Skill UI

This comprehensive guide teaches you how to integrate and use the ElevenLabs Text-to-Speech (TTS) API. It provides multiple code examples (TypeScript, Python, cURL) for generating high-quality speech audio from text. Learn advanced features such as detailed voice parameter control, choosing optimal models (e.g., streaming vs. standard), and implementing low-latency streaming for real-time applications.

This comprehensive guide provides a production-grade reference architecture for building robust Text-to-Speech (TTS) and voice applications using the ElevenLabs API. It covers detailed project structure, service layer design (including TTS orchestration, voice management, and caching), configuration handling, and best practices for streaming and multi-model orchestration, ensuring scalability and reliability in a commercial SaaS environment.

Provides comprehensive guides for upgrading the ElevenLabs SDK (JS and Python) and migrating between model generations. This guide covers necessary steps for package renaming, model ID changes (e.g., v1 to v3), API endpoint stability, and best practices for maintaining compatibility during major platform updates. Essential for developers working with advanced voice synthesis.

This skill performs a deep, cross-model audit of experimental results to ensure integrity before claiming findings. It systematically checks for common fraud patterns, such as generating fake ground truths, misleading score normalization, or citing phantom results. Use it when evaluating reported experimental outcomes to ensure methodological rigor and trustworthiness.

FastMCP CLI provides a unified command-line interface to interact with Model Context Protocol (MCP) servers. It allows users to discover available tools and invoke them programmatically using `fastmcp list` and `fastmcp call`. The CLI supports various server targets (HTTP URLs, local files, configs), complex argument types, and ensures structured output, making it essential for building automated, multi-tool workflows and system integrations.

Generates high-quality, deterministic, and editable vector diagrams (SVG) for system architecture, workflows, and pipelines. By using a structured JSON specification (FigureSpec), it ensures that the same input always yields the identical output, making it ideal for reproducible technical documentation, academic papers, and formal system modeling where precise layout and connections are critical. It is optimized for non-data-plot, formal diagrams.

This skill automatically converts structured data specifications (such as CSV, JSON schemas, SQL DDL, or Protobuf definitions) into functional, production-ready code. It generates complete models, validation logic, full CRUD API endpoints, and unit tests in multiple languages (Python, TypeScript, Go, etc.), significantly reducing boilerplate coding time and ensuring type safety.

Finta is a comprehensive workflow tool designed for managing investor relations post-fundraise. It streamlines the process of sending periodic, data-rich updates (including MRR, ARR, and burn rate) to all investors. Users can track complex cap table changes, model future dilution, and leverage a network feature to find warm introductions, ensuring professional and compliant communication with Limited Partners (LPs).

This skill converts complex technical descriptions, such as system architectures, data flow diagrams, flowcharts, and sequence diagrams, into professional, production-quality SVG diagrams. It supports various technical models, including Agent and Memory architectures, and exports the final output as high-resolution PNG files for seamless documentation and presentation use.

A comprehensive evaluation suite designed to benchmark the performance of Large Language Models (LLM) and Vision-Language Models (VLM) specifically for home security applications. It covers 143 diverse tests across 16 critical domains, including tool use, prompt injection resistance, contextual reasoning, alert triage, and detailed scene analysis, ensuring robustness for smart home AI systems.

This benchmark evaluates Vision-Language Models (VLMs) on detecting potential safety hazards within indoor environments. It uses static camera frames, simulating real-world fixed security camera monitoring. The test covers 40 scenarios across 5 critical categories, including fire/smoke, electrical risks, trips/falls, child safety, and falling objects, providing a rigorous measure of VLM's practical safety inspection capability.

This expert assistant specializes in creating, generating, editing, and optimizing professional visual assets for marketing campaigns. Whether you need blog heroes, social media graphics, product mockups, or brand banners, it guides you through selecting the right AI model (e.g., Gemini, Midjourney, Ideogram) or design workflow (e.g., Figma, Canva). It provides best practices for prompting, consistency, and web optimization, ensuring high-quality, brand-compliant visuals every time.