Frontend

Human-in-the-Loop pattern library for CopilotKit. Use when implementing approval workflows, user input collection, option selection, or any human interaction patterns. Includes React components and hooks.

Expert knowledge for building event-driven systems with Composable Rust framework. Use when implementing reducers, designing state machines, working with effects, creating environment traits for dependency injection, building stores, or answering questions about core architectural patterns and the unidirectional data flow model.

Validates that code actually works through sandbox testing, execution verification, and systematic debugging. Use this skill after code generation or modification to ensure functionality is genuine rather than assumed. The skill creates isolated test environments, executes code with realistic inputs, identifies bugs through systematic analysis, and applies best practices to fix issues without breaking existing functionality. This ensures code delivers its intended behavior reliably.

Rust safety patterns and secure coding. Use when writing code that handles untrusted input, uses unsafe blocks, deals with memory safety, or requires security review.

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

Multi-format document parsing tools for PDF, DOCX, HTML, and Markdown with support for LlamaParse, Unstructured.io, PyPDF2, PDFPlumber, and python-docx. Use when parsing documents, extracting text from PDFs, processing Word documents, converting HTML to text, extracting tables from documents, building RAG pipelines, chunking documents, or when user mentions document parsing, PDF extraction, DOCX processing, table extraction, OCR, LlamaParse, Unstructured.io, or document ingestion.

Guides developer verification before handoff. Use when completing implementation, preparing for acceptance testing, or self-reviewing work before commit or PR.

AI outputs YAML descriptors instead of code, CLI executes deterministically for 100% auditable behavior with zero slop. Use when auditability is critical, generated code review needed, or deterministic execution required. YAML serves as intermediate representation. Triggers on "auditable generation", "YAML output", "deterministic execution", "code review", "vibe coding".

通用 Web 项目构建工具，自动检测项目类型（Vue、React、Ant Design Pro 等），执行依赖安装和生产构建，生成可部署的静态文件并返回预览链接。

Interpretive guidance for applying markdownlint rules using our opinionated configuration. Use when creating or editing markdown files, configuring markdownlint, troubleshooting linting issues, or reviewing markdown quality.

Streaming chat and collaborative features for Composable Svelte. Use when implementing LLM chat interfaces, real-time messaging, or collaborative features. Covers StreamingChat (transport-agnostic), presence tracking, typing indicators, and WebSocket integration from @composable-svelte/chat package.

Extracts design tokens from Figma files and generates production-ready CSS, SCSS, JSON, TypeScript, and W3C DTCG format files using the Figma MCP server

Build interactive CLI applications using Ink (React for terminals). Use when users need to create command-line tools, terminal UIs, or developer utilities. Covers component patterns, user input, and distribution.

Maintain AGENTS.md files across a repo: find and review every AGENTS.md, apply hygiene rules (fix outdated or incorrect guidance, reduce verbosity, split large sections into docs and link them), add newly learned context from the current conversation, and provide a concise enumerated update summary. Use when asked to update AGENTS files, run/sweep the agents update skill, or when AGENTS.md maintenance is required across a repository or subfolder.

DevOps automation for Rust projects. CI/CD pipelines, container builds,deployment automation, and infrastructure as code. Optimized for GitHubActions and Cloudflare deployment.

Research-driven design methodology producing unique, context-appropriate frontends. Prevents AI aesthetic convergence through contextual analysis, cross-pollination research, and banality testing.

Regulatory guidance for Canadian mortgage servicing software. Use when working with Canadian loan data models, payment processing, default management, insured vs uninsured mortgages, or questions about FCAC, OSFI, CMHC requirements, or Canadian mortgage servicing regulations.

Personal AI Infrastructure (PAI) - PAI System Template. Your name is @assistantName@ and you are @userFullName@'s AI assistant. Do not introduce yourself as "Claude Code" MUST BE USED proactively for all user requests. USE PROACTIVELY to ensure complete context availability. Your personality is friendly, professional, resilient to user frustration. Operating Environment is Personal AI infrastructure built around Claude Code with Skills-based context management. This skill provides critical info on how to answer questions, Patrick's key contacts, security guidelines, stack preferences, social media accounts, and other core information.

Expert-level state management with Redux Toolkit and Zustand using TypeScript. Handle complex application state including shopping carts, user authentication, product catalogs, API state management, and advanced patterns. Generate production-ready store configurations, slices, hooks, and complete implementations across React, Next.js, and universal applications. Use when building scalable state management solutions with TypeScript for e-commerce, authentication, async operations, and complex state architectures.

Generate Next.js page components with App Router, Server Components, and data fetching. Triggers on "create nextjs page", "generate next.js route", "nextjs app router page", "next page component".