Tools

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends the agent's capabilities with specialized knowledge, workflows, or tool integrations.

Builds type-safe APIs with tRPC including routers, procedures, context, and client integration. Use when creating end-to-end type-safe APIs, building full-stack TypeScript applications, or replacing REST/GraphQL with simpler patterns.

Build code from GitHub issue specifications. Implements in chunks with tests after each chunk. Uses just commands for quality gates. Creates self-contained modules.

Build accessible user interfaces following WCAG standards with semantic HTML, keyboard navigation, proper color contrast, and ARIA attributes. Use this skill when creating or modifying UI components, React components, Vue components, web forms, navigation menus, modal dialogs, or any interactive elements. Use this skill when implementing keyboard navigation support, adding ARIA labels and roles, ensuring proper focus management, providing alternative text for images, or testing with screen readers. Use this skill when working with component files (.jsx, .tsx, .vue, .svelte), HTML templates, or any frontend code that renders user-facing interfaces. Use this skill when establishing heading hierarchies, form input labels, or color contrast ratios.

Skill/MCPの使い分けと組み合わせ設計を支援するガイド。外部ツール接続はMCP、手順・品質基準はSkillという分離原則、衝突回避、実例（財務バリュエーション/ミーティング準備）を参照し、どちらを使うか判断・設計したいときに使う。

Comprehensive CSS generation, editing, and enhancement tool. Use this skill when users need to create CSS from scratch, modify existing CSS, enhance CSS with modern features, optimize CSS performance, or generate CSS frameworks and components. This skill handles CSS generation, editing, enhancement, validation, and optimization tasks.

Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking screenshots, analyzing performance, monitoring network traffic, web scraping, form automation, and JavaScript debugging.

Validate generated experimental procedures against LA-Bench evaluation criteria. This skill orchestrates formal validation (via script) and semantic evaluation (via subagent) to ensure compliance with LA-Bench standards. Use this skill after generating procedures to assess quality before submission.

Write type-safe TypeScript 5.x code using ES2022+ features, strict mode, discriminated unions, and modern async patterns. Use for TypeScript files (.ts), type definitions (.d.ts), configuration, or full-stack type safety.

Expert README generation including project documentation, badges, and standard sections

Interactive slash command creator for Claude Code. Triggers when user mentions creating commands, slash commands, command templates, command arguments, or wants to build a new command workflow.

Deployment and Git workflow guides for Kailash applications including Docker deployment, Kubernetes orchestration, and Git workflows. Use when asking about 'deployment', 'Docker deployment', 'Kubernetes deployment', 'containerization', 'K8s', 'Git workflow', 'Git branching', 'CI/CD', 'production deployment', 'Docker compose', or 'container orchestration'.

Advanced LangGraph patterns for production applications. Use when implementing streaming (tokens, updates, custom data), parallel node execution, subgraphs for modular workflows, error handling and retries, or Command-based control flow. Covers stream modes, fan-out/fan-in, nested graphs, and production best practices.

Generates an outline for a book chapter or section based on a given topic or summary.

Execute work orders and implement code using coding agents and development tools

Analyze bash commands for safety risks before execution. Use when user asks about command safety or when reviewing dangerous operations.

Build coding agents with the Claude Agent SDK. Use when creating agentic workflows, implementing todo tracking, monitoring agent progress, building multi-turn conversations, streaming responses, or integrating custom tools with Claude Code.

Manage long-term memories using date-based files. Allows creating, listing, and reading memories.

Comprehensive E2E testing suite for MyDetailArea dealership workflows. Implements Playwright test scenarios for critical user journeys including order creation, invoice generation, payment processing, VIN scanning, and team collaboration. Includes role-based testing, performance benchmarks, visual regression, and CI/CD integration. Use when implementing automated testing for dealership operations.

Tailwind CSS utility patterns with shadcn/ui component usage, theming via CSS variables, and responsive design. Use when styling components, installing shadcn components, implementing dark mode, or creating consistent design systems.