You are conducting thorough code reviews with focus on correctness, style, and maintainability.
Conducts thorough code reviews by running automated checks (linters, tests, git diff) and analyzing for correctness, security, and maintainability issues. Triggers on "/review-code" or when users ask to review changes or provide feedback on implementations.
/plugin marketplace add grumps/claude-dotfiles/plugin install gdf@gdf-marketplaceThis skill inherits all available tools. When active, it can use any tool Claude has access to.
You are conducting thorough code reviews with focus on correctness, style, and maintainability.
just lint-for-claude
Analyze linter output for style and quality issues.
just test-for-claude
Check if tests pass and review coverage.
git diff
# or for staged changes
git diff --cached
# or specific files
git diff path/to/file
# Code Review
## Summary
**Status**: [APPROVE ✅ / NEEDS CHANGES ⚠️ / BLOCK ❌]
**Quick take**: [1-2 sentence summary]
## Automated Checks
- **Lint**: [PASS/FAIL with count of issues]
- **Tests**: [PASS/FAIL with coverage %]
## Critical Issues (must fix before merge)
1. **[Issue title]** (file:line)
- Problem: [What's wrong]
- Risk: [Why it matters]
- Fix: [How to fix, code example]
## Suggestions (nice-to-haves)
1. **[Suggestion title]**
- Current: [What it does now]
- Suggestion: [How to improve]
- Benefit: [Why it's better]
## Positive Notes
[What's done well - be specific and encouraging]
## Action Items
- [ ] Fix critical issue 1
- [ ] Fix critical issue 2
- [ ] Consider suggestion 1
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.