This skill extracts clean markdown or text content from specific URLs using Tavily's extraction API. Perfect for research, documentation retrieval, and content aggregation without writing custom scraping code.

Poor database performance can slow applications to a crawl. This skill provides 27 optimized PostgreSQL patterns covering indexes, query optimization, connection management, security, and schema design to achieve 10-100x performance improvements.

Crawl4AI enables efficient web scraping with JavaScript support, schema-based extraction, and flexible output formats. Users can extract data without LLM calls for cost-effective automation or use LLM-powered extraction for complex content.

AI agents struggle to learn from past experiences and improve over time. ReasoningBank provides adaptive learning patterns using AgentDB so agents can track trajectories, judge outcomes, and distill memories into reusable patterns.

Traditional databases struggle with semantic search queries. AgentDB delivers 150x faster vector operations with sub-millisecond search times for building intelligent RAG systems and knowledge bases.

AgentDB vector searches slow down as data grows, causing application lag. This skill provides quantization and indexing techniques to achieve 150x faster searches with 4-32x memory reduction while maintaining accuracy.

Building self-learning agents requires complex reinforcement learning setup. This skill provides templates and guidance for 9 algorithms including Decision Transformer, Q-Learning, and Actor-Critic.

Build sophisticated distributed AI systems with sub-millisecond synchronization and advanced search capabilities. Learn to implement QUIC sync, custom distance metrics, and hybrid vector plus metadata search for production applications.

Measuring agent quality requires structured approaches. This skill provides multi-dimensional evaluation rubrics, test set management, and production monitoring to continuously assess and improve agent performance.

Limited context windows constrain complex tasks and increase API costs. This skill provides proven techniques to double or triple effective context capacity through compaction, observation masking, KV-cache optimization, and context partitioning.

Context is the foundation of effective AI agent performance. This skill teaches you how to understand, design, and optimize context in agent systems. Learn the principles of progressive disclosure, attention mechanics, and context budgeting to build more capable AI agents.

Manual evaluation of LLM outputs is slow and inconsistent across reviewers. This skill provides production-grade techniques for automated evaluation using LLMs as judges. It includes direct scoring rubrics, pairwise comparison with position bias mitigation, and confidence calibration.

This skill provides comprehensive documentation and SDK references for Azure AI services including Search, Speech, OpenAI, Vision, Translation, and Document Intelligence. It helps developers quickly find the right APIs and code patterns for their AI solutions.

JSON Canvas is an open file format for infinite canvas data used in Obsidian. This skill provides comprehensive documentation and guidance for creating valid JSON Canvas files with nodes, edges, groups, and connections for visual canvases, mind maps, and flowcharts.

The ZINC database contains 230M+ purchasable chemical compounds for drug discovery research. This skill provides programmatic access to search by ZINC ID, SMILES, or supplier code, retrieve 3D structures, and perform similarity searches for virtual screening and molecular docking studies.

Working with large datasets that exceed memory limits. Zarr-python enables chunked array storage with compression for efficient cloud-native scientific computing workflows.

This skill enables creating, editing, and analyzing Excel spreadsheets with formulas, formatting, and data analysis. It also recalculates formulas and verifies zero errors for publication-quality outputs.

Processing large tabular datasets that exceed RAM requires specialized tools. Vaex enables out-of-core DataFrame operations, lazy evaluation, and billion-row-per-second processing on datasets too big for memory. Perfect for astronomical data, financial time series, and large-scale scientific analysis.

High-dimensional data is difficult to visualize and analyze. UMAP reduces dimensions while preserving structure, enabling clear 2D/3D visualizations and better clustering results.

Graph Neural Networks power modern applications like drug discovery, social network analysis, and recommendation systems. This skill provides ready-to-use templates and documentation for implementing GNNs with PyTorch Geometric.