Loading...
Loading...
Found 35 Skills
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.
OpenSearch development best practices for indexing, querying, search optimization, vector search, and cluster management
This skill should be used when the user asks to "connect to Turso", "use libSQL", "set up a Turso database", "query Turso with TypeScript", or needs guidance on Turso Cloud, embedded replicas, or vector search with libSQL.
Use when working with code refactoring context restore
Salesforce Data Cloud Retrieve phase. 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 sf-soql), segment creation or calculated insight design (use sf-datacloud-segment), or STDM/session tracing/parquet analysis (use sf-ai-agentforce-observability).
Retrieval-Augmented Generation - chunking strategies, embedding, vector search, hybrid retrieval, reranking, query transformation. Use when building RAG pipelines, knowledge bases, or context-augmented applications.
Kinetica SQL query knowledge. Activate when the user is writing analytical queries for Kinetica, asking about Kinetica-specific functions, or working with geospatial, time-series, graph, or vector data.
Clean code patterns for Azure AI Search Python SDK (azure-search-documents). Use when building search applications, creating/managing indexes, implementing agentic retrieval with knowledge bases, or working with vector/hybrid search. Covers SearchClient, SearchIndexClient, SearchIndexerClient, and KnowledgeBaseRetrievalClient.
Search conversation history and semantic memory to recall previous discussions, decisions, and context. Use when the user asks to "search memory", "what did we discuss", "remember when", "find previous conversation", "check history", or before starting work to recall prior decisions.
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.
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.