review
The /review slash command inspects staged and unstaged git changes in the workspace, then performs a comprehensive code review by evaluating modifications against correctness, security, performance, and maintainability standards using the agent-reviewer prompt template. Use this command when preparing commits to identify critical issues, security vulnerabilities, and code quality improvements before pushing changes.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/guanyang/open-agent-hub/HEAD/commands/review.md -o ~/.claude/commands/review.mdreview.md
# Slash Command: /review ## Core Objective Inspect modified files in the workspace and execute a thorough code review. ## Steps for the Agent 1. **Gather Modified Files**: Run `git diff` (unstaged) and `git diff --cached` (staged) to identify modified files. 2. **Load Review Guide**: Read the [agent-reviewer](../agents/agent-reviewer.md) prompt template. 3. **Analyze Code Diffs**: Evaluate all modifications against: - Correctness & Safety. - Security (OWASP Top 10, credential exposures). - Performance (N+1 queries, resource leaks). - Maintainability. 4. **Output Report**: Present a structured report: - 🛑 **[Critical]**: Blocker issues. - ⚠️ **[Warning]**: Highly recommended improvements. - 💡 **[Suggestion]**: Readability enhancements. - Print the `<review-compaction>` loop state.
Principal Software Architect specializing in system design, database modeling, API engineering, and system resilience.
Principal Diagnostics Engineer specializing in root cause analysis, error troubleshooting, and hotfixes.
Principal Clean Code Specialist specializing in code simplification, performance tuning, and refactoring loops.
Senior Technical Lead and Security Auditor specializing in code quality, correctness, and security audits.
Senior QA Automation Engineer specializing in unit, integration, and E2E test suite creation.
Run when user calls /commit or asks to generate a commit message. Analyzes staged changes and writes a structured commit message.
Run when user calls /test-tdd. Scans modified files, locates their corresponding unit/integration test suites, and runs them.
This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison, rubric calibration, evaluator bias mitigation, confidence scoring, and automated quality assessment.