Skill UI

Use Voiceover Studio to convert written scripts into high-quality, professional audio narration. This tool supports diverse applications including product demos, IVR prompts, podcast episodes, and short-video voiceovers. It manages complex requirements such as specific accents, emotions, speaking pace, and precise language/locale preservation, ensuring the resulting audio is ready for immediate use.

This skill implements the LLM Council concept, enabling multiple open-weight language models to collaborate on complex queries. The process follows a three-stage deliberation: 1) Parallel independent responses from selected models; 2) Peer-to-peer ranking of the responses; and 3) Final synthesis by a designated Chairman LLM. Powered by Fireworks AI, it ensures deep, multi-faceted analysis and consensus building for high-stakes decision support.

NVIDIA garak is an open-source LLM vulnerability scanner designed for comprehensive red-teaming and security assessment. It systematically probes large language models (via OpenAI-compatible APIs, Hugging Face, etc.) using thousands of adversarial prompts. It covers critical vulnerabilities such as prompt injection, jailbreaking, data leakage, and toxicity. Use this tool to establish a repeatable security baseline before or after deployment, validate the effectiveness of safety guardrails, or generate quantitative evidence for AI risk assessments.

This skill guides developers on implementing Conversational Language Understanding (CLU) using the official azure-ai-language-conversations Python SDK. It demonstrates how to analyze conversation intent and entities, build advanced NLP features, and integrate language understanding into applications using ConversationAnalysisClient. Best practices emphasize using DefaultAzureCredential and context managers for robust, production-ready code.

A comprehensive guide and skill for deploying large language models (LLMs) locally using the llama.cpp framework and GGUF quantization format. It covers searching the Hugging Face Hub, selecting optimal quantizations (e.g., Q4_K_M), running local servers, and achieving OpenAI-compatible API endpoints. Supports various hardware backends including CPU, Mac Metal, CUDA, and ROCm. Ideal for developers needing offline, private LLM inference.

A comprehensive guide for training or fine-tuning advanced sentence-transformer models. This skill assists in selecting the correct architecture—including Bi-encoders (SentenceTransformer), CrossEncoders (for reranking), and SparseEncoders—for various Natural Language Processing (NLP) tasks. Use cases include semantic retrieval, similarity matching, document clustering, and pair-wise classification.

This skill provides expert capabilities for training and fine-tuning transformer language models using the TRL (Transformers Reinforcement Learning) library. It supports state-of-the-art post-training methods, including Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), Group Relative Policy Optimization (GRPO), and Reward Model training. Use this skill to align and customize foundation models for advanced tasks via CLI commands.

This skill executes the DeepSWE benchmark, a comprehensive coding-agent evaluation suite. It uses OpenRouter and mini-swe-agent to score various Large Language Models (LLMs) on 113 tasks, providing reproducible results for model comparison, development assessment, and research benchmarking. Use this when a standardized, deep evaluation of LLM coding capabilities is required.

This tool enables complex web interactions using plain natural language commands. Instead of relying on unreliable selectors, it utilizes a powerful page-agent and LLM loop to interpret user intent, performing actions like filling forms, clicking buttons, and extracting data from dynamic websites. Ideal for testing and automation in pages with ambiguous or changing markup.

Optimizes and refines AI prompts to improve clarity, structure, and output quality for large language model tasks and applications.

RouterBase acts as a unified, OpenAI-compatible API gateway, allowing applications to route requests across diverse large language models (LLMs) like GPT, Claude, and Gemini. It helps developers migrate existing OpenAI SDK calls, implement sophisticated primary/fallback model selection based on cost, latency, and quality, and manage multimodal payloads (image, audio, video) from a single, standardized endpoint.

This skill facilitates the persistent storage of critical brand knowledge, including campaign learnings, brand guidelines, and competitive intelligence, into a specialized memory layer (such as a vector database). It automatically indexes content, deduplicates entries via hashing, and applies rich metadata tagging, ensuring that valuable institutional knowledge is preserved and retrievable through natural language search across different sessions.