Skill UI

This comprehensive guide details the architecture of memory for intelligent agents. It covers the distinction between short-term context, long-term vector storage, and advanced cognitive models (CoALA framework: semantic, episodic, procedural). Learn how to implement robust memory retrieval mechanisms, select appropriate vector databases (Pinecone, Qdrant, etc.), and utilize embedding models to build truly context-aware, persistent AI applications.

This comprehensive workflow guides the end-to-end implementation of Retrieval-Augmented Generation (RAG) systems. It covers critical stages, including selecting optimal embedding models, setting up vector databases, designing chunking strategies, implementing hybrid retrieval, integrating Large Language Models (LLMs), and performing rigorous evaluation. Use this when building knowledge-grounded AI applications or advanced semantic search systems.

Sentence Transformers provides 5000+ pre-trained models that generate sentence, text, and image embeddings for RAG, semantic search, clustering, and multilingual production workloads without relying on external APIs.

SAELens provides a framework for training and analyzing Sparse Autoencoders (SAEs). SAEs decompose the dense, often polysemantic activations of large language models into sparse, monosemantic features. Use this when you need to discover the discrete, interpretable concepts a model has learned, study feature superposition, or analyze specific safety-relevant behaviors (like bias or deception) within deep neural networks.

Vexor is a powerful command-line interface designed for advanced semantic search across local files. By utilizing vector embeddings and integrating with large language models (like Claude/Codex), it allows users to search files based on meaning and context, rather than just exact keywords. This is ideal for large codebases or document repositories where traditional keyword search methods are insufficient.

Helps implement optimized Power BI semantic models by analyzing the active model with MCP tools, then advising on star schemas, DAX, relationships, security, documentation, and performance best practices for reporting scenarios.

Provides a systematic guide for diagnosing and improving poor search quality in vector databases like Qdrant. This guide covers troubleshooting issues such as low recall, when approximate search degrades, selecting optimal embedding models, and correctly tuning HNSW parameters, quantization, and filtering strategies. Essential for optimizing RAG and semantic search pipelines.

This skill provides expert, guided assistance for creating, auditing, and improving Best Practice Analyzer (BPA) rules for Power BI semantic models. It utilizes an interactive, double-diamond discovery process to gather deep context about your organizational standards, model structure, and business goals before generating tailored, reusable data validation and governance rules.

A comprehensive guide for using C# scripting within Tabular Editor to programmatically manipulate and automate Power BI semantic models. This skill supports bulk metadata operations, creating calculation groups, managing security roles, and advanced data model restructuring using the TOM API and LINQ.

Skills and references for writing, debugging, and optimizing DAX in semantic models. Provides a tiered framework, engine internals, patterns, and model optimization strategies, along with trace capture and performance profiling guidance for local and remote models.

Expert guidance for the Fabric CLI (fab) and REST APIs covering workspaces, items, lakehouses, notebooks, pipelines, semantic models, reports, capacities, OneLake, deployment, and admin, including capacity unit cost estimation.

PBIP is the developer-mode file format for Power BI, transforming the opaque PBIX binary into a human-readable, folder-based structure. This structure is crucial for enabling robust source control (Git diffing), external editing using specialized tools like VS Code, and seamless multi-author collaboration. It standardizes how reports and semantic models are structured for professional BI development pipelines.