Skill UI

Provides expert guidance on designing, implementing, and optimizing cutting-edge computer vision pipelines. Expertise spans real-time object detection (YOLO26), advanced promptable segmentation (SAM 3), and leveraging Vision Language Models (VLMs) for complex visual reasoning. Ideal for building high-performance systems in robotics, autonomous vehicles, and industrial inspection, including 3D reconstruction and edge deployment optimization.

Generates complete, production-ready Google Cloud Platform (GCP) code examples and infrastructure templates. It spans various modern AI patterns, including ADK agents, Genkit RAG flows, and multimodal analysis using Vertex AI and Gemini. The output includes runnable code, deployment configuration (Terraform/IaC), security best practices (IAM, VPC-SC), and monitoring setup, ensuring enterprise-grade reliability and cost optimization.

An expert architect specializing in designing, implementing, and managing complex hybrid and multi-cloud environments. Expertise spans major public clouds (AWS, Azure, GCP), private clouds (OpenStack, VMware), and container platforms (Kubernetes). Focus areas include cross-cloud networking, Infrastructure as Code (IaC) using Terraform, workload optimization, zero-trust security implementation, and FinOps cost management.

A minimal example demonstrating how to implement basic tracing using the Langfuse SDK. It illustrates the hierarchy of traces, spans, and generations (LLM calls), providing code examples in TypeScript and Python for easy setup and integration testing.

A comprehensive skill set for building, deploying, and managing production-grade Machine Learning systems. Expertise spans modern frameworks (PyTorch, TensorFlow), model serving using Kubernetes, advanced feature engineering (Feast, Tecton), and robust MLOps practices (monitoring, A/B testing, CI/CD). Focuses on delivering scalable, reliable, and business-value-driven AI solutions.

This skill guides the setup of distributed tracing and performance monitoring using Sentry. It covers configuring the SDK (e.g., setting tracesSampleRate) to capture latency, identify performance bottlenecks, and trace requests across the entire application stack. It demonstrates how to create manual spans for business logic and utilizes profiling for deeper performance insights, ensuring comprehensive application observability.

Define a Gitleaks-driven secret scanning workflow that spans repo baseline scans, pre-commit hooks, GitHub Actions CI/CD runs, custom detection rules, and remediation steps to stop hard-coded credentials from entering source control.

Comprehensive Go testing guidance that spans table-driven subtests, testify suites, mocking, unit/integration tests, benchmarks, coverage, fuzzing, goleak leak detection, snapshot checks, and GitHub Actions CI to keep production suites reliable.

This skill manages the schema for human feedback (annotation configs) within the Arize platform. It allows users to define label types (categorical, continuous, freeform) and programmatically apply these annotations to project spans using the Python SDK. Essential for establishing standardized human review processes and improving model evaluation.

This skill generates highly precise deep links to various resources within the Arize platform, including traces, spans, sessions, datasets, and evaluators. It requires collecting specific resource IDs (e.g., project_id, dataset_id) and managing time ranges (startA/endA) to ensure the user is taken to the exact view, optimizing the user experience for ML practitioners and data scientists.

Defines and runs LLM-as-judge evaluators on Arize via ax commands, handling evaluator creation, continuous monitoring, column mapping, trigger runs, and evaluation spans or experiments with configurable templates, models, and query filters.

Guides adding Arize AX tracing to apps via an agent-assisted two-phase flow, emphasizing read-only analysis before manual instrumentation, favoring auto-integration, and adding manual chain/tool spans for LLM tool calls.