Skill UI

This comprehensive skill guides users through the entire lifecycle of developing AI agent skills. From initial concept (Understand) to structured design, writing the core skill logic, rigorous testing, and final performance optimization. It ensures skills are robust, accurate, and highly triggerable across any domain, including engineering, content creation, and research.

This guide provides a comprehensive methodology for load testing and capacity planning within Snowflake data warehouses. It covers optimizing query performance by adjusting warehouse sizes (Scale UP), simulating high concurrency using multi-threading (Scale OUT), and configuring advanced scaling policies (Standard, Economy, Maximized). Users can benchmark critical queries using SQL and simulate real-world user traffic using Python, ensuring robust and cost-efficient production environments.

This guide provides a comprehensive method for setting up Snowflake observability. It teaches how to leverage built-in ACCOUNT_USAGE views to monitor critical metrics such as query performance (latency, error rates), credit consumption, and storage growth. Furthermore, it demonstrates how to implement automated alerts for operational issues (e.g., high failure rates, stuck warehouses) and export metrics to external monitoring systems like Grafana or Prometheus.

TileDB-VCF is a high-performance library built on TileDB's sparse array technology, designed for the efficient storage and retrieval of large-scale genomic variant-call data (VCF/BCF). It supports scalable, incremental ingestion of single-sample VCF/BCF files and enables highly efficient parallel querying across vast genomic regions and multiple samples. This tool is essential for building robust population genomics databases, conducting GWAS, and performing large-scale cohort studies.

This skill provides a production-grade, containerized integration service for connecting to the Together AI platform. It facilitates high-performance inference, fine-tuning, and model deployment across over 100 open-source models using Together's OpenAI-compatible API. Includes comprehensive Docker setup, environment variable management, health checks, and zero-downtime rolling update strategies for robust, real-time LLM serving.

This guide provides advanced strategies for optimizing Webflow Data API v2 performance. Learn how to mitigate rate limits and reduce latency by utilizing CDN-cached live item reads, implementing application-level or Redis caching, and leveraging bulk endpoints for efficient data writes. Essential for high-traffic, data-intensive Webflow projects that require robust scaling.

This skill provides high-performance, real-time object detection utilizing the Google Coral Edge TPU accelerator. It processes live camera frames to identify up to 80 COCO classes (e.g., person, car, dog). Optimized for native macOS and Linux deployment, it achieves extremely low latency (e.g., ~4ms at 320x320), making it ideal for embedded vision systems, surveillance, and low-latency monitoring applications.

This skill provides real-time object detection capabilities by leveraging the Google Coral Edge TPU accelerator. It operates natively within Windows Subsystem for Linux (WSL), allowing high-speed, low-latency inference on live camera frames. By utilizing hardware acceleration, it achieves impressive performance (e.g., ~4ms inference at 320x320), making it ideal for edge computing projects requiring rapid visual analysis and resource efficiency.

This skill provides high-performance, real-time object detection using the Intel OpenVINO runtime. It operates via a Docker container, ensuring cross-platform compatibility. Supports detection across various Intel accelerators (NCS2, iGPU, Arc GPU) and CPUs. Users can customize parameters like confidence threshold, target classes, processing FPS, and model precision to optimize performance for specific hardware and accuracy needs.