Skill UI

Automates building and evaluating classification models by analyzing datasets, selecting features, tuning hyperparameters, and reporting metrics via the classification-model-builder plugin for supervised learning requests.

Generates Python code and workflows for collaborative, content-based, or hybrid recommendation models, handling data prep, training, evaluation, and scalability so Claude can deliver tailored suggestions across domains.

Provides detailed evaluation of machine learning models using plugin metrics to assess accuracy, precision, recall, F1, and other key indicators, helping users compare models and validate performance before deployment.

A comprehensive workflow for executing advanced, semantic web searches using Exa. This tool moves beyond simple keyword matching, enabling deep context retrieval by understanding the intent behind the query. Key features include RAG context retrieval, content extraction (summaries, highlights, full text), and robust filtering by date range, specific domains, and content categories. Ideal for building knowledge base search features and complex research pipelines.

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.

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.

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.

This comprehensive guide outlines advanced strategies for optimizing PostHog in production environments. Key techniques covered include implementing local feature flag evaluation to eliminate network latency, optimizing event batching for network efficiency, utilizing strategic event sampling, and writing efficient HogQL queries. Master these methods to dramatically improve data collection reliability and query speed.

This skill simulates the role of a quantitative analyst, providing comprehensive tools for building complex financial models, backtesting trading strategies, and analyzing market data. It covers advanced topics like portfolio optimization (Markowitz, Black-Litterman), calculating risk metrics (VaR, Sharpe ratio), and performing statistical arbitrage. Ideal for quantitative finance professionals needing rigorous data analysis, robust backtesting, and risk-adjusted performance evaluation.

This advanced tool simulates complex DeFi flash loan strategies across major protocols like Aave, dYdX, and Balancer. It calculates net profitability, estimates gas costs, and assesses comprehensive risks (MEV, liquidity, execution). Use it to evaluate arbitrage opportunities, analyze liquidation potential, or compare multiple lending providers before executing real transactions.

Automates splitting datasets into training, validation, and test subsets by generating and running Python code so you can quickly prepare data for machine learning model training and evaluation.

This skill provides comprehensive capabilities for web searching, content extraction, and web crawling using the Tavily API. It is ideal for tasks requiring up-to-date information retrieval, deep content scraping from specific URLs, or comprehensive website crawling for research purposes, making it a powerful research augmentation tool.