Skill UI

Azure Batch SDK for Java: create and manage pools, jobs, tasks, and compute nodes to run large-scale parallel and HPC workloads in the cloud, with sync/async clients and autoscale support.

Build AI agents that interact with computers like humans, performing tasks such as viewing screens, moving cursors, clicking buttons, and typing text. This skill covers Anthropic's Computer Use, OpenAI's Operator, and open-source alternatives. It emphasizes sandboxing, security, and handling vision-based control challenges for desktop automation and GUI interaction.

Expert guidance for designing, implementing, and optimizing computer vision pipelines, including YOLO26 detection, SAM 3 segmentation, VLMs, depth estimation, calibration, and edge deployment.

Analyzes exercise logs to identify workout patterns, track fitness progress, compute correlations with health metrics like blood pressure and blood glucose, and generate personalized training recommendations.

This skill covers deploying and managing virtual machines on Google Cloud Platform using Compute Engine. It includes creating instance templates, configuring managed instance groups for auto-scaling, and utilizing preemptible or spot VMs for cost optimization. Users will learn to provision GPU instances, manage snapshots, and apply startup scripts via gcloud CLI commands for production workloads.

This skill enables AI assistants to interact with the Hugging Face Hub via Model Context Protocol (MCP). Users can search for models, datasets, and papers, retrieve repository details, fetch documentation, and execute compute jobs on GPU or CPU. It also allows leveraging Gradio Spaces as functional AI tools. Ideal for developers and researchers needing direct access to the HF ecosystem for model discovery, training, and deployment workflows.

Hunt NTLM/Negotiate information disclosure on internet-reachable IIS, SharePoint, Exchange, and other Windows-based services. This skill guides authorized security assessments to detect exposed NTLM authentication headers, parse Type-2 challenges, and extract internal domain, computer names, and other juicy details for reconnaissance.

This skill analyzes data warehouses to identify stale, unused, or redundant tables that increase storage costs. It classifies waste patterns, computes safety tiers, and provides actionable cleanup recommendations. Supports Snowflake, BigQuery, Redshift, and Databricks. Ideal for reducing cloud infrastructure expenses and optimizing data governance.

Deploy long-running Node.js HTTP functions directly on Neon database branches. Automatically injects DATABASE_URL and runs compute next to your data. Ideal for stateful streaming, WebSocket servers, and agent backends that exceed traditional serverless limits. Managed via Neon CLI.

Master Odoo ORM patterns: search, browse, create, write, domain filters, computed fields, and performance-safe query techniques. Ideal for developers building or optimizing Odoo modules.

Implement physically based sky and aerial perspective systems in Three.js for planetary atmospheres and ground-to-space transitions. Includes Rayleigh/Mie scattering, precomputed LUTs, depth-based transmittance, and atmosphere-aware lighting.

Prove data/AI workflows end-to-end on tiny samples, find cost-saving wins, then scale within budget using cost-gated steps. Ideal for multi-stage pipelines involving paid compute like LLM tokens or warehouse credits.