ] Magic numbers are constants ## π§ͺ Testing - [ ] Unit tests cover main functionality - [ ] Edge cases have tests - [ ] Tests are readable and maintainable - [ ] Mocking is used appropriately - [ ] Integration tests for critical paths ## π Documentation - [ ] Public APIs are documented - [ ] Complex algorithms have explanations - [ ] README updated if needed - [ ] Breaking changes documented - [ ] Migration guide if applicable ## π¨ Style - [ ] Follows project coding standards - [ ] Consistent formatting - [ ] No commented-out code - [ ] No debug statements left - [ ] Imports organized ```