code-review
This skill uses Claude hooks which can execute code automatically in response to events. Review carefully before installing.
This skill contains shell command directives (!`command`) that may execute system commands. Review carefully before installing.
Code Review
YOUR ARGUMENTS: $ARGUMENTS
DO NOT ask the user for arguments. They are provided above. Parse them NOW and proceed with the review.
The argument is the path to the phase file to review (e.g., plans/voice-assistant/phase-01-database-schema.md).
Recent Git Activity
Recent commits (helps identify which files were modified for this phase):
!git log --oneline -10 2>/dev/null || echo "(not a git repository)"
Recently changed files:
!git diff --name-only HEAD~5 2>/dev/null || echo "(no recent changes)"
More from darraghh1/my-claude-setup
playwright-mcp
Live browser interaction via Playwright MCP — navigate pages, click buttons, fill forms, take screenshots.
97drawio-mcp
Create, edit, and export draw.io diagrams via the draw.io MCP server with real-time browser preview.
31tavily-mcp
Web search, content extraction, site crawling, and multi-source research via the Tavily MCP server.
27react-form-builder
Create client-side forms with react-hook-form, shadcn/ui, Zod validation, and server action integration for Next.js applications. Use when building forms, input validation, or 'create/edit' UI flows. Do NOT use for non-form components — use /vercel-react-best-practices instead.
26service-builder
Build pure, interface-agnostic services with injected dependencies for Next.js/Supabase applications. Use when creating service layers, business logic classes, or CRUD operations. Do NOT use for server actions — use /server-action-builder instead.
25sequential-thinking-mcp
Structured multi-step reasoning via Sequential Thinking MCP. Use for complex debugging, architectural trade-offs, or root cause analysis.
24