Skill UI

This skill covers using the Azure Event Hubs SDK for TypeScript to build high-throughput event streaming applications. It includes real-time data ingestion, sending events to specific partitions, receiving events with checkpointing for production reliability, and handling batch processing options. Ideal for IoT telemetry and real-time data pipelines.

This skill provides a Java SDK client library for sending custom logs to Azure Monitor via Data Collection Rules (DCR) and Data Collection Endpoints (DCE). It covers installation, client creation, synchronous and asynchronous uploads, error handling, and best practices for ingestion.

Send custom logs to an Azure Monitor Log Analytics workspace with the Python Logs Ingestion API. Covers authentication, Data Collection Rules, batching, async clients, and error handling.

Auto-instrument Node.js and TypeScript apps with Azure Monitor OpenTelemetry for distributed tracing, custom metrics, and log ingestion. Covers auto-instrumentation, ESM loader, sampling, exporters, and manual provider setup.

Extract text and data from many files at once with shared config, per-file overrides, bounded parallelism, and error recovery. Supports PDFs, DOCX, XLSX, and more, with JSON or text output for LLM ingestion.

Guide for splitting extracted text into chunks for LLM context windows or RAG ingestion. Covers chunk size, overlap, markdown/yaml/semantic chunkers, tokenizer-based sizing, and the standalone chunk command.

Clarity Gate is a pre-ingestion verification system designed for Retrieval-Augmented Generation (RAG) workflows. It ensures documents entering knowledge bases are properly qualified by checking for uncertainty markers and distinguishing assumptions from facts. This skill produces Clarity-Gated Documents (CGD) and validates Source of Truth (SOT) files. It helps prevent hallucinations by enforcing epistemic quality standards before data ingestion. Note that it verifies document form rather than factual truth, requiring human-in-the-loop validation for accuracy.

Extract structured tabular data from PDFs, spreadsheets, and images using layout-aware detection and configurable table models, with markdown or JSON cell output for LLM ingestion and downstream processing.

This skill extracts full transcripts and rich metadata from a single YouTube video URL. It uses yt-dlp to download subtitles, cleans VTT timing markers, and pulls video details (title, channel, date). The output is a structured, queryable Markdown file, ideal for populating a personal knowledge vault and enabling downstream knowledge graph extraction or content repurposing.

An expert agent designed to collect critical data assets—including metadata, data lineage, and query logs—from any data warehouse platform. It uses the push ingestion API to send this data directly to Monte Carlo. This method is essential for integrating data sources that cannot be reliably covered by standard pull collectors, such as custom lineage paths or historical query logs.

Validates 1EdTech/IMS Global OneRoster v1.1 and v1.2 CSV roster sets for manifest integrity, bulk vs delta strictness, foreign key references, and encoding sanitization. Use for pre-flight checks before SIS/Clever/ClassLink ingestion.

This skill enables splitting extracted text into optimized chunks for LLM context windows or RAG ingestion pipelines. It supports configurable chunk sizes, overlap settings, and various chunker types including text, markdown, YAML, and semantic splitting. Users can utilize token-based sizing for specific models or standalone commands for pre-existing text. Ideal for preparing documents for vector stores or summarization tasks.