Documentation
Command
/review
Perform a thorough code review of: $ARGUMENTS
$ npx -y skills add vignesh2027/claude-best-practice --agent claude-code
Command definition
review.md/review — Deep Code Review
Perform a thorough code review of: $ARGUMENTS
If no arguments provided, review all staged/uncommitted changes.
Review Dimensions
1. Correctness
- Does the code do what it's supposed to do?
- Are edge cases handled?
- Are error conditions caught and handled?
2. Security
- Input validation at system boundaries
- SQL injection, XSS, CSRF risks
- Authentication and authorization checks
- Secrets or credentials exposed?
- Dependency vulnerabilities
3. Performance
- Unnecessary database queries (N+1 problems)
- Unoptimized loops or algorithms
- Missing indexes on queried columns
- Memory leaks or unbounded caches
4. Maintainability
- Is the code readable and self-explanatory?
- Are functions doing too many things?
- Is there duplication that should be extracted?
- Are names clear and consistent with the codebase?
5. Test Coverage
- Are there tests for the new functionality?
- Do tests cover failure paths?
- Are tests testing behavior, not implementation?
6. Architecture
- Does the change fit the existing patterns?
- Is the abstraction level appropriate?
- Does it create problematic coupling?
Output Format
For each issue found, report:
SEVERITY: [Critical / High / Medium / Low / Nit]
FILE: path/to/file.ts:line
ISSUE: description of the problem
SUGGESTION: how to fix it
End with:
- **Overall assessment**: Approve / Request Changes / Needs Major Work
- **Top 3 must-fix items** (if any)
Read more
/review — Deep Code Review
Perform a thorough code review of: $ARGUMENTS
If no arguments provided, review all staged/uncommitted changes.
Review Dimensions
1. Correctness
- Does the code do what it's supposed to do?
- Are edge cases handled?
- Are error conditions caught and handled?
2. Security
- Input validation at system boundaries
- SQL injection, XSS, CSRF risks
- Authentication and authorization checks
- Secrets or credentials exposed?
- Dependency vulnerabilities
3. Performance
- Unnecessary database queries (N+1 problems)
- Unoptimized loops or algorithms
- Missing indexes on queried columns
- Memory leaks or unbounded caches
4. Maintainability
- Is the code readable and self-explanatory?
- Are functions doing too many things?
- Is there duplication that should be extracted?
- Are names clear and consistent with the codebase?
5. Test Coverage
- Are there tests for the new functionality?
- Do tests cover failure paths?
- Are tests testing behavior, not implementation?
6. Architecture
- Does the change fit the existing patterns?
- Is the abstraction level appropriate?
- Does it create problematic coupling?
Output Format
For each issue found, report:
SEVERITY: [Critical / High / Medium / Low / Nit] FILE: path/to/file.ts:line ISSUE: description of the problem SUGGESTION: how to fix it
End with:
- **Overall assessment**: Approve / Request Changes / Needs Major Work
- **Top 3 must-fix items** (if any)
Stats
4
Stars
1
Forks
Maintained
Maintenance
Shell
Language
Last commit
Created
In this plugin
See everything inside Ships withclaude-best-practice
The most comprehensive, production-ready guide to mastering Claude Code From vibe coding → agentic engineering → autonomous AI development teams Built for engineers who treat Claude Code as infrastructure, not a toy.
41 skill3 agents
Other commands on claude-best-practice.
More commands from other plugins.
compare
CommandCompare two or more options side by side, recommend one, and let the reader pick in the page
explain
CommandExplain code in detail - what it does, how it works, and why
commit-smart
CommandCreate smart commit with quality checks and conventional format

