.claude/skills/review/SKILL.md
Review code for issues, improvements, and best practices.
npx skillsauth add allierays/agentic-loop .claude/skills/reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Review code for issues, improvements, and best practices.
When asked to review code, perform a thorough analysis looking for:
// VULNERABLE - SQL injection
const query = `SELECT * FROM users WHERE name = '${userInput}'`;
// SAFE - parameterized query
const query = "SELECT * FROM users WHERE name = ?";
db.execute(query, [userInput]);
// VULNERABLE - XSS
element.innerHTML = userInput;
// SAFE
element.textContent = userInput;
// or with sanitization
element.innerHTML = DOMPurify.sanitize(userInput);
any typeStructure your review like this:
## Code Review: [filename or description]
### Summary
[1-2 sentence overview of the code quality]
### Critical Issues
These must be fixed before merging:
1. **[Issue Title]** (Line X)
- Problem: [What's wrong]
- Risk: [What could happen]
- Fix: [How to fix it]
[Code suggestion if applicable]
### Improvements
These should be addressed:
1. **[Issue Title]** (Line X)
- Current: [What it does now]
- Better: [What it should do]
- Why: [Benefit of changing]
### Minor Suggestions
Nice to have, low priority:
1. **[Suggestion]** (Line X)
- [Brief explanation]
### What's Good
[Acknowledge good patterns and practices in the code]
### Verdict
[ ] Ready to merge
[ ] Needs minor changes
[ ] Needs significant changes
[ ] Needs rewrite
| Severity | Block Merge? | Examples | |----------|--------------|----------| | Critical | Yes | Security vulnerabilities, data loss risks | | High | Yes | Missing error handling, type safety issues | | Medium | Review | Performance issues, code quality | | Low | No | Style preferences, minor improvements |
Focus only on critical and high-severity issues:
"Quick review of this code"
Check everything:
"Full review of src/api/users.ts"
Deep dive on security - injection, XSS, auth, access control, secrets:
"Security review of the authentication flow" "Check for SQL injection vulnerabilities" "Full security audit of the API endpoints"
Focus on performance:
"Performance review of the dashboard page"
Check for vulnerable dependencies:
"Check our dependencies for known vulnerabilities"
tools
Show complete reference for all agentic-loop commands (slash commands, Ralph CLI, vibe CLI).
data-ai
Quick reference cheatsheet for all agentic-loop commands including Ralph.
development
Run a comprehensive code quality check looking for common patterns that AI coding agents introduce.
development
Take an interactive tour of agentic-loop - the system for going from idea to shipped code with AI.