hybrid-search-implementation

reikiplanet

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

azure-search-documents-py

oki3505F

Azure AI Search SDK for Python. Use for vector search, hybrid search, semantic ranking, indexing, and skillsets.

building-rag-systems

Asmayaseen

Build production RAG systems with semantic chunking, incremental indexing, and filtered retrieval. Use when implementing document ingestion pipelines, vector search with Qdrant, or context-aware retrieval. Covers chunking strategies, change detection, payload indexing, and context expansion. NOT when doing simple similarity search without production requirements.

skool-rag

aiagentwithdhruv

Query Skool community content using RAG pipeline with vector search. Use when user asks to search Skool knowledge, find community answers, or query Skool content.

similarity-search-patterns

reikiplanet

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

similarity-search-patterns

haniakrim21

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

vector-database-engineer

oki3505F

Expert in vector databases, embedding strategies, and semantic search implementation. Masters Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similar

Vertex Infra Expert

nivkazdan

Use when provisioning Vertex AI infrastructure with Terraform. Trigger with phrases like "vertex ai terraform", "deploy gemini terraform", "model garden infrastructure", "vertex ai endpoints terraform", or "vector search terraform". Provisions Model Garden models, Gemini endpoints, vector search indices, ML pipelines, and production AI services with encryption and auto-scaling.

chroma

sharp-skills

Chroma is the open-source AI-native vector database for building LLM-powered search and retrieval applications. Use when asked to: store and query embeddings for semantic search, build a RAG (retrieval-augmented generation) pipeline, add vector search to an AI app, persist and reload a vector index, filter documents by metadata in a vector store, integrate ChromaDB with LangChain or LlamaIndex, create or manage document collections with embeddings, or switch from in-memory to persistent/client-server Chroma storage.

rag-engineer

oki3505F

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

similarity-search-patterns

JuanJoseGonGi

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

bim-cost-estimation-cwicr

jdmorag97-rgb

Automated cost estimation from BIM models using DDC CWICR database with 55,719 work items. AI classification + vector search for accurate pricing.

scry

ExoPriors

Query the ExoPriors Scry API -- SQL-over-HTTPS search across 229M+ entities spanning forums, papers, social media, government records, and prediction markets. Use when the task involves: Scry API, ExoPriors, /v1/scry/query, scry.search, scry.entities, materialized views, corpus search, epistemic infrastructure, 229M entities, lexical search, BM25, structured agent judgements, scry shares, cross-corpus analysis. NOT for: semantic/vector search composition or embedding algebra (use vector-composition), LLM-based reranking (use rerank), cross-platform people graph traversal (use people-graph), OpenAlex academic helpers (use openalex), or the user's own local Postgres / non-ExoPriors data sources.

vexor

oki3505F

Vector-powered CLI for semantic file search with a Claude/Codex skill

hybrid-search-implementation

mowgliph

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

vector-index-tuning

JuanJoseGonGi

Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.

vector-index-tuning

reikiplanet

Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.

azure-search-documents-ts

oki3505F

Build search applications using the Azure AI Search SDK for JavaScript (@azure/search-documents). Use it when creating or managing indexes, implementing vector or hybrid search, applying semantic ranking, or building aggregation and retrieval workflows.

surrealdb

24601

Expert SurrealDB 3 skill. Use when working with SurrealDB, SurrealQL queries, multi-model data modeling (document, graph, vector, time-series, geospatial), schema design, graph traversal, vector search, security and permissions, deployment and operations, performance tuning, SDK integration (JavaScript, Python, Go, Rust, Java, .NET), Surrealism WASM extensions, Surrealist IDE, Surreal-Sync migrations, or SurrealFS.

similarity-search-patterns

mowgliph

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

Pinecone

sharp-skills

Production Pinecone vector database client for Python. Handles upsert, query, and index management with retry logic, namespace isolation, API key rotation, and dimension mismatch guards. Use when a user asks to: store embeddings in Pinecone, query similar vectors, build a RAG pipeline with Pinecone, manage Pinecone indexes, upsert vectors with metadata, filter vector search results, handle Pinecone API errors, or rotate Pinecone API keys in production.

Open Notebook

reikiplanet

A self-hosted, open-source alternative to Google NotebookLM for AI-powered research and document analysis. Use it to organize research materials into notebooks, ingest diverse content sources (PDFs, videos, audio, web pages, Office documents), generate AI-powered notes and summaries, create multi-speaker podcasts from research, chat with documents using context-aware AI, search across materials with full-text and vector search, or run custom content transformations. Supports 16+ AI providers including OpenAI, Anthropic, Google, Ollama, Groq, and Mistral, and provides complete data privacy through self-hosting.

azure-search-documents-py

haniakrim21

Azure AI Search SDK for Python. Use it for vector search, hybrid search, semantic ranking, indexing, and skillsets. Triggers: "azure-search-documents", "SearchClient", "SearchIndexClient", "vector search", "hybrid search", "semantic search".

vexor

haniakrim21

Vector-powered CLI for semantic file search with a Claude/Codex skill

vector-search

joshrotenberg

Redis vector search and embedding patterns

vector-index-tuning

mowgliph

Optimize vector index performance for latency, recall, and memory. Use when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.

Semantic Search Engine

Eli-yu-first

Implements semantic search with embedding models, vector databases, and hybrid search strategies

rag-implementation

mowgliph

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

azure-search-documents-ts

haniakrim21

Build search applications using the Azure AI Search SDK for JavaScript (@azure/search-documents). Use it when creating or managing indexes, implementing vector or hybrid search, applying semantic ranking, or building agentic retrieval workflows with knowledge bases.

