Skill UI

Automates adapting pretrained models via transfer learning by analyzing requirements, generating PyTorch or TensorFlow fine-tuning code, validating data, tracking KPIs, and saving artifacts so you can quickly reuse existing models for new datasets and tasks.

Automates change-data-capture pipeline planning by guiding developers through ETL, orchestration, and streaming best practices, then generating validated configs and code when “cdc pipeline creator” is requested.

This skill provides comprehensive, structured audit logging for OpenRouter API interactions. It automatically captures essential metadata like total cost, token usage, model details, latency, and status, while also performing PII redaction. The resulting audit trail is stored in an append-only SQLite database, making it ideal for building compliance-ready systems, detailed cost monitoring, and deep debugging of production environments.

This comprehensive workflow guides developers through implementing full-stack product analytics using PostHog. It covers key areas including defining event taxonomies, capturing user actions (client-side), identifying and updating user properties, and performing B2B group analytics. It also demonstrates server-side event tracking using posthog-node, ensuring a complete, accurate, and traceable view of user behavior and product usage across web, mobile, and API sources.

This skill provides advanced techniques for optimizing PostHog Cloud usage and reducing associated costs. It covers auditing event volume, implementing intelligent event sampling (e.g., sampling pageviews or autocapture events), filtering bot traffic, and tuning session recording rates. The goal is to maintain critical analytical value while staying within budget limits.

This guide provides minimal working examples demonstrating the three core PostHog functionalities: event capture, user identification, and feature flag evaluation. It covers both server-side (Node.js, Python) and client-side (JavaScript) SDK usage, as well as direct API calls, making it perfect for initial integration setup, testing, and learning basic product analytics patterns.

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.

A comprehensive skill for ingesting, analyzing, and manipulating multi-modal video and audio content. Supports real-time desktop capture, live stream monitoring (RTSP), and file uploads (URL/local). Capabilities include advanced indexing (visual, semantic, temporal), precise moment searching, professional timeline editing (subtitles, overlays, dubbing), transcoding, and generating actionable alerts. Ideal for content creators, monitoring systems, and complex media workflows.

This skill provides a comprehensive method for querying advanced threat intelligence using ATT&CK data. It maps the Tactics, Techniques, and Procedures (TTPs) of specific APT groups into MITRE ATT&CK Navigator layers. Users can build multi-layer heatmaps to identify detection gaps, compare threat coverage, and create structured threat-intel reports for defense engineering.

This skill detects advanced cyber-physical attacks mimicking the Stuxnet pattern. It monitors for unauthorized modifications to PLC logic and detects discrepancies between reported sensor readings and actual physical process behavior. Ideal for high-security OT/ICS environments when hunting for APT lateral movement or validating process integrity against sophisticated threats.

A powerful toolset for automating core PostHog product analytics tasks via Rube MCP. It enables developers and analysts to capture user events, list and filter event data, manage feature flags (creation, retrieval, listing), and inspect user profiles. Ideal for integrating advanced product tracking and A/B testing workflows directly into development pipelines.