Skill UI

Expertise in building production-grade LLM applications, advanced Retrieval-Augmented Generation (RAG) systems, and complex intelligent agents. This skill covers the entire AI lifecycle, including model orchestration, vector search optimization, multimodal integration (vision/audio), MLOps deployment, and robust safety governance for enterprise-level AI solutions.

Expertise in building production-grade LLM applications, advanced Retrieval-Augmented Generation (RAG) systems, and complex intelligent agents. This skill covers the entire AI lifecycle, including model orchestration, vector search optimization, multimodal integration (vision/audio), MLOps deployment, and robust safety governance for enterprise-level AI solutions.

This skill guide is essential for building advanced applications using Gemini and Gemma 4 hosted models. It covers working with multimodal content (text, images, audio, video), implementing complex features like function calling and structured output. It provides up-to-date SDK usage examples for Python, JavaScript, Go, and Java, ensuring developers use the latest, recommended API standards.

Guides configuring Firebase AI in Flutter, generating text/chat with Gemini, streaming responses, multimodal prompts, and handling errors with security considerations.

A deep dive into handling typed content blocks (text, image, tool_use, thinking, document) in LangChain 1.0. This skill standardizes multi-modal message composition, tool-call iteration, and complex content handling across providers like Claude, GPT-4o, and Gemini, solving key API discrepancies.

Fast local parsing of PDFs, Office files, and images with per-token bounding boxes. Extract spatial text, run OCR on scans, produce layout-preserved JSON for RAG, batch-ingest folders, and render pages to PNG for multimodal agents. Fully local, no cloud API.

The RunAPI CLI serves as the dedicated execution layer for interacting with RunAPI's suite of advanced AI models. It allows developers to programmatically generate multimodal content, including images, videos, and music/audio, directly from the terminal or CI/CD pipeline. Users can submit one-off jobs, manage asynchronous tasks, and pass complex JSON request bodies to various services like Suno, Claude, and Gemini, making it essential for robust AI automation workflows.

Use this comprehensive skill for interacting with the Gemini API. It supports a wide range of advanced AI tasks, including text generation, multi-turn chat, multimodal understanding, image/video creation, function calling, and structured output. Provides modern SDKs for robust application development in Python and JavaScript/TypeScript.

This skill guides developers on building real-time, bidirectional, and multimodal streaming applications using the Gemini Live API. It covers low-latency voice, video, and text streaming over WebSockets, incorporating advanced features like Voice Activity Detection (VAD), function calling, and secure session management. Ideal for conversational AI, interactive video conferencing, and complex real-time user experiences.

A comprehensive guide for authors writing the Related Work section of ACM Multimedia papers. It teaches how to position cross-modal contributions by covering diverse single-modality shelves (Vision, Audio, Language, HCI), tracing the cross-modal lineage, defining the specific cross-disciplinary novelty (delta), and adhering to academic hygiene standards like double-blinding and venue verification.