Skill UI

Automates creating and validating GCP BigQuery views with best-practice guidance, production-ready code snippets, and integrations for Vertex AI, Cloud Run, Firebase, and similar services to keep analytics workloads consistent.

A comprehensive guide detailing optimization techniques for Databricks environments. It covers optimal cluster sizing for various workloads (ETL, ML, Streaming), advanced Spark configurations (AQE, memory management), and deep data optimization strategies for Delta Lake, including Z-Ordering and Liquid Clustering. It also provides methods for query plan analysis and join optimization.

This bundle collects comprehensive diagnostic evidence from the Juicebox platform. It gathers API connectivity status, dataset health reports, analysis quota usage, and rate limit information into a single archive. Use it to systematically troubleshoot complex issues such as failed dataset uploads, stalled AI analysis runs, API authentication failures, or quota exhaustion.

Ray Data offers scalable distributed data processing for ML workloads, streaming across CPU/GPU clusters and integrating with PyTorch, TensorFlow, and Ray Train. Use it for batch inference, ETL, and multi-modal preprocessing from a laptop up to hundreds of nodes.

Ray Train orchestrates distributed PyTorch, TensorFlow, and HuggingFace workloads from laptops to clusters, automating GPU placement, fault tolerance, checkpointing, and hyperparameter sweeps so teams can scale massive model training with minimal code changes.

Detects abnormal access patterns across major cloud storage platforms, including AWS S3, GCS, and Azure Blob Storage. By analyzing cloud audit logs (CloudTrail, etc.), this tool identifies critical security threats such as after-hours bulk data downloads, sudden spikes in API calls (GetObject spikes), access from new geographic IPs, and potential data exfiltration. It utilizes statistical baselines and time-series anomaly detection for proactive threat hunting and security incident investigation.

This advanced research technique is designed for deep dives into football topics. Instead of relying solely on the original query, it mandates tracking every discovered entity—such as player names, club names, or coaches—from search results. By treating these entities as new leads, the user must formulate follow-up searches using the discovered names and remaining constraints, ensuring nothing relevant is overlooked and building a comprehensive knowledge chain.

A comprehensive skill for managing the entire lifecycle of Volcano Jobs within the KubeSphere environment. It supports the scheduling and execution of complex batch workloads, including deep learning tasks using PyTorch and TensorFlow, MPI, and general resource-intensive jobs. Provides detailed API usage and troubleshooting guidance for job scheduling and resource conflicts.

This utility displays the precise, real-time token usage and estimated cost savings for the current session. It reads directly from the internal session log, ensuring objective and accurate data without requiring AI computation. Triggered by /caveman-stats, it provides immediate performance metrics to monitor API costs and usage patterns.

A comprehensive tool for extracting YouTube transcripts, searching videos, browsing channels, and monitoring new uploads. It supports detailed transcript analysis, content summarization, and playlist management by leveraging the TranscriptAPI. Ideal for researchers, content strategists, and market analysts who need structured data from video content without downloading files.