Agent skill

code-review

Performs structured code reviews focusing on bugs, security, performance, and best practices. Use when reviewing code, pull requests, diffs, or when the user asks for feedback on implementations.

Stars 1
Forks 1

Install this agent skill to your Project

npx add-skill https://github.com/Cambridge-AI-Build-Club/MCP-Workshop/tree/main/3-skills/code-review

SKILL.md

Code Review

Quick Start

When reviewing code, follow this structured approach:

Review Checklist:
- [ ] Correctness: Does it work as intended?
- [ ] Security: Any vulnerabilities or data exposure?
- [ ] Performance: Obvious inefficiencies?
- [ ] Readability: Clear naming, structure, comments?
- [ ] Edge cases: Null, empty, boundary conditions?

Review Process

Step 1: Understand Context

  • What problem does this code solve?
  • What are the requirements/constraints?

Step 2: Scan for Critical Issues

  • Security vulnerabilities (injection, auth, data exposure)
  • Logic errors and bugs
  • Resource leaks or performance bombs

Step 3: Evaluate Quality

  • Code organization and structure
  • Naming conventions
  • Error handling patterns
  • Test coverage (if applicable)

Step 4: Provide Feedback

  • Lead with positives
  • Categorize issues: Critical / Important / Suggestion
  • Include specific line references
  • Offer concrete alternatives

Output Format

Structure feedback as:

markdown
## Summary
[1-2 sentence overview]

## Critical Issues
[Must fix before merge]

## Recommendations  
[Should address]

## Suggestions
[Nice to have improvements]

## What's Working Well
[Positive observations]

Language-Specific Guidance

For detailed patterns by language, see:

  • PATTERNS.md - Common anti-patterns by language
  • SECURITY.md - Security checklist by context

Review Scope Guidelines

Review Type Focus Areas Depth
Quick review Bugs, security Surface
Standard review + Performance, readability Thorough
Deep review + Architecture, patterns Comprehensive

Default to standard review unless specified otherwise.

Expand your agent's capabilities with these related and highly-rated skills.

Cambridge-AI-Build-Club/MCP-Workshop

meeting-notes

Creates structured meeting notes, minutes, and action items from conversations or transcripts. Use when documenting meetings, standups, retrospectives, or extracting action items from discussions.

1 1
Explore
mattpocock/skills

edit-article

Edit and improve articles by restructuring sections, improving clarity, and tightening prose. Use when user wants to edit, revise, or improve an article draft.

111,310 9,758
Explore
mattpocock/skills

obsidian-vault

Search, create, and manage notes in the Obsidian vault with wikilinks and index notes. Use when user wants to find, create, or organize notes in Obsidian.

111,310 9,758
Explore
mattpocock/skills

scaffold-exercises

Create exercise directory structures with sections, problems, solutions, and explainers that pass linting. Use when user wants to scaffold exercises, create exercise stubs, or set up a new course section.

111,310 9,758
Explore
mattpocock/skills

setup-pre-commit

Set up Husky pre-commit hooks with lint-staged (Prettier), type checking, and tests in the current repo. Use when user wants to add pre-commit hooks, set up Husky, configure lint-staged, or add commit-time formatting/typechecking/testing.

111,310 9,758
Explore
mattpocock/skills

git-guardrails-claude-code

Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.

111,310 9,758
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results