Skill UI

A comprehensive pipeline for processing, validating, and optimizing scraped web content from Firecrawl. This tool handles markdown cleaning, structured data extraction using Zod validation, content deduplication, and chunking tailored for Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) systems. It ensures crawled data is standardized, clean, and ready for downstream consumption or knowledge base indexing.

Firecrawl provides a comprehensive API for web data harvesting. It enables users to perform single-page scraping, multi-page crawling, site mapping (URL discovery), and advanced structured data extraction using Large Language Models (LLMs). Ideal for integrating data pipelines, building web monitoring tools, or conducting market research.

This advanced workflow provides comprehensive meeting intelligence by allowing users to search across stored transcripts using keywords and date filters. It integrates the AskFred AI assistant for natural language Q&A over single or cross-meeting data. Furthermore, it aggregates detailed meeting analytics, providing key metrics such as total duration, action items, and top keywords for robust reporting and knowledge retrieval.

A practical decision framework for determining whether to use regular expressions or Large Language Models (LLMs) when parsing structured text (e.g., forms, quizzes, invoices). It recommends starting with deterministic, low-cost regex for 95-98% of structured data, and only invoking expensive LLM calls for identifying and validating ambiguous edge cases, optimizing both cost and accuracy.

This guide details how to write advanced correlation searches using Splunk's Search Processing Language (SPL). It covers techniques like threshold-based detection, sequence analysis, and anomaly detection to identify sophisticated security threats (e.g., brute force, data exfiltration, lateral movement) in a Security Operations Center (SOC) environment. Mastery of SPL is essential for closing SIEM detection gaps and ensuring compliance.

The Stock Analyzer Skill provides comprehensive technical analysis for stocks and ETFs. It utilizes industry-standard indicators like RSI, MACD, and Bollinger Bands to generate actionable trading signals. Users can perform advanced technical comparisons, monitor portfolio strength, and identify chart patterns through natural language queries, eliminating the need for manual indicator calculation.

A comprehensive toolkit for advanced geospatial analysis. It covers remote sensing (Sentinel, Landsat), GIS operations (vector/raster/point cloud), spatial statistics, and Machine Learning for Earth Observation. Supports cloud-native workflows, multiple data types, and 8 programming languages, making it ideal for complex scientific research and commercial spatial projects.

Hypogenic is an advanced framework that uses Large Language Models (LLMs) to systematically generate and test hypotheses on complex tabular datasets. It supports three powerful modes: data-driven generation (HypoGeniC), literature-grounded refinement (HypoRefine), and combined union methods. This tool is essential for accelerating scientific discovery in fields such as predictive modeling, content analysis, and deception detection by combining empirical data insights with theoretical knowledge.

MarkItDown is a powerful tool designed to convert a wide array of file types—including PDF, DOCX, images, audio, and structured data (JSON/XML)—into clean, token-efficient Markdown format. It supports advanced features like OCR for scanned documents, transcription for audio, and AI-enhanced descriptions, making diverse content readily consumable and structured for modern Language Models and AI pipelines.

Medchem is a powerful Python library designed for molecular filtering and prioritization in drug discovery. It allows users to apply rigorous, literature-derived drug-likeness rules (e.g., Lipinski, Veber, CNS), detect structural alerts (PAINS, NIBR), calculate complexity metrics, and combine multiple criteria using a custom query language. It is essential for compound library triage and hit-to-lead optimization.

This guide details how to set up and execute large-scale, distributed GPU training jobs on the CoreWeave platform. It covers both single-node multi-GPU setups and multi-node training utilizing PyTorch DDP and Kubernetes resources (A100/H100). This workflow is ideal for fine-tuning large language models (LLMs) or running complex deep learning models that require high-performance, shared-storage compute clusters.

This guide demonstrates how to deploy GPU workloads on the CoreWeave platform using Kubernetes (kubectl). It covers deploying vLLM inference services for large language model (LLM) testing and running batch CUDA jobs for benchmarking. This is ideal for users running their first GPU workloads, testing inference pipelines, or verifying cluster access on bare-metal GPU nodes (A100, H100).