Loading...
Loading...
Found 40 Skills
Knowledge Base RAG implements the complete Retrieval-Augmented Generation pipeline: document ingestion, intelligent chunking, embedding generation, vector store indexing, semantic retrieval, and grounded response generation.
Anthropic's Contextual Retrieval technique for improved RAG. Use when chunks lose context during retrieval, implementing hybrid BM25+vector search, or reducing retrieval failures.
Vector database selection, embedding storage, approximate nearest neighbor (ANN) algorithms, and vector search optimization. Use when choosing vector stores, designing semantic search, or optimizing similarity search performance.
Semantic search over global agent memory. Use to retrieve previously learned patterns, decisions, gotchas, and workarounds. Prevents stale-context errors across long sessions and multi-agent pipelines.
Use when working with code refactoring context restore
Expert knowledge for Azure AI Search development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when designing indexes, skillsets, vector/semantic search, indexers, private endpoints, or RAG apps, and other Azure AI Search related development tasks. Not for Azure Cosmos DB (use azure-cosmos-db), Azure Data Explorer (use azure-data-explorer), Azure Synapse Analytics (use azure-synapse-analytics).
Provides expertise on Chroma vector database integration for semantic search applications. Use when the user asks about vector search, embeddings, Chroma, semantic search, RAG systems, nearest neighbor search, or adding search functionality to their application.
Salesforce Data Cloud Retrieve phase. Use this skill when the user runs Data Cloud SQL, async queries, vector search, search-index workflows, or metadata introspection for Data Cloud objects. TRIGGER when: user runs Data Cloud SQL, describe, async queries, vector search, search-index workflows, or metadata introspection for Data Cloud objects. DO NOT TRIGGER when: the task is standard CRM SOQL (use querying-soql), segment creation or calculated insight design (use segmenting-datacloud), or STDM/session tracing/parquet analysis (use observing-agentforce).
Expert in deploying and customizing a modular RAG system with MCP protocol for AI assistants
Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.
RAG, embedding, vector search를 통해 사내/최신 데이터를 LLM 응답에 연결하는 방법과 선택 기준을 다루는 모듈.
Generate text embeddings and rerank documents via Together AI. Embedding models include BGE, GTE, E5, UAE families. Reranking via MixedBread reranker. Use when users need text embeddings, vector search, semantic similarity, document reranking, RAG pipeline components, or retrieval-augmented generation.