Agent Claude Code
Audit frontend code for WCAG 2.1 AA compliance. Use when building UI components, before launch, or when accessibility issues are reported. Checks semantic HTML, keyboard navigation, ARIA, color contrast, and screen reader compatibility.
Agent Claude Code
Reviews system design, module boundaries, and architectural patterns. Use PROACTIVELY when adding new modules, creating new directories, or restructuring code. Catches structural problems before they become expensive to fix.
Agent Claude Code
MUST BE USED PROACTIVELY after writing or modifying any code. Reviews against project standards, TypeScript strict mode, React patterns, accessibility, and performance. Catches anti-patterns before they ship.
Agent Claude Code
Writes and updates project documentation automatically. Use PROACTIVELY after code changes to keep docs in sync. Generates JSDoc comments, component docs, README updates, and API references without being asked.
Agent Claude Code
Monitors all other agents and produces a single unified project health report. Use when starting a coding session, before deploying, or when context-switching back to a project. Summarizes findings from code-reviewer, performance-auditor, accessibility-auditor, architecture-reviewer, doc-generator, and test-writer.
Agent Claude Code
Analyze frontend performance — bundle size, Core Web Vitals, rendering, network waterfall. Use when investigating slow pages, optimizing load times, or auditing performance before launch.
Agent Claude Code
Plan safe, incremental refactoring strategies. Use when code needs restructuring, patterns need updating, or technical debt needs addressing. Creates a step-by-step migration plan with rollback points.
Agent Claude Code
Writes and runs tests automatically. Use PROACTIVELY after new features, bug fixes, or refactors to maintain coverage. Creates unit tests with React Testing Library, factory functions, and proper mocking.
Command Claude Code
Auto-diagnose and fix build or compile errors iteratively.
Command Claude Code
Run comprehensive code quality checks on a directory or file.
Command Claude Code
Scaffold a new React component with test, story, and types.
Command Claude Code
Pre-deployment verification checklist.
Command Claude Code
Generate and run Playwright end-to-end tests from user flow descriptions.
Command Claude Code
Run a Lighthouse audit, parse scores, and generate a prioritized fix list.
Command Claude Code
Guided migration between patterns, libraries, or approaches.
Command Claude Code
Explore and document an unfamiliar codebase.
Command Claude Code
Full frontend performance audit — bundle analysis, dependency weight, image optimization, load waterfall.
Command Claude Code
Review current branch changes and prepare for PR.
Command Claude Code
Test-driven development workflow — red, green, refactor, commit.
Command Claude Code
Work on a ticket end-to-end — from reading requirements to creating a PR.
Hook Claude Code
Runs before the agent uses a tool for Edit, Write, MultiEdit, Edit, Write and MultiEdit tool calls, running an inline shell check (2 commands). From Piyush8296/claude-workspace.
Hook Claude Code
Runs after a tool call finishes for Edit, Write, MultiEdit, Edit, Write, MultiEdit, Edit, Write, MultiEdit, Edit, Write, MultiEdit, Edit, Write, MultiEdit, Edit, Write and MultiEdit tool calls, running an inline shell check (6 commands). From Piyush8296/claude-workspace.
Hook Claude Code
Runs when the agent finishes a response, running an inline shell check (2 commands). From Piyush8296/claude-workspace.
Settings file Claude Code
Agent settings declaring 3 hook events (PreToolUse, PostToolUse, Stop) and 40 allowed tools.