RAG Implementation

oki3505F

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

rag-architect

ARazaAnjum

Use when building RAG systems, vector databases, or knowledge-grounded AI applications requiring semantic search, document retrieval, or context augmentation.

Similarity Search Patterns

miethe

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

Similarity Search Patterns

oki3505F

Implement efficient similarity search with vector databases. Use when building semantic search, implementing nearest neighbor queries, or optimizing retrieval performance.

supabase

chiuweilun1107

Supabase development and self-hosted operations. Use when user mentions supabase, database query, migration, Edge Function, RLS policy, pgvector, vector search, backup, health check, or says "資料庫", "supabase掛了", "備份", "向量搜尋", "RAG". Covers CLI ops, Docker management, schema design, and vector/RAG pipelines.

vector-database-engineer

haniakrim21

Expert in vector databases, embedding strategies, and semantic search implementation. Mastery of Pinecone, Weaviate, Qdrant, Milvus, and pgvector for RAG applications, recommendation systems, and similarity search.

parse-documents

hiydavid

Build a document-ingestion pipeline for RAG from Unity Catalog Volume files using `ai_parse_document`, chunking, Delta tables, and optional initial Vector Search index creation. Use when: (1) User wants to parse PDFs, DOCX, PPTX, or images into structured text, (2) User asks for ai_parse_document notebook templates or chunking strategy selection, (3) User needs end-to-end document-to-index ingestion from raw files. Do not use for standalone Vector Search endpoint/index lifecycle operations that are not tied to document parsing; use `create-update-vector-search-index` for those tasks.

RAG Implementation

haniakrim21

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

vector-index-tuning

oki3505F

Optimize vector index performance for latency, recall, and memory usage. Use this when tuning HNSW parameters, selecting quantization strategies, or scaling vector search infrastructure.

create-update-vector-search-index

hiydavid

Create, update, and manage Databricks Vector Search endpoints and indexes using the Python SDK. Use when: (1) User wants to create a Vector Search endpoint or index, (2) User says 'create vector search', 'create index', 'update index', 'sync index', 'upsert vectors', (3) User needs to set up delta-sync or direct-access indexes, (4) User asks about embedding configuration, sync modes, or endpoint types, (5) User wants to manage index lifecycle (create, sync, upsert, delete records, schema changes). Covers endpoint creation, both index types (delta-sync and direct-access), managed vs self-managed embeddings, sync operations, and data upsert/delete.

research-workflow

ExoPriors

End-to-end research workflow orchestrator for ExoPriors/Scry. Chains corpus search, semantic embedding, LLM reranking, and artifact sharing into complete research pipelines. Use when asked to produce a literature review, reading list, research brief, shareable report, systematic corpus analysis, or a complete research pipeline. Invoke with /research. NOT for: single SQL queries (use scry), isolated semantic searches (use vector-composition), standalone reranks (use rerank), or simple author lookups (use people-graph).

vector-store

OperatingSystem-1

Store and retrieve knowledge using vector similarity search. Use for semantic search across learnings, documentation, and shared agent knowledge. Supports both local ChromaDB and shared Postgres (pgvector) stores. Use when you need persistent memory, cross-agent knowledge sharing, or semantic search over documents.

Azure.Search.Documents (.NET)

haniakrim21

Azure AI Search SDK for .NET (Azure.Search.Documents). Use for building search applications with full-text, vector, semantic, and hybrid search. Covers SearchClient (queries, document CRUD), SearchIndexClient (index management), and SearchIndexerClient (indexers, skillsets). Triggers: "Azure Search .NET", "SearchClient", "SearchIndexClient", "vector search C#", "semantic search .NET", "hybrid search", "Azure.Search.Documents".

weaviate

sharp-skills

Production-depth skill for Weaviate vector database operations. Use when asked to: configure Weaviate authentication and rotate API keys, set up cluster replication and horizontal scaling, migrate schemas without downtime, tune memory limits and handle resource pressure, import vectors with automatic or custom embeddings, perform hybrid/semantic/BM25 search, configure multi-tenancy for SaaS isolation, or troubleshoot backup hangs and crash panics in production deployments.

vector-database-patterns

sharp-skills

Stores and queries high-dimensional embeddings efficiently for semantic search, RAG, and similarity matching. Use when building semantic search, recommendation systems, RAG pipelines, or any feature requiring "find similar" functionality. Triggers on: vector search, semantic search, embeddings, RAG, similarity search, pgvector, Pinecone, Weaviate, Chroma, nearest neighbor, ANN.

hybrid-search-implementation

oki3505F

Combine vector and keyword search for improved retrieval. Use when implementing RAG systems, building search engines, or when neither approach alone provides sufficient recall.

memory-setup

frekyr17-png

Enable and configure Moltbot/Clawdbot memory search for persistent context. Use when setting up memory, fixing "goldfish brain," or helping users configure memorySearch in their config. Covers MEMORY.md, daily logs, and vector search setup.

Together Embeddings

zainhas

Generate text embeddings and rerank documents via Together AI. Embedding models include BGE, GTE, E5, UAE families. Reranking is done via the MixedBread reranker. Use this when users need text embeddings, vector search, semantic similarity, document reranking, RAG pipeline components, or retrieval-augmented generation.

AI Engineer

oki3505F

Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use proactively for LLM features, chatbots, AI agents, or AI-powered applications.