Skill UI

Generate production-ready TypeScript project structures for Next.js, React with Vite, Node.js APIs, libraries, or CLI tools. Includes pnpm setup, type-safe configs, testing, linting, and modern build tooling best practices.

A skill for reverse engineering front-end web applications. It helps locate API signature chains, analyze encrypted request parameters, sample runtime behavior, and reproduce logic locally in Node.js for evidence-based output. Suitable for security assessments and understanding client-side encryption.

Secure LLM-powered applications against prompt injection, data leakage, and abuse using input validation, output controls, and tenant isolation. Implements OWASP LLM Top 10 mitigations with Python and Node.js examples.

This skill enables horizontal scaling of Large Language Model inference clusters on Kubernetes. It utilizes KEDA for event-driven autoscaling based on custom GPU metrics like request queues and cache usage. The guide covers deploying vLLM on GPU nodes, configuring Prometheus for monitoring, implementing spot instance strategies for cost efficiency, and setting up queue-based scaling for batch jobs. It ensures optimal resource utilization and cost management for high-traffic AI workloads.

Build enterprise agents for Microsoft 365, Teams, and Copilot Studio with the Microsoft 365 Agents SDK in TypeScript/Node.js. Covers Express hosting, AgentApplication routing, streaming responses with Azure OpenAI, invoke activities, and Copilot Studio client and WebChat integration.

This skill enables developers to override Markstream node renderers and add trusted custom tags across Vue, React, Svelte, and Angular. It allows scoped or renderer-local mappings without replacing the parser. Useful for customizing built-in elements or rendering specific tags like thinking. It emphasizes security by treating custom tags as trusted input and maintaining safe HTML policies.

Build Model Context Protocol servers to enable LLMs to interact with external APIs and services. Supports Python (FastMCP) and Node/TypeScript (MCP SDK) for creating tools that help AI agents accomplish real-world tasks. Learn to design well-structured tools, manage context, and implement transport mechanisms like stdio or Streamable HTTP.

This skill generates standardized, production-ready `mise.toml` configurations. It helps developers standardize runtime versions across mixed-language projects (e.g., Node.js, Python, Go, etc.) and CI/CD pipelines, eliminating the need for multiple legacy version managers like asdf or nvm. Ideal for ensuring reproducible, consistent development environments.

Design n8n AI agents, chains, classifiers, extractors, tool calling, memory, RAG, structured output, and human-review flows. Covers sub-node patterns, connection types, and best practices for production workflows.

This skill provides expert guidance for writing JavaScript code within n8n Code nodes. It covers using $input, $json, and $node syntax, making HTTP requests with $helpers, and working with dates using DateTime. It helps with troubleshooting Code node errors and choosing between Code node modes. Use this for complex transformations, custom calculations, recursive operations, and data aggregation that simple nodes cannot handle.

This skill guides users on writing Python code within n8n Code nodes, focusing on standard library usage. It details critical limitations regarding external packages, offering workarounds for HTTP requests and data analysis. Users learn when to prefer Python over JavaScript and how to handle specific syntax requirements safely within the n8n environment.

This skill guides users on writing and debugging JavaScript or Python code for the n8n Custom Code Tool, which is invoked by AI agents via LangChain. It covers input schemas, sandbox limits, return formats, and security best practices. Unlike standard Code nodes, this tool requires string returns and specific input handling for AI interaction.