
Audits components and pages for WCAG accessibility issues and suggests fixes. Use when building new UI, reviewing components for a11y compliance, or fixing reported accessibility bugs.
Rewrites text to be clearer, simpler, and more engaging using Scott Adams' writing principles and persuasive techniques. Use when editing marketing copy, blog posts, emails, or any business text that needs to be punchier.
Facilitates solution ideation with clear trade-offs and a final recommendation. Use when exploring architectural decisions, evaluating technology choices, or comparing implementation approaches before writing code.
Reviews code changes for correctness, maintainability, security, and adherence to project conventions. Use when reviewing PRs, auditing recent changes, or getting a second opinion on implementation quality.
Generates end-to-end tests using Playwright with the "given/should" prose format. Use when writing e2e tests for user flows, page interactions, or integration scenarios that exercise the full application stack.
Generates React component render tests using happy-dom and Testing Library with the "given/should" prose format. Use when writing tests for display components, hooks, user interactions, or accessibility checks.
Logs completed epics and significant accomplishments in reverse chronological order. Use after completing major features, releases, or architecture changes to maintain a project changelog.
Breaks down feature requests into sequential, implementable tasks with code changes under 50 lines each. Use when planning new features, refactors, or multi-step changes to ensure logical ordering and no broken intermediate states.
React Router V7 patterns for loaders, actions, forms, routes, middleware, and error handling. Use when writing or reviewing React Router code.
Plans and executes safe refactoring with tests as a safety net. Use when restructuring code, extracting functions, renaming across files, or simplifying complex logic without changing behavior.
Security audit for web applications based on OWASP Top 10 and common vulnerabilities. Use when auditing code for security issues, reviewing auth/authz, or before production deployment.
Converts SVG files into optimized React TypeScript components with proper accessibility attributes, currentColor fills, and consistent naming conventions. Use when adding icons or SVG assets to a React project.
Generates well-structured unit tests using Vitest with the "given/should" prose format. Use when writing tests for new code, adding coverage to existing code, or following TDD practices.
Improves text for clarity, directness, and engagement following professional writing best practices. Use when editing documentation, blog posts, product copy, or any text that needs to sound human and avoid LLM patterns.
Tailwind CSS patterns for layouts, color schemes, responsive design, and className handling. Use when writing or reviewing component styles.
Generates integration tests for server actions, database operations, and API routes using Vitest with the "given/should" prose format. Use when testing infrastructure facades, route actions, session management, or multi-service interactions.
Suggests clear, descriptive names for functions and variables following consistent naming conventions. Use when naming new code constructs, renaming for clarity, or reviewing naming in code reviews.
Structured debugging skill for methodical root cause analysis. Use when investigating bugs, unexpected behavior, or errors. Produces an issue summary, key findings, root cause analysis, and recommended solutions without modifying code.
Generates clear, example-driven documentation with runnable code samples and progressive complexity. Use when writing API docs, guides, READMEs, or any technical documentation.
Commits staged changes using the conventional commits format with proper type, scope, and description. Use when committing code changes to maintain a clean, standardized git history.
Continuously steers the codebase toward the VISION.md. Reads the vision, assesses current state, picks the highest-impact next action, builds with TDD, commits, and repeats. Never stops. Use when you want autonomous, vision-driven development.